Abstract: A method and system for determining anomalies in call center communications. Data relating to communications is streamed and processed to obtain baseline probability distributions over various domains of communications. Streams related to subsequent calls are compared to the baselines to determine anomalies.

Abstract: A method, apparatus and network node for clustering a terrestrial area based on Geohash coordinates by selecting a node based on a Geohash area identified by a Geohash string of a predetermined length; subdividing the Geohash area into subareas by increasing the Geohash string by a length of one; and sequencing through the subareas to identify subarea/subareas that exceed a threshold number of a selected parameter. For subareas not exceeding the threshold number of the selected parameter, combining those subareas into clusters without exceeding the threshold number of the selected parameter in respective clusters. For subareas exceeding the threshold number of the selected parameters, subdividing those subareas into further subareas by increasing the Geohash string by one and sequencing through the further subareas to place the further subareas into clusters without exceeding the threshold number of the selected parameter.

Abstract: A computer-implemented method includes receiving a request of data records for a data schema, obtaining a schema alignment which maps the data schema to a subset of an ontology of a knowledge graph, generating at least one query based on the subset of the ontology of the knowledge graph, obtaining a list of data records by executing the at least one query on the knowledge graph to obtain a list of data records, and persisting the list of data records to the data schema.

Abstract: A computer-implemented method includes representing a plurality of database tables as respective vectors in a multi-dimensional vector space, receiving an indication that a first database table represented by a first vector and a second database table represented by a second vector are related to each other, moving positions of the respective vectors representing the plurality of database tables in the multi-dimensional vector space in response to the indication, and grouping the plurality of database tables into one or more table clusters based on positions of the respective vectors representing the plurality of database tables in the multi-dimensional vector space.

Abstract: Standardized address generation from address substrings includes receiving an address string for a place-of-interest, one-to-many mapping at least one of a plurality of address substrings of the address string to respective address components, concatenating the address substrings using a template that specifies an order of concatenating the address substrings, and making the concatenated address substrings available for further use.

Abstract: At least some embodiments are directed to an entity matching detection system. The entity matching detection system includes a latent similarity identification machine learning model that receives one or more data records and generates a final similarity score indicative of a latent similarity between the one or more data records and a second data record. The entity matching detection system can identify lexical and semantic similarities between attribute values and can analyze and compute similarity scores for direct-linked attribute values and cross-linked attribute values extracted from different data records.

Abstract: An example method of performing searches by comparing regions includes identifying a search point contained in geo-located data. The search point is nearest in distance to a query location. A search region associated with the search point is determined. The search region includes neighbor points contained in the geo-located data that are nearest the search point. Centroids corresponding respectively to the plurality of neighbor points of the search region are determined. The centroids of the search region are compared to other centroids corresponding to other regions of the geo-located data. The number of other centroids that match with the plurality of centroids are counted, and the counts are placed in descending order, to list the other regions having the highest similarity first. An ordered list of the other regions is generated based on their respective similarities to the query region.

Abstract: A system and method for generating shard data based on semantic sharding is proposed. Shard data is generated by a map sharder that is configured to generate the shard data based on semantic objects in a geographical area and a definition of sections. The sections cover parts of the geographical area. The map sharder searches, for each of the sections, for semantic objects that are located at least partly in a section and stores found objects in a shard data entry of the shard data.

Abstract: A method for generating a composite visibility indicator of at least one entity includes selecting a first category of entities; selecting a first position; associating the first position with a first geographical zone, said first geographical zone defining a zone around the first position as a function of the selected category; generating at least one request to collect a plurality of indicators, and generating a composite visibility indicator for each entity of the first category selected within the first zone, the visibility indicator being a function of the first indicator and of the second indicator.

Abstract: An application instance that includes one or more machine learning models receives, from a subscriber computing system, a document comprising unstructured data. Based on the unstructured data, the application instance generates an optimized model input that includes a plurality of parsed document sections. For each parsed document section, the application instance generates an output set by performing, by a machine learning model, at least one key information extraction operation. The machine learning model transmits the output in structured form to a target application operated or hosted at least in part by a subscriber entity associated with the subscriber computing system.

Abstract: The system uses natural language to paths of a transition diagram via answer set programming system and provides: an approach for mapping events described in natural language sources to a logical formalism; and integration of Natural Language Processing and constraint-based reasoning inspired by Reasoning about Actions and Change. The system further uses (a) a non-trivial variant of IR in which sources include sequences of events, and queries are made about the state of the world after such events; (b) the extension of techniques for representing dynamic domains to increase the flexibility of the reasoning processes in the presence of uncertainty; (c) a formalization of the IR task based on action languages; (d) an automated IR procedure based on Answer Set Programming (ASP).

Abstract: Techniques for identifying a first process in a stream of event data. The techniques include accessing a stored signature for the first process, wherein the signature includes a plurality of features, and wherein the signature specifies a frequency and weight for each of the plurality of features; receiving a stream of event data having a plurality of events; selecting a window of event data that includes a subset of the plurality of events; calculating a first similarity between the signature for the first process and the event data within the window; and identifying the first process in the stream of event data when the first similarity is within a predetermined measure of similarity.

Abstract: In an example, an article may be analyzed to identify entity terms. Entity term relevance scores associated with the entity terms may be determined based upon the article and the entity terms. One or more first entity terms may be selected based upon the entity term relevance scores. One or more sets of reference position information associated with the one or more first entity terms may be determined. A first set of reference position information is based upon one or more positions, in the article, of one or more references to a first entity term. One or more second entity terms of the one or more first entity terms may be selected based upon the one or more sets of reference position information. A set of one or more salient entity tags associated with the article may be generated based upon the one or more second entity terms.

Abstract: One or more computing devices, systems, and/or methods for constructing and implementing a network management plan are provided. Baseline classifications are assigned to a set of locations. Sub-locations at the set of locations are evaluated to determine whether to override any of the baseline classifications. A model is used to evaluate images depicting the set of locations to generate predicted classifications for the set of locations. Classifications are assigned to the set of locations by implementing conflict resolution rules to selectively retain or replace baseline classifications with predicted classifications. The classifications are used to construct and/or implement a network management plan.

Abstract: Methods and systems for generating a response to a query using an AI engine. One method includes translating a received query into a profile comprised of at least a query type and a priority. The method further includes collecting, based on the profile, a first set of data items from a first data file storing data categorized as general public data and a second set of data items from a second data file storing data categorized as personal private information and applying an AI correlation engine to the second set of data items to determine PPI-agnostic relevancy indicators for PPI included in the second set of data items. The method further includes masking, based on the query cluster profile, the second set of data items by replacing the PPI included in the second set of data items with the PPI-agnostic relevancy indicators.

Abstract: A system and method for customized scheduling of sources, including breaking down a source of content into at least two categories, including posts and engagements, and gathering content related to a specific source. A scheduler handles scheduling of posts and engagement for a single source and entities that are due to be crawled are sent to a scheduling queue, in which each content type for a source can have its own queue. A process points to the correct scheduler queue in order to request content to be crawled, attaches to the proper queue, processes requests, queries the social network for content, parses the response and sends any new data to be saved to the system.

Abstract: Systems and method for lifelong tag learning. The system includes a computing device having a processor and a storage device storing computer executable code. The computer executable code is configured to: provide product descriptions and seed tags characterizing products; train a named-entity recognition (NER) model using the product descriptions and the seed tags; predict pseudo tags from the product descriptions using the NER model; calculate confidence scores of the pseudo tags; compare the confidence scores with a threshold, and define the pseudo tags as true tags when the confidence scores are greater than the threshold; add the true tags to the seed tags to obtain updated tags; and repeat the steps of training, predicting, calculating, comparing and adding using the product descriptions and the updated tags, so as to keep updating the updated tags.

Abstract: Methods, computer readable media, and devices for dynamically identifying and associating disparate records are disclosed. One method may include receiving a first set of association criteria, identifying a first source object and a first target object based on the first set of association criteria, creating a first association object indicating an association between the first source object and the first target object, storing the first association object, receiving a second set of association criteria, identifying a second source object and a second target object based on the second set of association criteria, and creating a second association object.

Abstract: A system and method for generating data visualizations. The method includes generating an enriched data layer based on a plurality of knowledge graphs, the plurality of knowledge graphs including a plurality of first nodes, the enriched data layer including a plurality of second nodes, wherein each of the plurality of second nodes is connected via an edge to at least one of the plurality of first nodes; and generating a data visualization based on the enriched data layer and a request for data, wherein the request for data indicates a type of data corresponding to at least one of the plurality of second nodes, wherein the data visualization is generated using data represented by at least one of the plurality of first nodes connected to the at least one of the plurality of second nodes.

Abstract: A system and method for providing visual data for user interfaces based on a knowledge graph. A method includes identifying at least one second node with respect to a first node based on connections between nodes of a knowledge graph, wherein the knowledge graph includes the first node and the at least one second node, wherein the first node represents a dimension of interest; selecting at least one third node from among the at least one second node by determining a correlation between the first node and each of the at least one second node; determining a new value for a dimension of each of the at least one third node based on a target value such that the correlation of the third node to the first node is maintained while achieving the target value; and generating visual data for an action item user interface based on the new values.