Abstract: Generating a query response by receiving data for a non-user utterance, determining a question answering (QA) system response to the non-user utterance, receiving data for a user utterance responsive to the non-user utterance, determining a confidence score for the user utterance, determining a deviation between the user utterance and the QA system response, and providing the QA system response according to a combination of the deviation and the confidence score.

Abstract: A method is disclosed. The method includes receiving a text phrase from a user and parsing the text phrase using a natural language parser to generate distinct words. A vector of values relating to the distinct words is generated and compared to vectors in a graph database which relate to learned communities of language. Based on the comparing, a most similar community in the learned communities of language is determined and an action set associated with the most similar community is queried. A response to the text phrase from the user is then generated based on the action set and provided to the user.

Abstract: A communications server apparatus (100) is configured to receive (202) text data comprising at least one text data element associated with an abbreviated text unit. The text data element is compared (204) with a plurality of candidate text data elements from a representation of a given text database, each candidate text data element associated with a respective candidate text unit in the database. Values for a similarity measure between the at least one text data element and the candidate text data elements are determined (206), and candidate text data elements are processed (208) to select candidate text data elements with associated candidate text units having an ordered relationship with the abbreviated text unit. The similarity measure values and the candidate text data element selections are used (210) to nominate an associated candidate text unit as a disabbreviated text unit for the abbreviated text unit.

Abstract: Some implementations are directed to generating a personal database entry for a user based on free-form natural language input formulated by the user via one or more user interface input devices of a computing device of the user. The generated personal database entry may include one or more terms of the natural language input and descriptive metadata determined based on one or more terms of the natural language input and/or based on contextual features associated with receiving the natural language input. Some implementations are directed to generating, based on one or more personal database entries of a user, output that is responsive to further free-form natural language input of the user. For example, one or more entries that are responsive to further natural language input of the user can be identified based on matching content of those entries to one or more search parameters determined based on the further input.

Abstract: Provided herein are systems, methods and computer readable media for classification and tagging of textual data. An example method may include accessing a corpus comprising a plurality of documents, each document having one or more labels indicative of services offered by a merchant, generating a query based on extracted features and the documents, generating a precision score for at least a portion of the generated query and selecting a subset of the generated queries based on an assigned precision score satisfying a precision score threshold, the selected subset of the generated queries configured to provide an indication of one or more labels to be applied to machine readable text. A second example method, utilized for tagging machine readable text with unknown labels, may include assigning a label to textual portions of the machine readable text based on results of the application of the queries.

Abstract: A method includes searching a technical document including a first, second, and third data fields based on search terms and search year ranges related to a technical field, generating a keyword set using the first, second, and third data fields of the searched technical document, scoring a plurality of keywords included in the keyword set, and selecting some of the plurality of keywords, re-searching the technical document related to the technical field, using the selected keywords, scoring the re-searched technical document to derive a representative document representing the technical field, and deriving a representative keyword representing the technical field, using the second data field included in the representative document, wherein the first data field includes a title of the technical document, the second data field includes a summary of the technical document, and the third data field includes keywords of the technical document.

Abstract: A method may include in response to a user request for a playlist, identifying, by a processing device, a plurality of media items from the playlist, for each of the plurality of media items, determining whether a respective media item is available for a playback on a user device, in response to a determination that the respective media item is not available for the playback on the user device, causing the use device to advance to a next media item on the playlist without user interaction, and in response to a determination that the respective media item is available for the playback on the user device, causing the user device to play the respective media item.

Abstract: Embodiments of the technology described herein, provide improved visual search results by combining a visual similarity and a textual similarity between images. In an embodiment, the visual similarity is quantified as a visual similarity score and the textual similarity is quantified as a textual similarity score. The textual similarity is determined based on text, such as a title, associated with the image. The overall similarity of two images is quantified as a weighted combination of the textual similarity score and the visual similarity score. In an embodiment, the weighting between the textual similarity score and the visual similarity score is user configurable through a control on the search interface. In one embodiment, the aggregate similarity score is the sum of a weighted visual similarity score and a weighted textual similarity score.

Abstract: Disclosed are methods, systems, and non-transitory computer-readable media for displaying relevant data based on facial recognition. The method may include displaying a graphic user interface (GUI) on a display of a user device for a face recognition search process, and determining whether a facial recognition user input has been received. In response to determining the facial recognition user input has been received, a request message may be generated, the request message include an image, and the request message may be transmitted to a facial recognition service. A response may be received from the facial recognition service, and the GUI may be updated to display one or more information cards based on the received response, the one or more information cards being associated with the image.

Abstract: A system, apparatus, method, and non-transitory computer readable medium for performing image search verification using an online platform may include a memory storing computer readable instructions and a database corresponding to a neural network associated with the online platform, and processing circuitry configured to execute the computer readable instructions. The processing circuitry may cause the server to receive an image-based search query from a first user device, the image-based search query including at least one image including a search object, and search query parameters related to the search object, analyze the search object using the neural network to determine an object type of the search object and at least one object type specific characteristic of the search object, and receive at least one search result response from at least one second user device.

Abstract: A method, an apparatus, an electronic device, and a computer storage medium for accessing raster data are provided. The raster data access method comprises: executing a corresponding window query input to determine a target pixel resolution corresponding to a query window according to a raster data access request; calculating a sampling level according to the target pixel resolution and a stored pixel resolution of a raster object, and determining whether the sampling level is greater than a threshold; and accessing raster data corresponding to the query window according to a column-level index if the sampling level is greater than the threshold, the column-level index being an index generated by down-sampling according to raster data of the raster object in a column. Using the raster data access method can achieve quick access to raster data.

Abstract: The invention provides a computer-implemented method of processing an image, the method comprising the steps of: identifying objects in the image using a content analysis engine; based on information from a relationship database, using a contextual analysis engine to automatically: identify contextual relationships between some or all of the identified objects in the image, derive a background or landscape of said image from one or more of said identified objects; and subsequently, and analyse the identified contextual relationships between the identified objects and the derived background or landscape to thereby associate one or more contexts with said image.

Abstract: Concepts and technologies directed to surrogate metadata aggregation for dynamic content assembly are disclosed. Embodiments can include a system that comprises a processor and a memory that stores computer-executable instructions that configure a processor to perform operations. The operations can include obtaining a first visual content from a digital data store, where the first visual content is configured to digitally represent a first scene. The operations can include performing image recognition on the first visual content so as to identify a second visual content that is digitally configured to represent a second scene. The operations can include determining that native original metadata cannot be obtained for the first visual content, where the native original metadata includes information about the first scene digitally represented by the first visual content.

Abstract: Improved systems and devices for medical imaging distribution are provided. A medical imaging order may be received from a medical facility that includes medical imaging. A configuration may be selected and applied based on a body site and an urgency field associated with the order that defines queueing rules for the medical imaging order. Utilization factors for queues associated with radiologists may also be determined. The configuration and the utilization factors may be used to determine a subset of queues associated with a subset of radiologists. The subset of queues may be prioritized based on certain requirements, such as how many medical imaging reports a particular radiologist is required to review, how many medical imaging reports are required to be allocated to a particular radiologist, and the like. The highest prioritized queue may be selected and the medical imaging order may be transmitted to the radiologist associated with that queue.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed for source classification using HDMI audio metadata. An example apparatus includes a metadata extractor to extract values of audio encoding parameters from HDMI metadata obtained from a monitored HDMI port of a media device, the HDMI metadata corresponding to media being output from the monitored HDMI port; map the extracted values of the audio encoding parameters to a first unique encoding class (UEC) in a set of defined UECs, different ones of the set of defined UECs corresponding to different combinations of possible values of the audio encoding parameters capable of being included in the HDMI metadata; and identify a media source corresponding to the media output from the HDMI port based on one or more possible media sources mapped to the first UEC.

Abstract: Example systems and methods are audio identification based on data structure are disclosed. An example apparatus includes memory, and one or more processors to execute instructions to execute a constant Q transform on query time slices of query audio, binarize the constant Q transformed query time slices, execute a two-dimensional Fourier transform on query time windows within the binarized and constant Q transformed query time slices to generate two-dimensional Fourier transforms of the query time windows, sequentially order the two-dimensional Fourier transforms in a query data structure, and identify the query audio as a cover rendition of reference audio based on a comparison between the query data structure and a reference data structure associated with the reference audio.

Abstract: Methods, systems, and media for searching for video content are provided. In some embodiments, the method comprises: receiving one or more characters entered into a first query field by a user; determining a predicted search query based on the one or more received characters; determining a plurality of suggested search queries based on the one or more received characters; causing the predicted search query to be presented in the first query field and at least a portion of the plurality of suggested search query to be presented in a second query field, wherein the predicted search query is combined with the one or more received characters in the first query field; searching a database of videos based on the predicted search query; causing a plurality of video content items from the database of videos responsive to the predicted search query to be presented; and causing, without user interaction, a first video content item from the plurality of video content items to be played back.

Abstract: An electronic device is provided. The electronic device includes a display, at least one processor, and at least one memory configured to store instructions that cause the at least one processor to obtain first information from a first still image frame that is included in a first moving image, obtain second information from the first moving image, identify at least one image function based on at least one of the first information or the second information, and control the display to display at least one function execution object for executing the at least one image function. Various other embodiments can be provided.

Abstract: A system for integrated analysis and management of video data includes a routing server configured to receive video data from an external input video providing device, a video database configured to store the received video data, a video analyzing server cluster including a plurality of video analyzing servers configured to analyze the video data, a metadata database configured to store metadata of the video data, and a video search server configured to search the metadata database and the video database. As described in various embodiments of the present disclosure, the system can perform integrated analysis of various video data received from a number of channels and provide an analysis result, and can also rapidly provide an accurate search result in response to a user's request for search.

Abstract: Systems and methods are described herein for detecting that a person of interest is displayed in a live video for a threshold amount of time, attempting to identify an identity of the person determining that the attempting has failed, identifying broadcast times corresponding to a period of time in which the person was displayed in the live video, identifying trending topics in a social media space that relate to the live video, ascertaining an identity of the person of interest based on the trending topics, comparing the identity of the person of interest to a database of social media profiles, identifying a social media component that corresponds to the person, determining whether the person has modified the social media component within a predefined period of time, and providing information relating to a modification of the social media component simultaneously with the video.

Abstract: Methods, systems, and apparatuses, among other things, may detect and store activity in videos based on a spatiotemporal graph representation. Spatiotemporal proximity graphs may be built based on one or more received tracks and may include one or more nodes and each node may include one or more attributes associated with a corresponding entity. One or more spatiotemporal relationships may be identified between the entities based on each spatiotemporal proximity graph one or more activities of the entities may be identified based on the spatiotemporal relationships.

Abstract: Time-series columnar-based information is received and indexed in a compute infrastructure for cost-effective cloud-based object storage. The approach leverages a file format that enables highly-performant search and retrieval of the data stored in the cloud. In operation, an indexer receives the time-series information, indexes that information according to the file format, and forwards the indexed information for storage to the object store, where it is stored as a set of time-based partitions. A partition comprises a set of files, namely, a manifest file, a data file, and an index file. These files are structured as a compact instance of a set of raw unstructured data that comprises the given partition. Highly-performant information retrieval is enabled in response to a time-bounded query, because operations at a query peer (with respect to one or more partitions) are carried out in real-time during query processing and without requiring retrieval of the data file as a whole.

Abstract: Provided is a method for reverse real-time matching based on event-driven graph patterns. The method includes definition of a graph pattern, establishment of reverse matching architecture and a reverse matching method; and the graph pattern is used for describing a spatial connection relationship among vertices and edges in a graph in a reverse order and attribute constraints thereof, and includes a linked list of matching steps and matching contexts. Reverse real-time matching of the graph pattern is realized according to the reverse matching architecture, and the problem of event-driven subgraph matching in a real-time scene is solved.

Abstract: Certain aspects of the present disclosure provide techniques for enumerating relationships in an object graph using traversal context objects that are decoupled from the implementation details of an object graph and the objects stored therein. An example method generally includes receiving a request to traverse an object graph, the object graph including a plurality of objects. A root context object is generated, and a traversal context object associated with a root node of the object graph is generated. The traversal context object is linked to the root context object and added to a traversal data structure. The graph is traversed by adding and removing traversal context objects to and from the traversal data structure until a terminating event occurs.

Abstract: An upper-level integrated processing device recognizes an inquiry, generates a search request in a primitive form to be output to each of the individual AI search devices in response to the inquiry, receives an individual reply and the probability thereof corresponding to the search request in the primitive form from a plurality of individual AI search devices, normalizes the probabilities of the individual replies from the individual AI search devices to acquire normalized probabilities, and generates an inquiry reply corresponding to the individual replies and the normalized probabilities thereof, and the lower-level individual AI search device searches Individual AI database using artificial intelligence in response to reception of the search request in the primitive form, acquires an individual reply and the probability thereof, and outputs the same in the primitive form to the integrated processing device. The upper-level devices output reply using a plurality of AI search devices in combination.

Abstract: According to some disclosed embodiments an action is performed by an electronic social agent. The electronic social agent collects a first dataset indicating the user's state, the user's environment state, and a first user response to the performed action. Then, it is determined whether it is desirable to collect a second response from the user and, if so, it is further determined whether to generate a question to be presented to the user based on an analysis of a first dataset and the first user response. Then, an optimal time for presenting the question to the user is determined. A question that is based on the collected data and the first user response is generated by the electronic social agent for actively collecting an additional user response. Then, based on the collected additional user response, the decision-making model of the electronic social agent is updated and improved.

Abstract: The invention relates to computer-implemented systems and methods for analyzing and standardizing various types of input data such as structured data, semi-structured data, unstructured data, and images and voice. Embodiments of the systems and the methods further provide for generating responses to specific questions relating to certain rates and terms, such as LIBOR, as well as complex legal constructs, such as interest rate fallback waterfalls, for risk assessment and mitigation. The present invention performs environmental, social, governance analytics on asset-backed securities including commercial mortgage-backed securities.

Abstract: A method can include accessing data generated during field operations; generating a graph that includes vertices and edges using at least a portion of the data, where the edges represent relationships between vertices; and generating a query result using the graph responsive to receipt of a query.

Abstract: A control table (22) defines information for controlling a processing component (20) to perform an operation. The table (22) comprises entries each corresponding to a variable size region defined by a first limit address and one of a second limit address and size. A binary search procedure is provided for looking up the table, comprising a number of search window narrowing steps, each narrowing a current search window of candidate entries to a narrower search window comprising fewer entries, based on a comparison of a query address against the first limit address of a selected candidate entry of the current search window. The comparison is independent of the second limit address or size of the selected candidate entry. After the search window is narrowed to a single entry, the query address is compared with the second limit address or size of that single entry.

Abstract: A computer-implemented system and method performs a search operation. One or more servers coupled in communication with a network, and comprising a processor, a data store, and a controller comprising a matching unit that is configured to access the data store. The matching unit is configured to receive a partial query term inputted into a displayed search access point at a remote computer, and to match the partial query term to the data store to create a list of match keywords. The matching unit is further configured to perform a relevancy process on the matched keywords. The matching unit is yet further configured to determine top matched keywords based upon the relevancy and send a listing of the top matched keywords, to be displayed adjacent the displayed search access point at the remote computer. The listing is configured to be changed based on a change to the partial query term.

Abstract: One embodiment provides a method, including: receiving a ranked listing of a plurality of candidates; within a first one of a plurality of collaboration rounds: (i) aggregating the ranked listings into an overall listing, (ii) presenting the overall listing to a first one of the job candidate matching agents, and (iii) receiving at least one modification to the overall listing from the agents; (iv) presenting a version of the overall listing to each of the remaining agents; and (v) receiving any modifications from the agents until all of the agents have had a turn; conducting others of the plurality of collaboration rounds: (i) presenting a version of the overall listing and (ii) receiving any modifications from the agents; (iii) presenting a version of the overall listing to each of the remaining agents, and (iv) receiving any modifications from the agents; and providing the final version to a user.

Abstract: Systems and methods for determining an intended user selection of a search result. For example, a system may display a first set of search results, including a first search result, and thereafter replace display of the first set of search results with a second set of search results, including a second search result. The system may receive selection of the second search result. If the selection of the second search result was received shortly after display of the second set of search results replaced the first set of search results, the system may update the selection from the second search result to the first search result. For example, if selection of the second search result occurred shortly after display of the second search result replaced the first search result, the system may determine that the user intended to select the first search result but inadvertently selected the second search result.

Abstract: A method for generating a case including receiving a source file associated with an adverse event and including adverse event information for the adverse event, generating case information including a medical product rank for each medical product of the plurality of medical products associated with the medical product information, generating a priority of the case based on the type of the event, and providing the case information to a user computing device to be displayed on a user interface. The user interface includes a medical products section including a medical product representation for each of the medical products. Each medical product representation is arranged on the medical products section based on the medical product rank such that a first medical product representation including a first medical product rank is located above a second medical product representation including a second medical product rank on the medical products section.

Abstract: A system may iteratively scan a portion of a document, extract first data from the portion of the document, and determine, using a trained model, whether the first data corresponds to one or more document types based on one or more confidence thresholds. The system may repeat this process, increasing the portion of the document scanned by a predetermined amount each iteration, until the first data corresponds to the one or more document types based on the one or more confidence thresholds. Responsive to determining the first data corresponds to the one or more document types based on the one or more confidence thresholds, the system may cause a graphical user interface (GUI) of a user device to display a notification indicating a document type match.

Abstract: Described is a system for producing a causal map from a body of text. The system receives multiple textual documents as input. Pairs of cause-effect phrases are extracted from the textual documents and embedded into a vector space. The embedded data is clustered into clusters using a probabilistic technique. A causal map having nodes and edges is generated from the clusters. Using the causal map, causal connections between clusters are obtained, where each node represents an event and each edge represents a causal relationship between events. The causal map is provided as an interactive graph.

Abstract: A computer-implemented method is disclosed. The method includes: obtaining document data for a first web document; identifying one or more tradeable objects based on performing a contextual scan of webpage content of the first web document; generating supplementary display data associated with the first web document, the supplementary display data including one or more user interface elements for initiating data record access actions in connection with at least one data record associated with the one or more identified tradeable objects; and graphically presenting the supplementary display data with the webpage content of the first web document.

Abstract: Methods, systems, and computer programs are presented for facilitating user engagement with a bot. One example method includes receiving user input indicative of a user activity. Responsive to the user input, a first server accesses a sequence specification for implementing the user activity. The sequence specification comprises a sequence of interactions with a plurality of service servers. The first server executes the sequence specification by invoking the plurality of service servers to provide services to implement the user activity in accordance with the sequence of interactions specified by the sequence specification.

Abstract: A computer system extracts product data from a website and correlates product records from multiple sources to one another as corresponding to the same product. A website is crawled efficiently by rendering webpages using a virtual browser that ignores blacklisted elements, extracts data from objects without rendering, and suppressing retrieval of remote resources. Data is extracted according to engine control statements including a selector and extractor. A website may be crawled repeatedly and changes in extracted data may be detected and flagged. Engine control statements may be automatically changed in response to detecting a change in the configuration of the website. Images of product records may be correlated with one another by first comparing text of the product records and selecting images for comparison based on composition. Images are compared using a machine learning model. Images determined to be similar may be presented to a human for a correlation decision.

Abstract: A computer-implemented method and a content characterization system (CCS) for dynamically characterizing a website rendered in one or more of a plurality of languages are provided. The CCS receives website data, analyzes it for characterization of the website, and generates multiple structured data objects with a core object that the CCS connects with the website. When changes are made to the website, the CCS dynamically incorporates the changes into the structured data objects connected with the core object. When a search query is received from a querying network entity, the CCS communicates relevant structured data objects to the querying network entity to answer the query optimally, thereby providing an optimal characterization of the website.

Abstract: Systems and methods are provided for generating a user click history table and a random bucket training table, generating training data for training a user-type-affinity machine learning model by combining the user click history table and the random bucket training table, and training the user-type-affinity machine learning model with the generated training data. The systems and methods further provide for generating a user click prediction table and generating user-type-affinity prediction values for each of the plurality of users by inputting the user click prediction table into the user-type-affinity machine learning model.

Abstract: An online recommendation system can choose recipes to recommend to a customer based on a set of ingredients the customer is inferred to have on hand (a customer pantry model). For example, the recommendation system can look at recent or historical purchases made by the customer and determine what items the customer still has available based on an assumed shelf life for the purchased items. Using the customer pantry model, the recommendation system selects recipes based on overlapping ingredients between recipe's ingredient lists and ingredients available to the customer (including the customer pantry model and their current shopping cart). In some implementations, the recommendation system first selects a set of candidate recipes based on the overlap, then selects the final set of recipes to recommend based on a score optimization (for example, performed using a machine learning model).

Abstract: Methods and systems for generating an integrated structure for the data from disparate data domains that may be used to aggregate, compare, and/or provide recommendations based on the data available from the disparate domains. The integrated structure may further be accessible to users to perform functions (e.g., searches, filtering operations, etc.) in real-time and receive outputs (e.g., in a user interface).

Abstract: Certain aspects of the present disclosure provide techniques for managing a search engine based on search performance metrics. An example method generally includes dividing a set of search history data into a first subset of search history data and a second subset of search history data. The first subset of data is associated with interaction with search results, and the second subset of data is associated with non-interaction with search results. A first quality score is generated for searches in the first subset of data. A second quality score is generated for searches in the second subset of data based on different search intents identified for each temporally related group in the second subset of data. An overall quality score is generated for a search engine, and one or more actions with respect to the search engine are taken based on the overall quality score.

Abstract: A processor-implemented method of creating a hyperlink from a text messaging text entry field in a text messaging app on a user's mobile device includes the app assigning one or more keyboard characters as control characters which designate a start of a text search string and an end of a text search string. The user enters text including the control characters into the text messaging app text entry field. Upon the user activating a send command to send a text message that includes the start and end control characters, displaying the search string as a hyperlinked text in the message thread which is selectable to invoke a search outside of the text messaging app.

Abstract: A data processing system is configured to augment a request for data. The data processing system includes a recommendation engine configured to receive, from a client device over a network, interaction data related to a user interaction with one or more data sources, generate extracted data that includes one or more portions of at least one resource of the one or more data sources. The extracted data is generated based on the interaction data. The data processing system parses the extracted data to identify one or more metrics of the extracted data, and retrieves, from the one or more data sources, the additional data based on the metric. A results compiler is configured to receive a request for data from the client device, and responsive to the request, send the additional data to the client device for presentation.

Abstract: A container having a compactor and bin for waste is disclosed permitting on-premises and remote monitoring of the system and collection is disclosed. The system can also detect non-complaint materials placed therein and act thereon. Methods are further disclosed for inventorying identification tags for tracking packages, merchandise and tags disposed of.

Abstract: The present invention is a website-based, Internet browser accessible method of behavior assessment that consists of a user within an organization accessing the website-hosted Workplace Behavior Observation Form (WBOF) through the Universal Resource Locator (URL) address for the site to answer all form items about an observed individual in the same workplace to determine when characteristics are identified indicating the presence of and predisposition to insider threat. When the WBOF is completed, the user completing the WBOF submits the form which then is automatically scored and analyzed by pattern classifiers trained using a multitude of past examples of known insider threat characteristics across all WBOF items as input which, in turn, provide outputs of threat and risk values that are embedded in a report template in designated locations to form a completed assessment of threat, organizational vulnerabilities, and risk to the organization. The completed report is forwarded to the user's email address.

Abstract: Digital content operation testing techniques are described. An authoring environment supports edit operations to digital content. The authoring environment includes an option to initiate testing of operation of edited digital content at a publish environment of a content delivery network, at which, the digital content is to be deployed. Data describing results of the testing is then communicated over the network based to the digital content editing system. The data is output within the user interface of the authoring environment in this example such that an effect of edits made to the digital content are viewable non-modally within the authoring environment.

Abstract: A system utilizing a web integration service to pull data from disparate computer server systems, and a normalizing module to generate a normalized data set utilized by an indexing module across a de-coupling boundary to generate a search index. An outflow module utilizes results from the search index and hierarchical grouping control structures to generate customized data flows to client devices with improved performance.

Abstract: A plurality of images are received from one or more social media platforms associated with a user. For a selected image of the plurality of images, a plurality of text descriptions are generated. The plurality of text descriptions are computer-generated captions that describe features of the selected image of the plurality of images. The plurality of text descriptions are processed through a natural language processing model. Based on processing, a plurality of interest contexts are derived from the plurality of text descriptions. A mapping of each of the plurality of interest contexts to one or more predefined categories associated with an online marketplace is generated. Based the mapping of each of the plurality of interest contexts to the one or more predefined categories, a user device associated with the user is caused to display an app page or web page associated with the one or more predefined categories.