MACHINE LEARNING SYSTEMS AND METHODS FOR FACILITATING PARCEL COMBINATION
Machine learning systems and methods are described in regard to automating and acting upon evaluations of hypothetical assemblages of adjacent land parcels so as to allow a developer, owner, or other investor to see and act upon potential land uses that are not reflected in conventional valuations. Some variants include a feature augmentation protocol for speciating one or more detailed structures feasible for an assemblage, a pattern matching protocol for identifying viable assemblages that might suit a developer's requirements or implementing numerous simultaneous offers to numerous potential sellers whose decisions might affect project viability.
Latest Rebls, Inc. Patents:
- SYSTEMS, METHODS, AND PROGRAM PRODUCTS FOR FACILITATING PARCEL COMBINATION
- SYSTEMS AND METHODS FOR FACILITATING PARCEL COMBINATION
- Systems, methods, and program products for facilitating parcel combination
- SYSTEMS, METHODS, AND PROGRAM PRODUCTS FOR FACILITATING PARCEL COMBINATION
- SYSTEMS, METHODS, AND PROGRAM PRODUCTS FOR FACILITATING PARCEL COMBINATION
This disclosure claims priority to U.S. App. No. 62/965,104 filed 23 Jan. 2021 (entitled “Parcel Aggregation Facilitation Systems and Methods”), which is incorporated by reference herein in its entirety for all purposes.
BRIEF DESCRIPTION OF THE DRAWINGSThe detailed description that follows is represented largely in terms of processes and symbolic representations of operations by conventional computer components, including a processor, memory storage devices for the processor, connected display devices and input devices. Furthermore, some of these processes and operations may utilize conventional computer components in a heterogeneous distributed computing environment, including remote file servers, computer servers and memory storage devices.
It is intended that the terminology used in the description presented below be interpreted in its broadest reasonable manner, even though it is being used in conjunction with a detailed description of certain example embodiments. Although certain terms may be emphasized below, any terminology intended to be interpreted in any restricted manner will be overtly and specifically defined as such.
The phrases “in one embodiment,” “in various embodiments,” “in some embodiments,” and the like are used repeatedly. Such phrases do not necessarily refer to the same embodiment. The terms “comprising,” “having,” and “including” are synonymous, unless the context dictates otherwise.
“Above,” “accelerating,” “achieved,” “aggregate,” “any,” “application-type,” “application-specific,” “assembled,” “augmented,” “automatic,” “availability,” “based on,” “because,” “complete,” “comprising,” “conditional,” “configured,” “correlated,” “current,” “decelerating,” “decreasing,” “digital,” “directly,” “displayable,” “distributed,” “executed,” “first,” “given,” “higher,” “hybrid,” “implemented,” “in combination with,” “inalterable,” “included,” “indicated,” “inferred,” “integrated,” “malicious,” “matching,” “monotonic,” “more,” “mutually,” “multiple,” “negatively,” “of,” “otherwise,” “particular,” “partly,” “positively,” “prior,” “private,” “public,” “received,” “remote,” “requester-specified,” “responsive,” “scoring,” “second,” “seeding,” “sequencing,” “shorter,” “signaling,” “simultaneous,” “single,” “smart,” “so as,” “special-purpose,” “specific,” “stepwise,” “suitability,” “techniques,” “temporal,” “third,” “through,” “transistor-based,” “undue,” “updated,” “upon,” “utility,” “version-controlled,” “via,” “without,” or other such descriptors herein are used in their normal yes-or-no sense, not merely as terms of degree, unless context dictates otherwise. As used herein “inventory-type” instruction sets are those that primarily implement asset transfers or verifications thereof, moving quantities among accounts rather than changing them. As used herein “data transformative” instruction sets are those that primarily implement other kinds of computations. Although one of these types of instruction sets may invoke the other as a subroutine, only very rarely is a single code component of instructions a true hybrid.
In light of the present disclosure those skilled in the art will understand from context what is meant by “remote” and by other such positional descriptors used herein. Likewise they will understand what is meant by “partly based” or other such descriptions of dependent computational variables/signals. “On-chain” refers to (permanent) inclusion in a blockchain, whether or not such content is public or transparent. “On-list” encompasses not only on-chain but also other content linked and effectively rendered immutable using cryptography (e.g. in a consensus-based data verification). In an implementation that includes “on-list” content (e.g. a blockchain or tangle) as described below, “off-list” refers to content elements (e.g. an in-app account ledger) that have yet to be included “on-list.” A set of items is “numerous” if at least two dozen items are included. A “batch” data distribution (broadcast) is one in which data is directed to numerous recipients (i.e. dozens or more) within a limited time (e.g. less than 24 hours) after a triggering event (e.g. an administrator action or weekly trigger time). Terms like “processor,” “center,” “unit,” “computer,” or other such descriptors herein are used in their normal sense, in reference to an inanimate structure. Such terms do not include any people, irrespective of their location or employment or other association with the thing described, unless context dictates otherwise. “For” is not used to articulate a mere intended purpose in phrases like “circuitry for” or “instruction for,” moreover, but is used normally, in descriptively identifying special purpose software or structures.
Reference is now made in detail to the description of the embodiments as illustrated in the drawings. While embodiments are described in connection with the drawings and related descriptions, there is no intent to limit the scope to the embodiments disclosed herein. On the contrary, the intent is to cover all alternatives, modifications, and equivalents. In alternate embodiments, additional devices, or combinations of illustrated devices, may be added to, or combined, without limiting the scope to the embodiments disclosed herein.
As used herein, a plain reference numeral (e.g. like 490) may refer generally to a member of a class of items (e.g. like computing devices) exemplified with a hybrid numeral (e.g. like 490A) and it will be understood that every item identified with a hybrid numeral is also an exemplar of the class. Moreover although a reference numeral shared between figures refers to the same item, most figures depict respective embodiments.
Likewise such parcel assemblage-specific data 507 may include one or more instances of parcel assemblage identifiers 571, of parcel lists 573 for each respective parcel assemblage, of (protocols for) seeding 575 that define how seeding is/was done for a given species or specimen, of identifiers of speciation protocols 576 that define how speciation is/was done for a given species or specimen, of reference lot identifiers 577, of adjacent lot identifiers 578, or of other specimen-descriptive data 570 referenced herein. Alternatively or additionally such parcel assemblage-specific data 507 may include one or more instances of specimen-specific objective machine-learning-based scores 581, of determination dates 583 or similar evaluation data provenance, of scores reflecting subjective specimen compatibilities 584 (e.g. partly based on objective indicia and partly based on a preference model 514 of a potential buyer as described herein), of evaluation identifiers 586 that designate what each rank or other score herein signifies, of cycle counts 587 that designate how many recursions or other iterations of a protocol 576 were used in repeatably generating a given species 201 from its corresponding seeding 575, of current ranks 588 of each species hold relative to other generated species 201 of the same type, or other such augmented evaluation 580.
In some variants such operational data 505 may likewise include one or more instances of session or other user interaction dates 513 (e.g. signaling when an entity requested information); of preference models 514 (e.g. designating points or ranges of ideal parcel assemblage size, estimated price, or profit margin in a given investor's project or campaign); of search, presentation duration, or other action histories 515 by which such preference models may be derived; or of other such investor data 510.
In some variants such operational data 505 may likewise include one or more instances of historical or proposed prices 531; of option exercise or other fulfillment deadlines 532; of lists 534; of messages 535, of default values 537 (e.g. a designated value as described herein initially set by the system but available to change); of estimated returns on investment 538 or other figures of merit; of tracked module invocations 539 (whereby a task described herein is performed by a remote instance of one or more of the above-described modules 331-338 in response to a locally transmitted request); or of other acquisition data 530 pertaining to a potential or actual parcel availability described herein.
As used herein a “parcel assemblage” is a (nominally) contiguous set of real property parcels not all commonly owned. Two parcels are “contiguous” if they share a property line or if their respective boundaries are sufficiently proximate that the two parcels are adjacent. Two parcels can be “adjacent” across a public street only if they are suitable to be linked by a bridge, tunnel, or other artificial structure. As used herein an “instantaneous” response to a triggering event is one that is completed in less than one second after the triggering event. As used herein an operation is “deterministic” only if current temporal indicia and iteration-specific randomness do not affect its outcome. As used herein a protocol or other process is “deterministically repeatable” if seeding information, protocol identification, versions, and other operational data 505 is preserved (e.g. on a public blockchain 455) with sufficient fidelity and lasting accessibility that a mutation or other digital speciation thereof that was generated before may be perfectly and systematically re-created. A collection of geographic assemblages is referred to as “geographically dispersed” herein if more than half of the assemblages of the collection are each separated from all of the other assemblages in the collection by more than 100 meters. As used herein a parcel assemblage is “identified” by obtaining street addresses, boundary coordinates 361 or other legal definitions 372 that provide shape and position information, alphanumeric lot identifiers 548, or other such parcel-specific data 506 describing (serially or otherwise) adjacent parcels thereof.
Terms like “feature-augmentation-type” refer herein not only to feature augmentation per se but also to other technologies in which seeding or speciation are used for gleaning viable and detailed recommendation data (e.g. scores 581, ranks 588, merit-based default values, or other “better” configurations 872 initially presented in lieu of other available counterparts) derived from one or more profile tags or other heuristics. In light of teachings herein, for example, such seeding or speciation (or both) can be gleaned from a crowdsourced or other action history 515 so as to augment the features of the identified species without any undue experimentation.
Referring now to
With regard to data distillation as described herein, the selective inclusion of suitable parcel assemblages and viable structures depicted thereon are described herein as “pattern matching.” In the context of artificial intelligence, pattern matching is a branch of machine learning in which token sequences are searched for occurrences of (data corresponding to) a pattern. In light of technologies described herein, advanced machine learning may allow one or more servers described herein to overcome a computational barrier that previously made effective pattern matching in regard to structures that could be built on a regional assortment of parcel assemblages computationally prohibitive. As described herein, various technologies allow artificial intelligence to generate, sift, and selectively present vetted hypothetical structures automatically. Terms like “pattern-matching-type” refer herein not only to pattern matching per se but also to prioritization and other technologies in which one or more sequences of tokens are searched for occurrences of suitable adjacent land parcels for assemblage analysis, ranking, or recommendation (e.g. in an image 896 presented to a display screen 812). In a virtual or augmented reality implementation, for example, such assemblages and virtual structures thereon may come into view as a device 900 approaches and enters a corresponding physical location.
Referring now to
Memory 904 may contain one or more instances of operating systems 910, web browsers 914, and local apps 924. These and other software components may be loaded from a non-transitory computer readable storage medium 918 into memory 904 of the client device 900 using a drive mechanism (not shown) associated with a non-transitory computer readable storage medium 918, such as a floppy disc, tape, DVD/CD-ROM drive, flash card, memory card, or the like. In some embodiments, software components may also be loaded via the network interface 906, rather than via a computer readable storage medium 918. Special-purpose circuitry 922 may, in some variants, include some or all of the event-sequencing logic described herein as transistor-based circuitry 354 (e.g. in a peer-to-peer implementation) and one or more security features 960 (e.g. a fob or similar security apparatus).
In some contexts security feature 960 may implement or otherwise interact with a removable or other digital wallet 966. Such wallets may (optionally) each include one or more instances of private keys of utility tokens, of crypto currency, of provenance data, or of device-executable code snippets (e.g. smart contracts) configured to perform one or more functions as described below. In some embodiments client device 900 may include many more components than those shown in
Referring now to
Memory 1004 may contain one or more instances of operating systems 1010, hosted websites 1020, and aggregation modules 1026. These and other software components may be loaded from a non-transitory computer readable storage medium 1018 into memory 1004 of the server 1000 using a drive mechanism (not shown) associated with a non-transitory computer readable storage medium 1018, such as a floppy disc, tape, DVD/CD-ROM drive, flash card, memory card, or the like. In some embodiments, software components may also be loaded via the network interface 1006, rather than via a computer readable storage medium 1018. Special-purpose circuitry 1022 may, in some variants, include some or all of the event-sequencing logic described with reference to
After an implementation delay 1149 of several additional hours or days, such focused search parameters 1145 may have been used by the development server(s) 1000C to develop additional parcel assemblages (and species thereof) of likely interest (as manifested by a compatibility 584, rank 588, or other score 581 thereof) in an enhanced inventory 1150B. Moreover prior offers or other available owner data 550, contractual restriction status may be useful to update 1160 to facilitate real-time parcel selection refinement 1170, offer customization 1185, and the resulting firm offers or other offer-descriptive content 1190 being distributed to owners of parcels of confirmed interest.
The following table illustrates a root genetic algorithm suitable for use (e.g. by one or more development servers 1000C) in one or more variants described herein:
The following table illustrates an arena sizing algorithm suitable for use (e.g. by one or more development servers 1000C) in some variants described herein:
The following table illustrates a single-shelter algorithm suitable for use in some speciation described herein:
The following table illustrates a multi-building algorithm suitable for use in other speciation described herein:
Clause 1377B includes a background statement identifying (at least) a published information source 1346 (e.g. “tax records”), a street address 1347, and a corresponding published valuation 380 (e.g. “According to Zillow, your property at 1623 Main Street is worth $176,475”). Clause 1377B also presents an offer-descriptive statement featuring a proposed payment amount 1345 identified by a natural-language description 1316 (e.g. “earnest money” or “option purchase price”), and a payment mode identifier 1317 (e.g. “wire transfer” or “cashier's check”) intended to entice the owner (e.g. “We want to give you a $1000 down payment immediately, directly via Venmo today.”)
Clause 1377C includes additional transaction terms 890 including a proposed duration 1328 and a request for a phone number or other requested contact information 1346 to facilitate the inchoate transaction (e.g. “It may take 18 months for us to decide whether to complete the purchase, but either way you keep the $1000. Does that sound fair? If so, please reply with your phone number.”). Clause 1377D includes additional transaction terms 890 (e.g. “Please note that if you accept the $1000, you will have entered a legally binding contract. Also please note that another seller might accept this $1000 on a similar property if you do not reply quickly. This is a ‘first come, first serve’ opportunity.”). Clause 1377E includes a reference to further transaction terms (e.g. “Detailed terms for this contract are provided below.”). Following the salutation and signature, the prospective buying entity may self-identify with a place name 1367 local to the reference parcel or an area code 1368 local to the reference parcel.
Operation 1415 describes obtaining an identification of first and second assemblages both containing a reference parcel, wherein the first assemblage includes a first parcel adjacent the reference parcel in combination with the reference parcel, wherein the second assemblage includes a second parcel adjacent the reference parcel in combination with the reference parcel, and wherein a reference recordation signals that the reference parcel is not commonly owned with the first or second parcels (e.g. one or more assemblage modules 331 receiving or generating an identification of component parcels in respective first and second parcel assemblages 121, 122 both containing a reference parcel 160, wherein the first parcel assemblage 121 includes a first parcel 161 adjacent the reference parcel 160 in combination with the reference parcel 160, wherein the second parcel assemblage 122 includes a second parcel 162 adjacent the reference parcel 160 in combination with the reference parcel 160, and wherein one or more public records 558 signal that the reference parcel 160 is not commonly owned with the first parcel 161 or with the second parcel 162). This can occur, for example, in a context in which each assemblage module 331 manifests lot identifiers 547-548, boundary coordinates 361, and other such information about the parcels as respective (instances of) voltage configurations 351 thereof.
Operation 1430 describes recursively or otherwise obtaining first and second building models of the first assemblage each based on a respective application of first and second deterministically repeatable speciation protocols to a first multi-parcel-assemblage-specific seeding configuration associated with the first assemblage (e.g. an instance of a speciation module 333 obtaining first and second deterministically identified instances of species 201 including one or more simulated building models 202 depicted upon the first parcel assemblage 121 wherein each such species 201 is based on a respective application 877 of at least first and second speciation protocols 576 to a first multi-parcel-assemblage-specific seeding configuration associated with the first parcel assemblage 121). This can occur, for example, in a context in which the first speciation protocol 576 comprises a single-shelter algorithm like that of Table 3 herein; in which the second (instance of a) speciation protocol 576 comprises a multi-building model algorithm like that of Table 4 herein; and in which seeding 575 for such algorithms comprises a reference lot identifier 547, street address 1347, coordinates 361, or other repeatable designation of the reference lot 160 together with a repeatable designation of other parcels of the first parcel assemblage 121 as respective voltage configurations 353.
Operation 1440 describes recursively obtaining first and second building models of the second assemblage each based on a respective application of first and second deterministically repeatable speciation protocols to a first multi-parcel-assemblage-specific seeding configuration associated with the second parcel assemblage (e.g. a second instance of a speciation module 333 obtaining first and second deterministic instances of species 201 including one or more simulated building models 202 depicted at least partly upon the second parcel assemblage 122, wherein each such species 201 is based on an application 877 of respective speciation protocols 576 to a multi-parcel-assemblage-specific seeding 575 associated with the second parcel assemblage 122). This can occur, for example, in a context in which the “first” speciation protocol 576 is a multi-building model algorithm like that of Table 4 herein; in which the “second” speciation protocol 576 is a single-shelter algorithm like that of Table 3 herein; and in which seeding 575 for such algorithms comprises a reference lot identifier 547 or other repeatable designation of the reference lot 160 together with a repeatable designation of other parcels of the second parcel assemblage 122 as respective voltage configurations 353.
Operation 1450 describes causing the first building model of the first assemblage to be prioritized over the second building model of the first assemblage and to be presented to a user of a visual display in lieu of the second building model based on a machine-learning-based scoring protocol (e.g. a first instance of an evaluation module 334 causing a first species 201 of the first parcel assemblage 121 to be ranked above a second instance of an alternative species of the first parcel assemblage 121 and to be presented to an entity 10C using one or more display screens 912 in lieu of the alternative species based on a machine-learning-based score 581, rank 588, or other evaluation). This can occur, for example, in a context in which such evaluation data 580 comprises explicit preferences from the entity 10C; a preference model 514 derived from search, presentation duration, or other user action history 515; or no preference data at all. Alternatively or additionally, such preference data relating to one or more entities 10 may be obtained or used (or both) as a component of a supervised-learning-type protocol 576.
Terms like “supervised-learning-type” refer herein not only to supervised learning per se but also to other technologies in which input data is mapped to output data based on training data that pairs numerous vector-valued input objects (e.g. defining assemblages, speciations, or other such operational data 505) each to a corresponding desired output value (e.g. a valuation 380, score 581, selection, rank 588, authorization, or other user-provided preference indication) using one or more user-provided inductive biases (e.g. observed user actions 894). In light of teachings herein, for example, such machine learning implementations can be gleaned from search terms 890 or other user inputs 908 from such entities 10 without any undue experimentation.
Operation 1465 describes causing the first building model of the second assemblage to be prioritized over the second building model of the second assemblage, to displace the first building model of the first assemblage, and to be presented via the visual display in lieu of the second building model of the second assemblage all partly based on the machine-learning-based scoring protocol and partly based on one or more preference-indicative actions of the user of the visual display (e.g. a second instance of an evaluation module 334 and one or more indexing modules 335 jointly causing the first species 201 of the second parcel assemblage 122 to be deemed preferable over the second species of the second parcel assemblage 122; to replace or partly occlude a rendering of the first species 201 of the first parcel assemblage 121; and to be presented to the user in lieu of the second species of the second parcel assemblage 122 partly based on the machine-learning-based scoring protocol and partly based on one or more preference-indicative actions of the user). This can occur, for example, in a context in which an evaluation module 334 manifests an identifier of the first parcel assemblage as a voltage configuration 354 thereof; in which the rendering of the first species 201 of the first parcel assemblage 121 is thereby initially presented to the user; in which an indexing module 335 manifests a touchscreen activation or other preference-indicative user action as a voltage configuration 355 to index to a next-most-preferable option; in which the visual display presents (the first species 201 of) the second parcel assemblage 122 in response 825; and in which multiple visual display devices would otherwise be required to allow the automatically created message draft to be tailored by the user before transmission.
Operation 1480 describes causing a draft offer-descriptive message containing a parcel identifier, a parcel valuation, and a premium valuation to be presented simultaneously via the visual display as a real-time response to a request associated with the reference parcel following a presentation of one or more such building models via the visual display (e.g. one or more configuration modules 337 causing a draft offer-descriptive message 1335 containing a street address 1347 or other lot identifier 247; a public-records or independent-party-provided parcel valuation 380; and premium valuation 1338 10-50% higher than the prior parcel valuation 380 to be presented simultaneously via the one or more display screens 912 as a real-time response 825 to a request associated with the reference parcel 160 following a presentation of one or more such building models 202 corresponding to the message 1335). This can occur, for example, in a context in which the configuration module(s) 137 manifest the draft message 1335 in a memory (e.g. as a voltage configuration 357 on electrical nodes 347 thereof) and in which parcel adjacency would not otherwise get appropriately proactive consideration when undertaking to acquire real property parcels from multiple respective sellers.
Operation 1490 describes causing numerous additional pairings of a subject parcel identifier with a corresponding valuation to be presented together after a corresponding building model all within a one-hour period (e.g. one or more response modules 336 serially or otherwise causing dozens of additional pairings of a street address 1347 of a subject parcel 160 each with a corresponding published or other conventional valuation 380 of that parcel to be presented together after a corresponding species 201 of a preferable parcel assemblage 121 of that parcel all within a one-hour period). This can occur, for example, in a context in which the user has reviewed parcel assemblages 121-122 and corresponding species 201 as a semi-automatic protocol for validating parcel suitability; in which the response module(s) 336 manifest such pairings in a proposed offer batch of more than half of the parcels in those validated parcel assemblages; in which the user has reviewed a draft (version of a) message 1335 for at least one such parcel on a prior occasion; in which such validations are manifested as a voltage configuration 356 on electrical nodes 346 thereof); in which a transmission module 338 may thereafter send such offer-descriptive content 1190 to email or other addresses 553 associated with each owner name 551 thereof; and in which a strategically adequate number (i.e. more than 12) of contemporaneous parallel offers (i.e. all within the one-hour period) all based on the same machine-learning-based scoring protocol would otherwise remain unattainable. Alternatively or additionally, the “corresponding” valuations may include premium valuations 1338 each at least partly based on a conventional valuation 380 of the subject parcel (derived as a markup percentage designated by the user, e.g.).
In light of teachings herein, numerous existing techniques may be applied for configuring special-purpose circuitry or other structures effective for obtaining real property data and presenting key aspects of potential developments thereon as described herein without undue experimentation. See, e.g., U.S. Pat. No. 10,528,652 (“Generating predictive models for authoring short messages”); U.S. Pat. No. 10,521,943 (“Lot planning”); U.S. Pat. No. 10,521,865 (“Structural characteristic extraction and insurance quote generation using 3D images”); U.S. Pat. No. 10,510,087 (“Method and apparatus for conducting an information brokering service”); U.S. Pat. No. 10,459,981 (“Computerized system and method for automatically generating and providing interactive query suggestions within an electronic mail system”); U.S. Pat. No. 10,496,927 (“Systems for time-series predictive data analytics, and related methods and apparatus”); U.S. Pat. No. 10,467,353 (“Building model with capture of as built features and experiential data”); U.S. Pat. No. 10,387,414 (“High performance big data computing system and platform”); U.S. Pat. No. 10,382,383 (“Social media post facilitation systems and methods”); U.S. Pat. No. 10,198,735 (“Automatically determining market rental rate index for properties”); U.S. Pat. No. 10,192,275 (“Automated real estate valuation system”); U.S. Pat. No. 10,190,791 (“Three-dimensional building management system visualization”); U.S. Pub. No. 20170109668 (“Model for Linking Between Nonconsecutively Performed Steps in a Business Process; and U.S. Pub. No. 20170109638 (“Ensemble-Based Identification of Executions of a Business Process”).
In light of teachings herein, numerous existing techniques may be applied for configuring special-purpose circuitry or other structures effective for applying machine learning, blockchain, and other land-related data distillation as described herein without undue experimentation. See, e.g., U.S. Pat. No. 10,897,650 (“Vehicle content recommendation using cognitive states”); U.S. Pat. No. 10,889,925 (“Augmented reality system for stitching along a predetermined path”); U.S. Pat. No. 10,861,187 (“Method of processing object detection data”); U.S. Pat. No. 10,853,398 (“Generating three-dimensional digital content from natural language requests”); U.S. Pat. No. 10,846,873 (“Methods and apparatus for autonomous robotic control”); U.S. Pat. No. 10,839,431 (“Systems, methods and computer program products for cross-marketing related products and services based on machine learning algorithms involving field identifier level adjacencies”); U.S. Pat. No. 10,839,297 (“System and method for configuration of an ensemble solver”); U.S. Pat. No. 10,657,375 (“Augmented reality system for facilitating currency conversion”); U.S. Pat. No. 10,565,329 (“System and method for modelling system behaviour”); U.S. Pat. No. 10,521,508 (“Natural language processing for extracting conveyance graphs”); U.S. Pat. No. 10,373,073 (“Creating deep learning models using feature augmentation”); U.S. Pat. No. 10,297,129 (“Fire/security service system with augmented reality”); U.S. Pat. No. 10,204,362 (“Marketplace listing analysis systems and methods”); U.S. Pat. No. 9,770,189 (“Systematic distillation of status data relating to regimen compliance”); U.S. Pat. No. 9,746,913 (“Secured mobile maintenance and operator system including wearable augmented reality interface, voice command interface, and visual recognition systems and related methods”); U.S. Pat. No. 9,576,083 (“Automatic driver modeling for integration of human-controlled vehicles into an autonomous vehicle network”); and U.S. Pat. No. 9,245,229 (“Occupancy pattern detection, estimation and prediction”).
Operation 1535 describes obtaining multiple building models of each of the assemblages each based on a respective application of multiple deterministically repeatable speciation protocols to a respective multi-parcel-assemblage-specific seeding configuration (e.g. one or more speciation modules 333 generally configured and invoked as described above).
Operation 1550 describes causing a first building model of a first assemblage thereof to be prioritized over a second building model of the first assemblage and to be presented via a visual display based on a given scoring protocol (e.g. one or more evaluation module 334 generally configured and invoked as described above). This can occur, for example, in a context in which such diverse, selective, and controllable presentations allow a developer to see and act upon vetted search results that could not have been visualized via a single display screen 812 and in which such complex arrangements of property transfers would otherwise be too diffuse to allow any such multi-parcel-assemblage-specific development to occur without government compulsion or significant duress.
Operation 1680 describes causing a subsequent presentation of a parcel identifier simultaneously with a corresponding premium valuation at least partly based on a prior valuation thereof (e.g. one or more response, configuration, and transmission modules 356-358 generally configured and cooperatively invoked as described above).
Although various operational flows are presented in a sequence(s), it should be understood that the various operations may be performed in other orders than those which are illustrated or may be performed concurrently. Examples of such alternate orderings may include overlapping, interleaved, interrupted, reordered, incremental, preparatory, supplemental, simultaneous, reverse, or other variant orderings, unless context dictates otherwise. Furthermore, terms like “responsive to,” “related to,” or other past-tense adjectives are generally not intended to exclude such variants, unless context dictates otherwise.
While various system, method, article of manufacture, or other embodiments or aspects have been disclosed above, also, other combinations of embodiments or aspects will be apparent to those skilled in the art in view of the above disclosure. The various embodiments and aspects disclosed above are for purposes of illustration and are not intended to be limiting, with the true scope and spirit being indicated in the final claim set that follows.
In the numbered clauses below, first combinations of aspects and embodiments are articulated in a shorthand form such that (1) according to respective embodiments, for each instance in which a “component” or other such identifiers appear to be introduced (e.g., with “a” or “an,”) more than once in a given chain of clauses, such designations may either identify the same entity or distinct entities; and (2) what might be called “dependent” clauses below may or may not incorporate, in respective embodiments, the features of “independent” clauses to which they refer or other features described above.
CLAUSES1. A machine learning method for facilitating multi-parcel development (e.g., comprising one or more data flows 1100, 1200 or operational flows 1400, 1500, 1600 described above) comprising:
invoking transistor-based circuitry (e.g. one or more instances of assemblage modules 331) configured to obtain (at least) an identification of first and second assemblages 121, 122 wherein the first assemblage 121 includes a first parcel 161 adjacent the particular parcel 160 in combination with the particular parcel 160 and wherein the second assemblage 122 likewise includes a second parcel 162 adjacent the particular parcel 160 in combination with the particular parcel 160;
invoking transistor-based circuitry (e.g. one or more instances of speciation modules 333) configured to obtain first and second building models 202 of the first assemblage 121 each based on a respective application 877 of first and second speciation protocols 576 to a first multi-parcel-assemblage-specific seeding configuration 872 associated with the first assemblage 121; and
invoking transistor-based circuitry (e.g. another one or more instances of speciation modules 333) configured to obtain first and second building models 202 of the second assemblage 122 each based on a respective application 877 of first and second speciation protocols 576 to a first multi-parcel-assemblage-specific seeding configuration 872 associated (at least) with the second assemblage 122.
2. The machine learning method of any of the above Clauses wherein the first speciation protocol 576 comprises a multi-building model algorithm like that of Table 4 herein.
3. The machine learning method of any of the above Clauses wherein the second speciation protocol 576 comprises a single-shelter algorithm like that of Table 3 herein.
4. The machine learning method of any of the above Clauses wherein the first and second speciation protocols 576 each comprise a multi-building model algorithm or single-shelter algorithm and wherein seeding 575 for such algorithms comprises a (set of coordinates 361, dimensions 362, or other) repeatable designation of the reference lot 160 together with a repeatable designation of the other parcel(s) thereof.
5. The machine learning method of any of the above Clauses comprising:
triggering a supervised-learning-type protocol 576 that includes pairing numerous vector-valued input objects (e.g. as operational data 505) each to a corresponding output value using one or more user-provided inductive biases (e.g. observed user actions 894).
6. The machine learning method of any of the above Clauses comprising:
triggering a supervised learning protocol 576 that includes pairing first input data that includes the first assemblage 121 with a corresponding indication of user preference (e.g. activating a control 895 depicted in an image 896 of the first assemblage 121).
7. The machine learning method of any of the above Clauses comprising:
triggering a supervised learning protocol 576 that includes pairing numerous vector-valued input objects each to a corresponding desired output value (e.g. a valuation 380, score 581, selection, rank 588, authorization, or other user-provided preference indication) using one or more user-provided inductive biases.
8. The machine learning method of any of the above Clauses comprising:
triggering a supervised learning protocol 576 that includes pairing numerous vector-valued input objects each to a corresponding desired output value (e.g. a valuation 380, score 581, selection, rank 588, authorization, or other user-provided preference indication) using one or more user-provided inductive biases.
9. The machine learning method of any of the above Clauses comprising:
triggering a feature augmentation protocol 576 that includes an application 877 of the first and second speciation protocols to the first multi-parcel-assemblage-specific seeding configuration 872 associated with the first assemblage 121.
10. The machine learning method of any of the above Clauses comprising:
extracting one or more pattern definition terms 890 for use in a pattern matching protocol 576 as user input.
11. The machine learning method of any of the above Clauses comprising:
triggering a pattern-matching-type protocol 576 that determines a selective first inclusion of the first assemblage in a geographical map 360.
12. The machine learning method of any of the above Clauses comprising:
triggering a pattern matching protocol 576 that determines a selective first inclusion of the first assemblage in a geographical map 360 of a development site 211, neighborhood, city 546, or other region 111 (e.g. as an inventory 1150 of matching models 202 or assemblages that excludes some others in the region 111 that were not matching).
13. The machine learning method of any of the above Clauses comprising:
triggering a pattern matching protocol 576 that determines a selective first inclusion of the first assemblage and a selective exclusion of one or more other assemblages within 5 kilometers of the first assemblage 121 both (at least partly) based on the application 877 of the first and second speciation protocol to the first multi-parcel-assemblage-specific seeding configuration 872 associated with the first assemblage 121.
14. The machine learning method of any of the above Clauses comprising:
triggering a pattern matching protocol 576 that determines a selective first inclusion of the first assemblage and a selective exclusion of one or more other assemblages within 5 kilometers of the first assemblage 121 both partly based on the application 877 of the first and second speciation protocol to the first multi-parcel-assemblage-specific seeding configuration 872 associated with the first assemblage 121 and an application 877 of the first and second speciation protocol to the first multi-parcel-assemblage-specific seeding configuration 872 associated with the one or more other assemblages.
15. The machine learning method of any of the above Clauses comprising:
triggering a feature-augmentation-type protocol 576 that includes obtaining an other building model by gleaning a user-provided inductive bias manifesting a first inferred preference for (a result of) a first speciation protocol, generating the other building model using the first speciation protocol in lieu of the second speciation protocol, and displaying the other building model simultaneously with the first building model 202.
16. The machine learning method of any of the above Clauses comprising:
triggering a feature augmentation protocol 576 that includes obtaining an other (instance of a) building model by gleaning a user-provided inductive bias manifesting a first inferred (apparent user) preference for a first speciation protocol, generating the other building model using the first speciation protocol in lieu of the second speciation protocol, and displaying the other building model simultaneously with the first building model 202 (e.g. by showing both in a map 360 of a city that includes both assemblages thereof).
17. The machine learning method of any of the above Clauses wherein the method combines a supervised learning protocol 576 with a pattern matching protocol 576.
18. The machine learning method of any of the above Clauses wherein the method combines a pattern matching protocol 576 with a feature augmentation protocol 576.
19. The machine learning method of any of the above Clauses wherein the method combines a feature augmentation protocol 576 with a supervised learning protocol 576.
20. The machine learning method of any of the above Clauses wherein a comparison 879 among one or more records 558 signals that the particular parcel 160 is not commonly owned with the first parcel 161 or with the second parcel 162 (or with both).
21. The machine learning method of any of the above Clauses comprising:
invoking transistor-based circuitry (e.g. one or more instances of evaluation modules 334) configured to cause the first building model 202 of the first assemblage 121 to be prioritized over the second building model 202 of the first assemblage 121 and to be presented to a user of a visual display 812 (e.g. an entity 10C using one or more display screens 912) in lieu of the second building model 202 based on a programmatic scoring protocol 576 (e.g. a machine-learning-based score 581, rank 588, or other valuation 380);
22. The machine learning method of any of the above Clauses comprising:
causing numerous additional assemblages 121 to be depicted all via a single display screen 912 all within a one-hour period 892 wherein each of the additional assemblages 121 links a corresponding parcel 160 to at least one corresponding adjacent parcel 161 with which the corresponding parcel 160 is adjacent and wherein the corresponding parcels 160 include the particular parcel 160.
23. The machine learning method of any of the above Clauses comprising:
causing a collection of numerous additional assemblages 121 to be depicted all via a single display screen 912 all within a ten-minute period 892 wherein each of the additional assemblages 121 links a corresponding parcel 160 to at least one corresponding adjacent parcel 161 with which the corresponding parcel 160 is adjacent and wherein the corresponding parcels 160 include the particular parcel 160.
24. The machine learning method of any of the above Clauses comprising:
causing a geographically dispersed collection of numerous additional assemblages 121 to be depicted all via a single display screen 912 all within a ten-minute period 892 wherein each of the additional assemblages 121 links a corresponding parcel 160 to at least one corresponding adjacent parcel 161 with which the corresponding parcel 160 is adjacent, wherein more than half of the numerous additional assemblages 121 are separated from the other additional assemblages 121 by more than 100 meters, and wherein the corresponding parcels 160 include the particular parcel 160.
25. The machine learning method of any of the above Clauses comprising:
causing a first digital resource 891 to be offered (in overlapping time periods 892 or otherwise) simultaneously for many of the additional assemblages 121 via one or more smart contracts 885 on a first-come first-served basis so that one or more options 884 presented in regard to some of the additional assemblages 121 are (nominally) withdrawn via the one or more smart contracts 885 as an automatic and conditional response 825 to the first digital resource 891 being claimed in association with the particular parcel 160.
26. The machine learning method of any of the above Clauses comprising:
causing a first digital resource 891 to be offered simultaneously for many of the additional assemblages 121 on a first-come first-served basis so that one or more options 884 presented in regard to some of the additional assemblages 121 are withdrawn as an automatic and conditional response 825 to the first digital resource 891 being claimed in association with the particular parcel 160.
27. The machine learning method of any of the above Clauses comprising:
transmitting one or more messages 535 signaling the first digital resource 891 being claimed in association with the particular parcel 160 after transmitting (at least) the first digital resource 891 via one or more smart contracts 885 as an automatic and conditional instantaneous response 825 to the first digital resource 891 being claimed in association with the particular parcel 160.
28. The machine learning method of any of the above Clauses comprising:
transmitting one or more messages 535 signaling the first digital resource 891 being claimed in association with the particular parcel 160.
29. The machine learning method of any of the above Clauses comprising:
transmitting (at least) the first digital resource 891 as an automatic and conditional response 825 to the first digital resource 891 being claimed in association with the particular parcel 160.
30. The machine learning method of any of the above Clauses comprising:
causing a first digital resource 891 to be offered simultaneously for many of the additional assemblages 121 on a first-come first-served basis so that one or more options 884 presented to entities 10 that own a majority of the additional assemblages 121.
31. The machine learning method of any of the above Clauses comprising:
causing a first digital resource 891 to be offered simultaneously for many of the additional assemblages 121 on a first-come first-served basis so that one or more options 884 presented in regard to some of the additional assemblages 121 are (nominally) withdrawn as an automatic and conditional response 825 to the first digital resource 891 being claimed in association with the particular parcel 160.
32. The machine learning method of any of the above Clauses comprising:
transmitting one or more messages 535 via a visual display 812, 912 signaling the first digital resource 891 being claimed in association with the particular parcel 160 and transmitting (at least) the first digital resource 891 both as an automatic and conditional response 825 to the first digital resource 891 being claimed in association with the particular parcel 160.
33. The machine learning method of any of the above Clauses comprising:
invoking transistor-based circuitry (e.g. another one or more instances of speciation modules 333) configured to obtain first and second building models 202 of a third assemblage 123 based on an application 877 of the one or more other speciation protocols 576 to a first multi-parcel-assemblage-specific seeding configuration 872 associated with the third assemblage 123; and
invoking transistor-based circuitry (e.g. one or more instances of evaluation modules 334) configured to cause the first building model 202 of the third assemblage 123 to be prioritized over the one or more building models 202 of the first and second assemblages 121, 122 and to be signaled to the user 10 of the visual display 812 (at least partly) based on a programmatic scoring protocol 576.
34. The machine learning method of any of the above Clauses comprising:
invoking transistor-based circuitry (e.g. another one or more instances of speciation modules 333) configured to obtain first and second building models 202 of a third assemblage 123 based on an application 877 of the one or more other speciation protocols 576 to a first multi-parcel-assemblage-specific seeding configuration 872 associated with the third assemblage 123; and
invoking transistor-based circuitry (e.g. one or more instances of evaluation modules 334) configured to cause the first building model 202 of the third assemblage 123 to be prioritized over the one or more building models 202 of the first and second assemblages 121, 122 and to be signaled to the user 10 of the visual display 812 at least partly based on a programmatic scoring protocol 576 and partly based on another digital resource 891 having been claimed in association with one or more parcels of the third assemblage 123.
35. The machine learning method of any of the above Clauses wherein the one or more records 558 signal that the particular parcel 160 is not commonly owned with the first parcel 161 and wherein the one or more records 558 signal that the particular parcel 160 is not commonly owned with the second parcel 162.
36. The machine learning method of any of the above Clauses wherein the one or more records 558 signal that the particular parcel 160 is not commonly owned with the first parcel 161 and wherein the one or more records 558 signal that the particular parcel 160 is not commonly owned with the second parcel 162 and wherein the first and second assemblages 121, 122 are automatically included in an inventory 1150 as a conditional response 825 to information 860 in the one or more records 558 indicating that at least the first and second parcels 161, 162 are not commonly owned with one another.
37. The machine learning method of any of the above Clauses comprising:
causing the first building model of the second assemblage 122 to be presented via the visual display 812, 912 in lieu of the second building model of the second assemblage 122 partly based on the programmatic scoring protocol and partly based on one or more preference-indicative actions 894 of the user of the visual display 812, 912 (e.g. as a contemporaneous direct or other response 825 to an action of the user signaling interest in the particular parcel).
38. The machine learning method of any of the above Clauses comprising:
invoking transistor-based circuitry (e.g. one or more instances of evaluation modules 334) configured to cause the first building model 202 of an other assemblage to be prioritized over (at least) the first and second assemblages 121, 122 and to displace the first or second assemblage 121, 122 partly based on the programmatic scoring protocol 576 and partly based on a first preference-indicative action 894 of the user of the visual display 812, 912 (e.g. as a contemporaneous direct or other response 825 to the first preference-indicative action 894 of the user signaling interest in the particular parcel).
39. The machine learning method of any of the above Clauses comprising:
invoking transistor-based circuitry (e.g. one or more instances of evaluation modules 334) configured to cause the first building model 202 of the first assemblage 121 to be prioritized over the second building model 202 of the first assemblage 121 and to be presented to a user of a visual display (e.g. an entity 10C using one or more display screens 912) in lieu of the second building model 202 based on a programmatic scoring protocol 576.
40. The machine learning method of any of the above Clauses comprising:
applying one or more deterministically repeatable speciation protocols 576 as the applications 877 of the first and second speciation protocols 576 respectively to the first multi-parcel-assemblage-specific seeding configuration 872 associated with the first and second assemblages 121, 122.
41. The machine learning method of any of the above Clauses comprising:
applying one or more deterministically repeatable speciation protocols 576 as the applications 877 of the first and second speciation protocols 576 respectively to the first multi-parcel-assemblage-specific seeding configuration 872 associated with the first and second assemblages 121, 122 by causing a recordation of one or more parameters (as operational data 505) thereof on a public blockchain 455.
42. The machine learning method of any of the above Clauses comprising:
implementing the programmatic scoring protocol 576 to include a determination of one or more machine-learning-based assemblage valuations 380 as components of the programmatic scoring protocol 576.
43. The machine learning method of any of the above Clauses comprising:
implementing the programmatic scoring protocol 576 to include a determination of one or more machine-learning-based scores 581 as components of the programmatic scoring protocol 576.
44. The machine learning method of any of the above Clauses comprising:
implementing the programmatic scoring protocol 576 to include a determination of one or more machine-learning-based ranks 588 as components of the programmatic scoring protocol 576.
45. A machine learning system configured to perform any of the above-described methods.
46. A machine learning system 300, 400, 800 for facilitating multi-parcel development, the system comprising:
transistor-based circuitry (e.g. one or more instances of assemblage modules 331) configured to obtain an identification of (at least) first and second assemblages 121, 122 wherein the first assemblage 121 includes a first parcel 161 adjacent the particular parcel 160 in combination with the particular parcel 160, wherein the second assemblage 122 likewise includes a second parcel 162 adjacent the particular parcel 160 in combination with the particular parcel 160, and wherein one or more records 558 signal that the particular parcel 160 is not commonly owned with the first parcel 161 or with the second parcel 162 (or with both);
transistor-based circuitry (e.g. one or more instances of speciation modules 333) configured to obtain first and second building models 202 of the first assemblage 121 each based on (at least) a respective application 877 of first and second speciation protocols 576 to a first multi-parcel-assemblage-specific seeding configuration 872 associated with the first assemblage 121; and
transistor-based circuitry (e.g. another one or more instances of speciation modules 333) configured to obtain first and second building models 202 of the second assemblage 122 each based on a respective application 877 of first and second speciation protocols 576 (at least) to a first multi-parcel-assemblage-specific seeding configuration 872 associated with the second assemblage 122.
47. The machine learning system of Clause 45 wherein (at least two of) the mentioned instances of transistor-based circuitry are geographically remote from one another (i.e. more than 1 kilometer apart).
48. The machine learning system of Clause 45 wherein all of the mentioned instances of transistor-based circuitry reside within a single device (e.g. an ASIC).
49. The machine learning system of any of the above systems (e.g. Clause 45 et seq.) including a first indexing module 335 that comprises:
transistor-based circuitry 330 configured to manifest an activation of a control 895 as a voltage configuration 355 to index to a next-most-preferable option, wherein such indexing modifies a user selection.
50. The machine learning system of any of the above systems including a first response module 336 that comprises:
transistor-based circuitry 330 configured to generate a conditional response 825 in which numerous parcels 160 in a region 111 each undergoes one or more augmentations, disqualifications, or other such distillations (see
51. The machine learning system of any of the above systems including a first configuration module 337 that comprises:
transistor-based circuitry 330 configured to produce a natural-language message 1335 or other signal identifying one or more subject parcels or other components of an assemblage for which one or more building models 202 have been presented.
52. The machine learning system of any of the above systems including a first transmission module 338 that comprises:
transistor-based circuitry 330 configured to transmit one or more inquiries 883 or related resources 891, optionally including a component thereof sent to a cryptographically secured digital wallet 966 that receives or provides the one or more resources 891.
53. The machine learning system of any of the above systems including a first transmission module 338 that comprises:
transistor-based circuitry 330 configured to transmit one or more inquiries 883 or related resources 891, optionally including a component thereof sent to one or more mining rigs that comprise proof-of-work blockchain node devices 490A, 490C.
54. The machine learning system of any of the above systems including a first transmission module 338 that comprises:
transistor-based circuitry 330 configured to transmit one or more inquiries 883 or related resources 891, optionally including a component thereof sent to one or more stake authority nodes that comprise proof-of-stake blockchain node devices 490B, 490F.
55. The machine learning system of any of the above systems including a first invocation module 332 that comprises:
transistor-based circuitry 330 configured to perform an instance of one or more other modules by delegation (e.g. by triggering one or more functions thereof to be performed abroad or in one or more cloud servers 1000.
With respect to the numbered claims expressed below, those skilled in the art will appreciate that recited operations therein may generally be performed in any order. Also, although various operational flows are presented in sequence(s), it should be understood that the various operations may be performed in other orders than those which are illustrated or may be performed concurrently. Examples of such alternate orderings may include overlapping, interleaved, interrupted, reordered, incremental, preparatory, supplemental, simultaneous, reverse, or other variant orderings, unless context dictates otherwise. Furthermore, terms like “responsive to,” “related to,” or other such transitive, relational, or other connections do not generally exclude such variants, unless context dictates otherwise.
Claims
1-7. (canceled)
8. A pattern matching method for facilitating multi-parcel development, comprising:
- invoking first transistor-based circuitry configured to obtain an identification of first and second parcel assemblages wherein said first parcel assemblage includes a first parcel adjacent said particular parcel in combination with said particular parcel, wherein said second parcel assemblage likewise includes a second parcel adjacent said particular parcel in combination with said particular parcel, and wherein one or more records signal that said particular parcel is not commonly owned with said first parcel or with said second parcel;
- invoking second transistor-based circuitry configured to obtain first and second building models of said first parcel assemblage each based on a respective application of first and second speciation protocols to a first multi-parcel-assemblage-specific seeding configuration associated with said first parcel assemblage;
- invoking third transistor-based circuitry configured to obtain first and second building models of said second parcel assemblage each based on a respective application of first and second speciation protocols to a first multi-parcel-assemblage-specific seeding configuration associated with said second parcel assemblage;
- invoking fourth transistor-based circuitry configured to cause said first building model of said first parcel assemblage to be prioritized over said second building model of said first parcel assemblage and to be presented to a user of a visual display in lieu of said second building model based on a programmatic scoring protocol;
- causing a numerous additional parcel assemblages to be depicted all via a single display screen all within a ten-minute period wherein each of said numerous additional parcel assemblages links a corresponding parcel to at least one corresponding adjacent parcel with which said corresponding parcel is adjacent and wherein said corresponding parcels include said particular parcel; and
- causing a first digital resource to be offered simultaneously for many of said numerous additional parcel assemblages on a first-come first-served basis so that one or more options presented in regard to some of said many additional parcel assemblages are withdrawn as an automatic and conditional instantaneous response to said first digital resource being claimed in association with said particular parcel.
9-12. (canceled)
13. The pattern matching method of claim 8 comprising:
- triggering a supervised-learning-type protocol that includes pairing first input data that includes said first parcel assemblage with a corresponding indication of user preference pertaining to said user of said visual display wherein said supervised-learning-type protocol includes pairing numerous vector-valued input objects each to a corresponding output value using one or more user-provided inductive biases and wherein said numerous vector-valued input objects include said first input data.
14. The pattern matching method of claim 8 comprising:
- invoking fifth transistor-based circuitry configured to cause said first building model of an other parcel assemblage to be prioritized over said first and second parcel assemblages and to displace said first or second parcel assemblage partly based on said programmatic scoring protocol and partly based on a first preference-indicative action of said user of said visual display as a contemporaneous response to said first preference-indicative action of said user signaling interest in said particular parcel.
15. The pattern matching method of claim 8 comprising:
- triggering a pattern-matching-type protocol that determines a selective first inclusion of said first parcel assemblage in a geographical map; and
- triggering a feature augmentation protocol that includes obtaining an other building model by gleaning a user-provided inductive bias manifesting a first inferred preference for a first speciation protocol, generating said other building model using said first speciation protocol in lieu of said second speciation protocol, and displaying said other building model simultaneously with said first building model.
16. The pattern matching method of claim 8 comprising:
- triggering a pattern matching protocol that determines a selective first inclusion of said first parcel assemblage and a selective exclusion of one or more other parcel assemblages within 5 kilometers of said first parcel assemblage both based on an application of said first and second speciation protocols to said first multi-parcel-assemblage-specific seeding configuration associated with said first parcel assemblage wherein said first speciation protocol comprises a multi-building model algorithm and wherein seeding for said multi-building model algorithm comprises a repeatable designation of said particular parcel together with a repeatable designation of said first parcel adjacent said particular parcel as said first multi-parcel-assemblage-specific seeding configuration associated with said first parcel assemblage.
17. The pattern matching method of claim 8 comprising:
- triggering a pattern matching protocol that determines a selective first inclusion of said first parcel assemblage and a selective exclusion of one or more other parcel assemblages within 5 kilometers of said first parcel assemblage both partly based on said application of said first and second speciation protocols to said first multi-parcel-assemblage-specific seeding configuration associated with said first parcel assemblage and partly based on an application of said first and second speciation protocol to said first multi-parcel-assemblage-specific seeding configuration associated with said one or more other parcel assemblages wherein said second speciation protocol comprises a single shelter algorithm and wherein seeding for said single shelter algorithm comprises a repeatable designation of said particular parcel together with a repeatable designation of said second parcel adjacent said particular parcel as said first multi-parcel-assemblage-specific seeding configuration associated with said second parcel assemblage.
18. The pattern matching method of claim 8 comprising:
- extracting one or more pattern definition terms as user input for use in a first pattern matching protocol that determines a selective first inclusion of said first parcel assemblage in a geographical map of a region that includes said many additional parcel assemblages and numerous building models, wherein said numerous building models include said first building model of said first parcel assemblage;
- triggering a supervised learning protocol that includes pairing numerous vector-valued input objects each to a corresponding desired output value using one or more user-provided inductive biases, wherein said numerous vector-valued input objects include a first vector-valued input object corresponding to said first parcel assemblage; and
- triggering a feature augmentation protocol that includes an application of said first and second speciation protocols to said first multi-parcel-assemblage-specific seeding configuration associated with said first parcel assemblage.
19. The pattern matching method of claim 8 wherein said first digital resource is thereby offered simultaneously for said many additional parcel assemblages via one or more smart contracts on said first-come first-served basis so that said one or more options presented in regard to said some of said additional parcel assemblages are withdrawn via said one or more smart contracts as said automatic and conditional instantaneous response to said first digital resource being claimed in association with said particular parcel and wherein said first digital resource being claimed is manifested by signaling one or more cryptographically secured digital wallets and one or more mining rigs that comprise proof-of-work blockchain node devices both.
20. The pattern matching method of claim 8 comprising:
- triggering a pattern matching protocol that determines a selective first inclusion of said first parcel assemblage in a geographical map of a first region as an inventory that excludes one or more others in said region that were not matching; and
- causing a first digital resource to be offered simultaneously for many of said additional parcel assemblages on a first-come first-served basis so that one or more options presented in regard to some of said additional parcel assemblages are withdrawn as an automatic and conditional instantaneous response to said first digital resource being claimed in association with said particular parcel.
21. The pattern matching method of claim 8 comprising:
- triggering a feature-augmentation-type protocol that includes obtaining an other building model by gleaning a user-provided inductive bias manifesting a first inferred preference for said first speciation protocol, generating said other building model using said first speciation protocol in lieu of said second speciation protocol, and displaying said other building model simultaneously with said first building model; wherein said method combines a supervised learning protocol with a pattern matching protocol.
22. The pattern matching method of claim 8 comprising:
- invoking fifth transistor-based circuitry configured to cause said first building model of said first parcel assemblage to be prioritized over said second building model of said first parcel assemblage and to be presented automatically to said user of said visual display in lieu of said second building model based on said programmatic scoring protocol.
23. The pattern matching method of claim 8 comprising:
- applying one or more deterministically repeatable speciation protocols comprising said first and second speciation protocols respectively to said first multi-parcel-assemblage-specific seeding configuration associated with said first and second parcel assemblages; and
- implementing said programmatic scoring protocol to include a determination of one or more machine-learning-based parcel assemblage valuations as components thereof.
24. The pattern matching method of claim 8 comprising:
- implementing said programmatic scoring protocol to include a determination of one or more machine-learning-based ranks or scores (or both) as components of said programmatic scoring protocol.
25. The pattern matching method of claim 8 comprising:
- causing a geographically dispersed collection of numerous additional parcel assemblages to be depicted all via a single display screen all within a ten-minute period wherein each of said additional parcel assemblages links a corresponding parcel to at least one corresponding adjacent parcel with which said corresponding parcel is adjacent and wherein more than half of said numerous additional parcel assemblages are separated from said other additional parcel assemblages by more than 100 meters.
26. The pattern matching method of claim 8 comprising:
- invoking transistor-based circuitry configured to obtain first and second building models of a third parcel assemblage based on an application of said one or more other speciation protocols to a first multi-parcel-assemblage-specific seeding configuration associated with said third parcel assemblage;
- invoking transistor-based circuitry configured to cause said first building model of said third parcel assemblage to be prioritized over said one or more building models of said first and second parcel assemblages, and to be signaled to said user of said visual display at least partly based on a programmatic scoring protocol and partly based on another digital resource having been claimed in association with one or more parcels of said third parcel assemblage; and
- applying one or more deterministically repeatable speciation protocols respectively to said first multi-parcel-assemblage-specific seeding configuration associated with said first and second parcel assemblages by causing a recordation of one or more parameters thereof on a public blockchain.
27. The pattern matching method of claim 8 wherein said first and second parcel assemblages are automatically included in an inventory as an automatic and conditional response to information in said one or more records indicating that at least said first and second parcels are not commonly owned with one another.
28. A pattern matching method for facilitating multi-parcel development, comprising:
- invoking first transistor-based circuitry configured to obtain an identification of first and second parcel assemblages wherein said first parcel assemblage includes a first parcel adjacent said particular parcel in combination with said particular parcel, wherein said second parcel assemblage likewise includes a second parcel adjacent said particular parcel in combination with said particular parcel, and wherein one or more records signal that said particular parcel is not commonly owned with said first parcel or with said second parcel;
- invoking second transistor-based circuitry configured to obtain first and second building models of said first parcel assemblage each based on a respective application of first and second speciation protocols to a first multi-parcel-assemblage-specific seeding configuration associated with said first parcel assemblage;
- invoking third transistor-based circuitry configured to obtain first and second building models of said second parcel assemblage each based on a respective application of first and second speciation protocols to a first multi-parcel-assemblage-specific seeding configuration associated with said second parcel assemblage; and
- invoking fourth transistor-based circuitry configured to cause said first building model of said first parcel assemblage (1) to be prioritized over said second building model of said first parcel assemblage and (2) to be presented to a user of a visual display in lieu of said second building model both based on a programmatic scoring protocol whereby said first and second building models of said first parcel assemblage both become automatically generated and ranked alternative species encompassing said particular parcel.
29. The pattern matching method of claim 28 comprising
- causing a first digital resource to be offered simultaneously for many additional parcel assemblages via one or more smart contracts on a first-come first-served basis so that one or more options presented in regard to some of said many additional parcel assemblages are withdrawn via said one or more smart contracts as an automatic and conditional instantaneous response to said first digital resource being claimed in association with said particular parcel, wherein said first digital resource being claimed is manifested by signaling one or more blockchain nodes and one or more cryptographically secured digital wallets both and wherein said one or more blockchain nodes comprise one or more mining rigs configured as proof-of-work blockchain node devices.
30. The pattern matching method of claim 28 comprising
- causing a first digital resource to be offered simultaneously for additional parcel assemblages via one or more smart contracts on a first-come first-served basis so that one or more options presented in regard to some of said additional parcel assemblages are withdrawn via said one or more smart contracts as an automatic and conditional instantaneous response to said first digital resource being claimed in association with said particular parcel, wherein said first digital resource being claimed is manifested by signaling one or more blockchain nodes and one or more cryptographically secured digital wallets both.
31. A pattern matching system for facilitating multi-parcel development, comprising:
- first transistor-based circuitry configured to obtain an identification of first and second parcel assemblages wherein said first parcel assemblage includes a first parcel adjacent said particular parcel in combination with said particular parcel, wherein said second parcel assemblage likewise includes a second parcel adjacent said particular parcel in combination with said particular parcel, and wherein one or more records signal that said particular parcel is not commonly owned with said first parcel or with said second parcel;
- second transistor-based circuitry configured to obtain first and second building models of said first parcel assemblage each based on a respective application of first and second speciation protocols to a first multi-parcel-assemblage-specific seeding configuration associated with said first parcel assemblage;
- third transistor-based circuitry configured to obtain first and second building models of said second parcel assemblage each based on a respective application of first and second speciation protocols to a first multi-parcel-assemblage-specific seeding configuration associated with said second parcel assemblage; and
- fourth transistor-based circuitry configured to cause said first building model of said first parcel assemblage (1) to be prioritized over said second building model of said first parcel assemblage and (2) to be presented to a user of a visual display in lieu of said second building model both based on a programmatic scoring protocol whereby said first and second building models of said first parcel assemblage both become automatically generated and ranked alternative species encompassing said particular parcel.
Type: Application
Filed: Jul 22, 2022
Publication Date: Nov 10, 2022
Applicant: Rebls, Inc. (Bellevue, WA)
Inventors: Bryan Copley (Seattle, WA), Devyn Cairns (Richmond), Jeff Bumgardner (Sun Valley, ID), Phil Placek (Seattle, WA), Michael Ewald (North Myrtle Beach, SC)
Application Number: 17/871,717