Abstract: Various embodiments are generally directed to techniques of overlaying a virtual object on a physical object in augmented reality (AR). A computing device may receive one or more images of the physical object, perform analysis on the images (such as image segmentation) to generate a digital outline, and determine a position and a scale of the physical object based at least in part on the digital outline. The computing device may configure (e.g., rotate, scale) a 3D model of the physical object to match the determined position and scale of the physical object. The computing device may place or overlay a 3D virtual object on the physical object in AR based on a predefined location relation between the 3D virtual object and the 3D model of the physical object, and further, generate a composite view of the placement or overlay.

Abstract: Techniques for providing indirect local geo-positioning using AR markers are disclosed. A first movable AR marker can be located or found by a computing device. A location of the first movable AR marker can be known and shared with the computing device. The location of the first movable AR marker can be based on distance between the first movable AR marker and a fixed AR marker. A distance to the first movable AR marker can be determined. Based on the known location of the first movable AR marker and the distance to the first movable AR marker from the computing device, an estimate of the location of the computing device can be determined without having line-of-sight (LOS) to the fixed AR marker.

Abstract: In one aspect, the present disclosure relates to a method for or performing single-pass object detection and image classification. The method comprises receiving image data for an image in a system comprising a convolutional neural network (CNN), the CNN comprising a first convolutional layer, a last convolutional layer, and a fully connected layer; providing the image data to an input of the first convolutional layer; extracting multi-channel data from the output of the last convolutional layer; and summing the extracted data to generate a general activation map; and detecting a location of an object within the image by applying the general activation map to the image data.

Abstract: A session continuity platform may detect a user action during a first user session associated with a first user device, wherein the first user session is associated with a first platform. The session continuity platform may determine identification information of a user associated with the user session. The session continuity platform may determine a continuity record identifier associated with the identification information. The session continuity platform may obtain, based on the continuity record identifier, activity data from a plurality of continuity records of a distributed ledger. The session continuity platform may determine, based on the activity data, activity information associated with the user action and the second user session. The session continuity platform may cause the first user device to present the activity information via a display of the user device.

Abstract: A device may process, after obtaining an image that includes image data concerning a product, first audio data obtained concerning a first utterance of a user of a user device, and first video data obtained concerning a first eye gaze direction of the user, to determine a first reaction of the user to the image. The device may process, after causing display of the image and an overlay superimposed on the image by the user device, second audio data obtained concerning a second utterance of the user, and second video data obtained concerning a second eye gaze direction of the user, to determine a second reaction of the user to the image and the overlay. The device may retrain a product recommendation model using the first reaction and the second reaction, and may generate and cause display of a product recommendation based on the product recommendation model.

Abstract: Embodiments disclosed herein provide for a system and method for recalibrating an augmented reality experience in mobile devices using a plurality of physical markers. The system and methods provide for realigning the digital representation to the physical world using known physical locations associated with the physical markers that map directly to the digital representation.

Abstract: Various embodiments are generally directed to techniques of overlaying a virtual object on a physical object in augmented reality (AR). A computing device may receive one or more images of the physical object, perform analysis on the images (such as image segmentation) to generate a digital outline, and determine a position and a scale of the physical object based at least in part on the digital outline. The computing device may configure (e.g., rotate, scale) a 3D model of the physical object to match the determined position and scale of the physical object. The computing device may place or overlay a 3D virtual object on the physical object in AR based on a predefined location relation between the 3D virtual object and the 3D model of the physical object, and further, generate a composite view of the placement or overlay.

Abstract: Disclosed are techniques and an apparatus for accessing a smart contract library that may include a number of templates of different legal contracts implementable as a smart contract between respective parties. Each template may include a number of sections having different contractual terms and conditions and fillable fields for specific contract terms. Each respective section of the number of sections includes programming code operable to enforce conformance with specific section-related contractual terms and conditions of the respective section and with any specific contract terms input to a fillable field of the respective section. A first user address generated based on cryptographic keys may be associated with a contract-creating computing device in a private blockchain. The first user address may be associated with the first user in the private blockchain. A finalized smart contract may have a smart contract address generated from the first user address and a nonce value.

Abstract: Techniques to leverage machine learning for search engine optimization (SEO). Some techniques are applicable to turnkey e-commerce solutions operating on the Internet as an online platform. These techniques use machine learning to gain insights into patterns/relationships between search terms and items for sale on the online platform. Depending on a relevancy or an accuracy of a search term to a particular item for sale, the online platform inserts the search term into the online platform such that a public search engine crawler increases a search engine result position for the online platform. Other embodiments are described and claimed.

Abstract: Disclosed are techniques and an apparatus for accessing a smart contract library that may include a number of templates of different legal contracts implementable as a smart contract between respective parties. Each template may include a number of sections having different contractual terms and conditions and fillable fields for specific contract terms. Each respective section of the number of sections includes programming code operable to enforce conformance with specific section-related contractual terms and conditions of the respective section and with any specific contract terms input to a fillable field of the respective section. A first user address generated based on cryptographic keys may be associated with a contract-creating computing device in a private blockchain. The first user address may be associated with the first user in the private blockchain. A finalized smart contract may have a smart contract address generated from the first user address and a nonce value.

Abstract: An electronic device may include logic to provide a trust credential for linking to a permissioned network over a local network, comprising a plurality of user devices; retrieve a document in an initial status for editing, corresponding to a first state of a distributed ledger, maintained by the permissioned network; generate a first change in the document, wherein the document is in a second status; send, to the permissioned network via the local network, the first change for storage in the distributed ledger, in a second state; retrieve the document in a third status, including a second change, performed subsequently to the first change, the second change being generated by a user device, external to the electronic device, and coupled to the local network; and link to the distributed ledger to retrieve a third state of the distributed ledger, the third state comprising the first change and the second change.

Abstract: Embodiments are directed to systems, devices, methods, and techniques to determine words or word combinations of search engine queries and selected items corresponding to the words or word combinations. Embodiments also include applying a machine learning model to the word or word combinations and the selected items to determine a mapping between a word or word combination and a particular selected item, and updating attribute data in a web document with the word or word combination, wherein the web document is associated with the particular item such that a search including the word or word combination returns a result including the web document.

Abstract: A device having extended reality capabilities may capture a video feed including one or more video frames depicting an object that is visible in a field of view of the device. The device may provide the one or more video frames to a machine learning model that identifies the object and one or more parts of the object that are depicted in the one or more video frames. The device may obtain positional tracking information that represents a position and an orientation associated with the object relative to a coordinate space that corresponds to the field of view of the device. The device may obtain a workflow including a sequence of content items for visually inspecting the object using the extended reality capabilities of the device. The device may render digital content associated with the workflow using the extended reality capabilities of the device.

Abstract: A computer-implemented method for using a machine-learning trained predictive engine to predict failures includes receiving electronic prior transaction data corresponding to a plurality of prior successful transactions and a plurality of prior unsuccessful transactions, and training a machine learning predictive engine based on the plurality of prior successful transactions and the plurality of prior unsuccessful transactions. Electronic transaction data may be received, the electronic transaction data being associated with a user, an item, and candidate transaction terms, the electronic transaction data being associated with a candidate transaction. The machine learning predictive engine may determine a likelihood of success of the candidate transaction based on the electronic transaction data, and display the likelihood of success of the candidate transaction.

Abstract: Systems and methods for providing a disposal recommendation for an owned vehicle are provided. The method includes generating a profile for the owned vehicle, the profile including age, mileage, and location of the owned vehicle, receiving monitoring data of the owned vehicle, and receiving sales data for non-owned vehicles corresponding to the profile. The method may further include generating predicted depreciation data of the owned vehicle, based on the sales data and the monitoring data, and providing a recommended disposal time for the owned vehicle, based on the predicted depreciation data.

Abstract: An electronic device may include logic to provide a trust credential for linking to a permissioned network over a local network, comprising a plurality of user devices; retrieve a document in an initial status for editing, corresponding to a first state of a distributed ledger, maintained by the permissioned network; generate a first change in the document, wherein the document is in a second status; send, to the permissioned network via the local network, the first change for storage in the distributed ledger, in a second state; retrieve the document in a third status, including a second change, performed subsequently to the first change, the second change being generated by a user device, external to the electronic device, and coupled to the local network; and link to the distributed ledger to retrieve a third state of the distributed ledger, the third state comprising the first change and the second change.

Abstract: Methods and systems for rendering virtual displays using cryptographic symbols are disclosed. In one aspect, a display device is disclosed that includes a processor and data storage including instructions that, when executed by the processor, cause the system to perform operations. The operations include emitting infrared light toward a cryptographic symbol associated with a surface, receiving a reflection of the emitted natural or man-made sunlight from the cryptographic symbol, and, based on the reflection, decrypting the cryptographic symbol to determine a unique identifier. The operations further include, based on the identifier, generating a first virtual display, and rendering the first virtual display on an image of the surface, through a heads up display, or projected onto the surface.

Abstract: Various aspects described herein generally relate to visualizing a vehicle history using extended reality. In some implementations, an extended reality device may obtain image data corresponding to one or more vehicle parts that are visible in a field of view of the extended reality device. The extended reality device may identify one or more anchor points in a coordinate space corresponding to the field of view of the extended reality device and obtain a vehicle history report based on an identifier associated with the vehicle. The extended reality device may obtain digital content based on one or more records contained in the vehicle history report and an expected visual appearance of the one or more parts of the vehicle. The extended reality device may render the digital content on a display of the extended reality device. Various other aspects are provided.

Abstract: Systems and methods for providing a disposal recommendation for an owned vehicle are provided. The method includes generating a profile for the owned vehicle, the profile including age, mileage, and location of the owned vehicle, receiving monitoring data of the owned vehicle, and receiving sales data for non-owned vehicles corresponding to the profile. The method may further include generating predicted depreciation data of the owned vehicle, based on the sales data and the monitoring data, and providing a recommended disposal time for the owned vehicle, based on the predicted depreciation data.

Abstract: According to certain aspects of the disclosure, a computer-implemented method may be used for determining one or more vehicle recommendations. The method may include receiving data pertaining to a user's internet browsing activity. The received data may be indicative of the user's automotive vehicle preferences. The method may include comparing the received data to a collection of stored vehicle qualities. The method also may include identifying, based on the received data and the comparison of the received data to the collection of stored vehicle qualities, a vehicle characteristic of interest to the user. Using the vehicle characteristic of interest, one or more vehicle recommendations may be determined. One or more vehicle recommendations may be communicated to the user.