Abstract: A computer-implemented method for processing a query is disclosed. The method includes receiving, by a server, a query from a user device over a network, the query including one or more keywords; classifying, by the server, the query into one or more categories based on the one or more keywords of the query; determining, by the server, a confidence indicator associated with each of the one or more categories from the classifying; and modifying the query to boost the one or more categories when the confidence indicator associated with the one or more categories for one or more of the keywords of the query is greater than or equal to a confidence level threshold.

Abstract: A digital medium environment includes an asset processing application that performs editing of assets. A projection function is trained using pairs of actions pertaining to software edits, and assets resulting from the actions to learn a joint embedding between the actions and the assets. The projection function is used in the asset processing application to recommend software actions to create an asset, and also to recommend assets to demonstrate the effects of software actions. Recommendations are based on ranking distance measures that measure distances between actions representations and asset representations in a vector space.

Abstract: A data processing system according to an embodiment of the present invention may manage one or more tables and a plurality of archive files including one or more records extracted from the table. Upon receiving a search request for the table, the data processing system may generate a query (first partial query) to search for a record from the table corresponding to a condition specified by the search request, and generate a query (second partial query) to identify the archive file including the record extracted from the table specified as a search target in the search request, and search the identified archive file for the record corresponding to the condition specified by the search request. A query for deriving a union of the output results of the first partial query and the second partial query may be generated, and processing related to the generated query may be executed in parallel.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for indexing actions for resources. In an aspect, a method receiving, for each resource a plurality of resources that are each accessible by a user device, action data describing actions supported by each resource, each action being an action that can be performed by the user device processing the resource; for each resource: determining, from the action data, an action type for each action supported by the resource, determining, from the action data, action parameters for each action supported by the resource, and indexing the action data, action types and action parameters for the resource in an index that is searchable by a search engine.

Abstract: Systems and methods for augmenting and sharing data from audio/video (A/V) recording and communication devices are provided. In one embodiment, a method may include receiving, from an A/V recording and communication device, image data representing an image, analyzing the image data to determine one or more objects depicted by the image data, based on the analyzing the image data, determining at least one comment associated with the one or more objects; transmitting, to a first client device associated with the A/V recording and communication device, the image data representing the image and the at least one comment, receiving, from the first client device, consent for sharing the image data with a geographic area network, the consent indicating a selection of a comment from the at least one comment, and transmitting, to a second client device, the image data representing the image and the comment.

Abstract: The present disclosure describes methods, systems, and computer program products for performing fuzzy substring search. One computer-implemented method includes determining, by operation of a hardware processor, one or more tokens of an input string received from a client application, identifying, from a database, a reference string based on the one or more tokens of the input string, determining a plurality of character index values of the reference string, each character index value indicating a position of a character in the reference string, determining one or more hop index values of the input string, each hop index value indicating a position of a separator in the input string, and calculating a similarity score of the reference string relative to the input string based on the plurality of character index values of the reference string and the one or more hop index values of the input string.

Abstract: The present disclosure relates to enabling clients to identify qualified developers for software development projects. An example method of operating a developer exchange server includes updating stored progress of developers for mission-related activities, wherein the mission-related activities correspond to features of a software platform, and determining, based on the stored progress of each of the developers, a confidence score for each of the developers for each of the features. The method includes receiving a search request that indicates a subset of the features and corresponding confidence thresholds for each of the subset of features, and in response, determining a ranked listing of qualified developers based on the subset of the features, the corresponding confidence thresholds, and the respective confidence score of each of the developers for each of the subset of features. The method further includes providing the ranked listing of qualified developers in response to the search request.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for analyzing images for generating query responses. One of the methods includes determining, using a textual query, an image category for images responsive to the textual query, and an output type that identifies a type of requested content; selecting, using data that associates a plurality of images with a corresponding category, a subset of the images that each belong to the image category, each image in the plurality of images belonging to one of the two or more categories; analyzing, using the textual query, data for the images in the subset of the images to determine images responsive to the textual query; determining a response to the textual query using the images responsive to the textual query; and providing, using the output type, the response to the textual query for presentation.

Abstract: Systems and processes are disclosed for operating a digital assistant in a media environment. In an example process, a primary set of media items can be displayed. An audio input containing a media-related request can be received. A primary user intent corresponding to the media-related request can be determined. In accordance with a determination that the primary user intent comprises a user intent to narrow the primary media search query, a second primary media search query corresponding to the primary user intent can be generated. The second primary media search query can be based on the media-related request and the primary media search query. The second primary media search query can be performed to obtain a second primary set of media items. Display of the primary set of media items can be replaced with display of the second primary set of media items.

Abstract: Systems, methods, and non-transitory computer-readable media can acquire a set of properties associated with a set of content items. A plurality of property combinations can be selected from the set of properties. A plurality of numbers of unique properties associated with the plurality of property combinations can be determined. A diversity metric for the set of content items can be generated based on at least some of the plurality of numbers of unique properties associated with the plurality of property combinations.

Abstract: Example methods and apparatus to replicate panelists using a local minimum solution of an integer least squares problem are disclosed. An example apparatus includes a data organizer to determine, by executing an instruction with a processor, estimated aggregate panelist data based on attribute data corresponding to a seed panel and weight estimates used to replicate respective seed panelists in the seed panel; and a weight determiner to iteratively adjust, by executing an instruction with the processor, the weight estimates based on comparisons of the estimated aggregate panelist data as determined based on the adjusted weight estimates and input aggregate panelist data to generate final weight estimates; and replicate, by executing an instruction with the processor, respective ones of the seed panelists based on final weight estimates to generate a synthetic audience representative of return path data reported by a plurality of media devices.

Abstract: In one embodiment, a method includes identifying, by a search engine of an online social network, web domains external to the online social network. The method includes accessing domain-quality signals associated with each web domain. At least one of the domain-quality signals includes a measure of activations of social plug-ins of the online social network available on webpages of each web domain, a social plug-in being an executable script providing an activable user-interface element for interacting with the online social network from the webpage. The method includes calculating, for each web domain, a domain ranking based at least in part on the domain-quality signals associated with the web domain. The method includes identifying, by the search engine, some of the web domains as low-quality web domains to avoid accessing based at least in part on the domain rankings of the web domains not satisfying a threshold domain ranking.

Abstract: Example methods and apparatus to add a tagged snippet of multimedia content to a playlist are disclosed. An example apparatus comprises an automatic content recognition search service to search a fingerprint database to find a match between query fingerprints for a snippet of multimedia content captured from a multimedia program at a timestamp and reference fingerprints of matching reference multimedia content stored in the fingerprint database, a tag service to generate a tag representing the snippet of multimedia content, wherein the tag, the timestamp, meta information associated with the matching reference multimedia content, and a monitored variable for a number of viewers of the snippet of multimedia content are stored in a database storage as a tagged snippet of multimedia content, and to add the tagged snippet of multimedia content to a playlist for an identified multimedia program if the number of viewers of the tagged snippet exceeds a threshold.

Abstract: A method for parsing a question in a knowledge base includes: receiving a question entered by a user; performing phrase detection on the question to determine candidate phrases; mapping the candidate phrases to resource items in the knowledge base; further determining values of observed predicates and possible question parse spaces; performing uncertain inference on each proposition set in the possible question parse spaces according to the values of the observed predicates and values of hidden predicates, and calculating confidence; acquiring a combination of true propositions in a proposition set whose confidence satisfies a preset condition; generating a formal query statement according to the combination of true propositions.

Abstract: Technology is provided for improving digital assistant performance by generating and presenting suggestions to users for completing a task or a session. To generate the suggestions, a machine learned language prediction model is trained with features extracted from multiple sources, such as log data and session context. When input is received from a user, the trained machine learned language prediction model is used to determine the most likely suggestion to present to the user to lead to successful task completion. In generating the suggestion, intermediate suggestion data, such as a domain, intent, and/or slot, is generated for the suggestion. From the generated intermediate suggestion data for the suggestion, a surface form of the suggestion is generated that can be presented to the user. The resulting suggestion and related context may further be used to continue training the machine learned language prediction model.

Abstract: This disclosure covers methods, non-transitory computer readable media, and systems that analyze a previously unrecognized communication number associated with a sender of a direct digital message when a client device receives the direct digital message from the previously unrecognized communication number. Based on this analysis, the methods, non-transitory computer readable media, and systems provide profile information associated with the communication number for the client device to present together with the direct digital message. To find relevant profile information for the communication number, the disclosed methods, non-transitory computer readable media, and systems optionally query a social networking system for profile information connected to the communication number.

Abstract: A social networking system infers a sentiment polarity of a user toward content of a page. The sentiment polarity of the user is inferred based on received information about an interaction between the user and the page (e.g., like, report, etc.), and may be based on analysis of a topic extracted from text on the page. The system infers a positive or negative sentiment polarity of the user toward the content of the page, and that sentiment polarity then may be associated with any second or subsequent interaction from the user related to the page content. The system may identify a set of trusted users with strong sentiment polarities toward the content of a page or topic, and may use the trusted user data as training data for a machine learning model, which can be used to more accurately infer sentiment polarity of users as new data is received.

Abstract: A computerized, bandwidth-reduced system that will reconcile two ordered sets of values such that a series of changes made to the one are reflected in the other by creating defined REMOVE SERIES, SWAP SERIES, INSERT SERIES and CHANGE SERIES for one set of ordered values, transferring the REMOVE SERIES, SWAP SERIES, INSERT SERIES and CHANGE SERIES and using the REMOVE SERIES, SWAP SERIES, INSERT SERIES and CHANGE SERIES to reconcile another ordered set of values.

Abstract: A system, method, specialized computers, and software for improving wine consumption experience is disclosed. In some configurations, descriptors for wine and or music may be determined. Wine and music profiles may be generated. Wine-music pairs may be created in certain configurations. In some configurations, a user may use certain configurations to select a particular wine, have his or her mobile device play a song matched to that wine.

Abstract: A method implemented on an augmented reality (AR) electronic computing device for determining a likelihood of fraudulent content in an advertisement includes receiving a digital image of the advertisement. A dataset of information relating to the advertisement is extracted from the digital image. Content related to the advertisement is identified from the dataset of information. The identified content is used to request identification information regarding the advertisement. The identification information and supplemental information are used to calculate a scam score for the advertisement. The scam score indicates the likelihood of fraudulent content in the advertisement.

Abstract: The techniques enable a device to identify a best suitable application to open a resource such as a file. The file can be shared via a link or can be attached to a communication. The link comprises a uniform resource locator (URL) or is in some way associated with an underlying URL. The URL includes a pattern, or a portion that identifies a domain (e.g., a hostname) and/or a portion that identifies a type of file that is to be accessed and opened. Upon activation of the link, the device analyzes the URL to determine the pattern. The device then obtains, from a service associated with the URL, a ranked list of applications that are authorized to open the file. Moreover, the device performs, at run-time, a negotiation with the service to determine which application is best suited to open the file.

Abstract: An activity management system is configured to allow users to access multimedia content where the multimedia content is divided into segments. While a user is viewing or interacting with the multimedia content, the user can submit one or more activities (e.g., comments, questions, replies, or reactions) using an interface. The system is operable to electronically link the activity provided by the user with the particular segment of multimedia content in which the activity was captured by the system. The system is also configured to curate activities that are displayed to a user for any given segment based on (1) viewers linked to the user (e.g., groups, social media groups, etc.), (2) viewers that influence the user, (3) a threshold number of activities set by the viewer or the system; (4) group membership of either the viewer or the user; etc.

Abstract: The present disclosure relates to a published information processing method and device. One example method includes obtaining a data item to be published in a published information record from a network site, the data item associated with a service item of the network site; determining that the published information record does not include a prior published data item associated with the service item; in response to determining that the published information record does not include a prior published data item associated with the service item, generating an encryption value based on predetermined initial information; and storing the data item and the generated encryption value in the published information record, wherein the encryption value is configured to enable a user to detect whether the data item has been modified on the network site.

Abstract: A method of enhancing search results pertaining to an item with information about the item from a social network is disclosed. It is detected that a user is searching for information about the item in a context outside of a social networking context. Data relating to the item is collected from a social network of the user. A notification of the data relating to the item is generated to supplement a search result that is to be presented to the user in response to the searching.

Abstract: Datasets are annotated with metadata including categories. Each category corresponds to one or more fields. A hierarchy mapping is generated to indicate a hierarchical relationship between different categories. A natural language query specifies a first granularity level indicating a particular category and one or more field values corresponding to the particular category. Based on the hierarchy mapping, one or more categories that are hierarchically related to the particular category are identified. Based on the metadata, two or more datasets that include at least one hierarchically related category is selected. Based on the first granularity level, one or more dataset filters are generated. The one or more dataset filters are translated to a second granularity level corresponding to the at least one hierarchically related category. The translated filters are applied to at least one of the selected datasets. The two or more datasets are joined to generate a composite dataset.

Abstract: A system and method for content generation and targeting using machine learning are provided. In example embodiments, a probability that a user will visit a webpage based on historical data is calculated. A probability that the user will engage with a particular content category based on past user engagement is calculated. In response to the probability of the user engaging with the particular content category being equal to or greater than a first threshold, the content is generated. Further, in response to the probability of the user not visiting a webpage meeting or exceeding a second threshold, the generated content is sent to the user.

Abstract: A user interaction with a computer device is monitored, the user interaction comprising at least user consuming material via the computer device. Content of the material the user is consuming is identified. Physiological pattern generated by the user while consuming the content is captured via at a sensor device. Responsive to detecting that the physiological pattern represents an outlier, a term in the content is determined for which additional information is to be provided. The term may be determined from the content based on user knowledge, frequency of the term appearing in previous content consumed by the user and popularity of the term. A search query is executed with the determined term. Result of the search query may be filtered based on the user's knowledge. The filtered result and at least one of the previous content containing the term the user has previously consumed is presented.

Abstract: An unexpressed liking and an unexpressed dislike of a user, which are not specified in the user's preference are determined by cognitive analytics. The unexpressed liking and dislike correspond to a first and second characteristic of items, respectively. In a list, a first item having the first characteristic and available in an inventory is included, which is, and a second item having the second characteristic and also available in the inventory is excluded. Items included in the list are arranged according to the user's degrees of liking or the items. An item having the first characteristic is determined to be absent from the inventory. Using completed sales information received from a set of retailer systems, an estimated value of a lost sales opportunity produced when the absent item is purchased is computed. The prioritized list and an accommodation offer responsive to the cost of the lost opportunity are presented.

Abstract: Methods and systems that include, by a client computing device of a first user of a social-networking system, receiving from the first user an identifier associated with an intended recipient to which outgoing communication is to be initiated, wherein the identifier is received via a user interface of an application, identifying, based on the intended recipient, social information relevant to the first user, and displaying, in the user interface, the social information that is relevant to the first user. The identifier may include a phone number or an email address of the intended recipient. The social information may include a name of the intended recipient, and/or a social-network profile of the intended recipient. The intended recipient may be a second user of the social-networking system, and the social information may be identified based on how many degrees of separation there are between the first user and the second user.

Abstract: A hosted client instance includes a performance analytics module to present an internal key performance indicator and an external key performance indicator on a performance analytics dashboard. A query is executed to a connection to an external data source over a network to obtain a result set of data associated with the external key performance indicator. REST APIs associated with the performance analytics module are executed to: store the result set of data in a performance analytics storage device on the hosted client instance, the performance analytics storage device storing both the data associated with external and internal key performance indicators; and render, via a UI rendering engine of the performance analytics module, one or more widgets on the performance analytics dashboard. The REST APIs interact with the data associated with the internal and external indicators in the storage device to render the one or more widgets.

Abstract: Systems and methods for tracking and searching the usage, flow or communication of assets are disclosed. Embodiments as disclosed herein may create and update a graph representing the assets in an enterprise, where the objects and relationships in the graph represent the assets, communications, users or relationship. The graph may be queried to discover a wide variety of information regarding these assets, communications, users or relationships.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating digital video summaries based on analyzing a digital video utilizing a relevancy neural network, an aesthetic neural network, and/or a generative neural network. For example, the disclosed systems can utilize an aesthetics neural network to determine aesthetics scores for frames of a digital video and a relevancy neural network to generate importance scores for frames of the digital video. Utilizing the aesthetic scores and relevancy scores, the disclosed systems can select a subset of frames and apply a generative reconstructor neural network to create a digital video reconstruction. By comparing the digital video reconstruction and the original digital video, the disclosed systems can accurately identify representative frames and flexibly generate a variety of different digital video summaries.

Abstract: A method for generating a graphical display of a bipartite graph includes receiving bipartite graph data, generating, a first meta-node including at least two nodes in the first set of nodes in the bipartite graph data and a second meta-node including at least two nodes in a second set of nodes in the bipartite graph data based on the bipartite graph data using a minimum description length (MDL) optimization process to generate the first meta-node and the second meta-node. The method further includes generating a first graphical depiction of the first meta-node and the second meta-node, the graphical depiction including a single edge connecting the first meta-node and the second meta-node to provide a summarized display of the bipartite graph data.

Abstract: In one embodiment, a stream processing system ingests data from one or more data sources and converts the data into an unbounded stream for an event stream processor. The stream processing system may include a first coordinating spout instance that is deployed at a first time, the first coordinating spout instance to instantiate one or more second spout instances and deploy said one more second spout instances at a second time that is later than the first time; the one or more second spout instances to: connect to the one or more data sources, respectively, and ingest a respective portion of the data from its respective one of the one or more data sources; and output messages based on the ingested portions of the data; wherein the unbounded stream for the event stream processor is based on the messages. Other embodiments may be disclosed and/or claimed.

Abstract: Methods and devices for identifying available applications for use with hardware of a computer device may include generating an application request with at least one device identification and a hardware identification to determine available applications. The methods and devices may include transmitting the application request to a remote application store. The methods and devices may include receiving, from the remote application store, an available application list with one or more applications having application relationship metadata that identifies compatible usage with the at least one hardware identification. The methods and devices may include presenting the available application list on a display of the computer device.

Abstract: In an example, for each one or more search terms, pieces of data from flat data are searched to locate one or more matching pieces of data from the flat data, wherein a piece of data from the flat data matches if it contains at least one attribute with a value that is similar to the search term. Then, for each matching piece of data from the flat data, a fuzzy match score and a match frequency score are calculated. For each node in a graph structure, a ranking score based on a combination of the fuzzy match score and the match frequency score for a corresponding piece of data from the flat data is calculated. One or more search results are retrurned based on the ranking scores of nodes corresponding to pieces of data for the one or more search results.

Abstract: A system and method is provided for augmenting an image with stylized features. An exemplary method includes identifying, in a first image, a first version of an object having a first set of graphical features and identifying, in a second image, a second version of the object having a second set of graphical features. Moreover, the method includes extracting the first and second sets of graphical features from the first and second images, respectively, and generating a third set of graphical features by calculating differences between the first and second sets of graphical features. Finally, using the third set of graphical features, the method includes augmenting the first version of the object in the first image.

Abstract: Techniques for ephemeral messaging with remote ephemeral mode configuration are described. In one embodiment, an apparatus may comprise a messaging component operative to receive a messaging update at a messaging client on the client device from a messaging system; determine a message thread associated with the messaging update; and determine that the messaging update indicates a transition to an ephemeral mode for the message thread; and a user interface component operative to configure a user interface for the message thread to an ephemeral mode interface based on the transition to the ephemeral mode for the message thread. Other embodiments are described and claimed.

Abstract: Messages are collected and processed to determine topic identifiers that correspond to discussion groups. Queries are received and multiple discussion groups that are relevant to the query are determined based on the messages that are associated with the discussion groups and the topic identifiers associated with the discussion groups. The relevant discussion groups are ranked using a group preference model that simulates the behavior of a hypothetical seeker that considers discussion groups by selecting a message author who is an authority in a particular group, and exploring the discussion groups that are preferred by the selected author. The behavior of the seeker is simulated using a stationary Markov process and is used to generate a probability distribution that is used to rank the relevant discussion groups. The ranked relevant discussion groups are provided in response to the query.

Abstract: A method for sorting a data table is provided. The method may include providing a plurality of attribute value information for each data block of the data table. The method may also include receiving a query requiring a sorting on the first attribute of the data table. The method may further include determining a plurality of sequences of a plurality of data blocks having disjoint value ranges of the first attribute based on the provided plurality of attribute value information. The method may also include, for each determined sequence of the plurality of data blocks, reading a plurality of data, sorting the read plurality of data from each data block, and concatenating the sorted plurality of data from the plurality of data blocks within the determined sequence, thereby providing a sorted plurality of sequences. The method may further include merging the sorted plurality of sequences.

Abstract: Aspects of the present invention include a method, system and computer program product determining and scoring customer adoption levels of platform technologies. The method includes a processor accounting for each one of customer platform technology categories; determining one or more formulas to score and rank customer platform adoption levels; acquiring the relative platform technologies customer adoption levels data; determining a customer platform adoption score for each one of the customer platform technology categories; and determining a customer platform adoption ranking for each one of the customer platform technology categories.

Abstract: Visualization of a cohort for high-dimensional categorical data is disclosed. One example is a system including a display module to identify real-time selection of a query data element in an interactive visual representation of high-dimensional categorical data elements comprising a plurality of categorical components. A matrix generator generates a binary distance matrix with columns representing categorical components, and entries in a row indicative of a degree of similarity of respective categorical components of the selected query data element to a data element represented by the row, and determines a category weighting matrix by associating a weight with entries in each column of the binary distance matrix. An evaluator evaluates a weighted similarity score for a data element represented by a row of the category weighting matrix based on entries of the row. A selector iteratively and interactively selects, based on weighted similarity scores, a cohort of categorical data elements.

Abstract: In an example, a deep learning network is used to calculate a similarity score between a first query in a social networking service and each of one or more suggestable entities in the social networking service. The suggestable entities are determined via a first machine learned model. The deep learning network takes as input the suggestable entities as well as a history of interactions with a graphical user interface of a social networking service by a first member of the social networking service, a history of queries performed via the graphical user interface by the first member, and the first query itself.

Abstract: Techniques for using digital entity correlation to generate a composite knowledge graph from constituent graphs. In an aspect, digital attribute values associated with primary entities may be encoded into primitives, e.g., using a multi-resolution encoding scheme. A pairs graph may be constructed, based on seed pairs calculated from correlating encoded primitives, and further expanded to include subjects and objects of the seed pairs, as well as pairs connected to relationship entities. A similarity metric is computed for each candidate pair to determine whether a match exists. The similarity metric may be based on summing a weighted landing probability over all primitives associated directly or indirectly with each candidate pair. By incorporating primitive matches from not only the candidate pair but also from pairs surrounding the candidate pair, entity matching may be efficiently implemented on a holistic basis.

Abstract: Approaches provide for analyzing document data to provide contextual overlays. For example, an application executing on a computing device (or at least in communication with the computing device) can analyze document data to determine a set of keywords based on features extracted from the document data. The keywords can be used to query an index of websites based on a relevance function in order to determine websites that are most relevant to the text identified from the document, at least some of which can be analyzed using a search engine to identify contextual information in the websites associated with the document. Thereafter, the contextual information can be provided for display with the document.

Abstract: Methods, systems, and computer program products for carrying out interactive dialog in natural language using an ontology are provided herein. A computer-implemented method includes generating one or more domain-driven interpretations of a natural language dialogue query provided by a user via utilization of a web ontology language; determining multiple structured base queries, from among a stored collection of structured queries, that correspond to the natural language dialogue query, in view of the one or more generated domain-driven interpretations; selecting one of the multiple determined structured base queries, based on one or more items of context information pertaining to the dialogue; automatically generating a response to the selected structured base query; and outputting the generated response to the user.

Abstract: Monitored shareable links to content items in an online content management service. In one aspect, based on determining that a first view metric associated with a shareable link to a content item is above a first activity threshold associated with the shareable link, a first action is taken on the shareable link. The first action can be allowing or denying requested access to the content item via the shareable link or sending a notification to a user that requested creation of the shareable link regarding user activity on the shareable link. Further, based on determining that a second view metric associated with the shareable link is above a second activity threshold associated with the shareable link, a second action is taken on the shareable link. The second action can be like the first action.

Abstract: Systems, methods, and tangible computer-readable storage mediums for tracking collaboration are presented. More particularly, embodiments relate to providing, using a processor, an environment for collaboration between users; and tracking, using the processor, information regarding the collaboration; such that the tracked information includes rights information regarding rights of the collaborating users. Some further embodiments include storing, in a non-transient, computer-readable storage medium, the rights information. Some further embodiments include determining compensation for at least one user based on the rights information. Some further embodiments include: storing, in a non-transient, computer-readable storage medium, initial content; and storing, in the storage medium, additional content, such that the additional content builds on the initial content.

Abstract: A knowledge data management system (KDMS) implements data refinement orchestration, resolution, and refinement to provide a reusable and generic solution to ingest and link data via relationships and properties when constructing a knowledge graph. The KDMS thus operates to break down existing data storage silos by normalizing and integrating data with a uniform semantic schema, which results in more accurate and faster knowledge graph construction.

Abstract: This disclosure relates to systems, methods, and computer readable media for performing multi-format, multi-protocol message threading in a way that is most beneficial for the individual user. Users desire a system that will provide for ease of message threading by “stitching” together related communications in a manner that is seamless from the user's perspective. Such stitching together of communications across multiple formats and protocols may occur, e.g., by: 1) direct user action in a centralized communications application (e.g., by a user clicking ‘Reply’ on a particular message); 2) using semantic matching (or other search-style message association techniques); 3) element-matching (e.g., matching on subject lines or senders/recipients/similar quoted text, etc.); and 4) “state-matching” (e.g., associating messages if they are specifically tagged as being related to another message, sender, etc. by a third-party service, e.g., a webmail provider or Instant Messaging (IM) service).