Abstract: Methods and system for item matching are described. In one embodiment, compatibility-based text for an item may be accessed. A compatibility identifier may be identified based on the compatibility-based text. The compatibility identifier may be associated with an item cluster. The compatibility identifier may be used to identify a plurality of matching items. A result may be provided based on identification of the plurality of matching items. Additional methods and systems are disclosed.

Abstract: A process including obtaining a set of natural-language text documents that discuss a topic, the set of documents containing different states of knowledge about the topic at different times. The process includes selecting an ontology from among a plurality of ontologies that correspond to different domains of knowledge, the selection being based on the ontology corresponding to a domain of knowledge including the topic. The process includes identifying concepts discussed in the documents using the ontology and detecting changes in at least some of the concepts over time based on differences between discussion of the concepts in documents authored at different times. The process includes updating natural language instructions on the topic based on the detected changes in the concepts and storing the updated natural language instructions in memory.

Abstract: In another example, a device includes a processor and a computer-readable medium storing instructions which, when executed by the processor, cause the processor to perform operations. The operations include acquiring a plurality of data items from a plurality of data sources, wherein the at least two data sources data sources of the plurality of data sources are maintained by different entities, normalizing attributes of the plurality of data items, using a first machine learning technique, matching at least two data items of the plurality of data items to form a grouping, wherein the matching is based on similarities observed in the attributes of the at least two data items subsequent to the normalizing, and creating a single profile for an individual associated with the at least two data items, based on the grouping, wherein the single profile consolidates the attributes of the at least two data items.

Abstract: The present disclosure provides systems and methods for building an inventory database with automatic labeling. A system can maintain a hierarchical concept tree including labels. Each of the labels is associated with a set of attributes and a respective embedding. The system can receive, from a provider device, a request to generate labels for an item of media content. The request can include a request attribute. The system can generate, using a gated categorical model, document embeddings for the item of media content. The system can select a subset of the labels based on the request attribute. The system can determine a respective label score for each label of the subset of the labels based on the document embeddings and the respective embedding of the label. The system can provide a selected label of the subset of the labels based on the respective label score of the selected label.

Abstract: A log message classifier employs machine learning for identifying a corresponding parser for interpreting the incoming log message and for retraining a classification logic model processing the incoming log messages. Voluminous log messages generate a large amount of data, typically in a text form. Data fields are parseable from the message by a parser that knows a format of the message. The classification logic is trained by a set of messages having a known format for defining groups of messages recognizable by a corresponding parser. The classification logic is defined by a random forest that outputs a corresponding group and confidence value for each incoming message. Groups may be split to define new groups based on a recurring matching tail (latter portion) of the incoming messages. A trend of decreased confidence scores triggers a periodic retraining of the random forest, and may also generate an alert to operators.

Abstract: A system includes an OAI gateway; and a main server coupled to the OAI gateway via a network, and configured to be accessed by client workstations, the main server including: an OAI listener coupled to the OAI gateway; a notification server coupled to the OAI listener; and a memory defining a database and coupled to the OAI listener; the main server being configured to present to a workstation a user-fillable intake form having a plurality of questions, to be filled by an intake clerk, and the main server configured to receive answers to the questions from the workstation, and to present a score total to the workstation indicating whether to accept the potential customer, the score total varying depending on the received answers; and the system being configured to perform an automated action in response to the score total being above or below a predetermined threshold value. Other systems and methods are also provided.

Abstract: The present technology is directed to high performing trained machine learning models for information retrieval in a web store. In some embodiments, for example, when a search query is received from a user of an online retailer, a computer system associated with the online retailer accesses measurements of performance of sets of search results returned in response to previous user search queries. Each of the previous search results set is a set that was ranked by a machine learning model selected from a store of machine learning models that are each trained to rank search results. Based on the measurements of performance, the computer system selects a machine learning model to rank search results for a response to the received search query. The ranked search results are provided for output to the user.

Abstract: At least some embodiments are directed to a prediction system of software objects. The prediction system predicts a first aspect of a user profile utilizing a categorization machine learning model and a user activity profile, the user profile and the user activity profile are associated with a user. The user activity profile comprises a plurality of values associated with demographics and historical activity data of the user. The prediction system predicts a software object associated with the user profile utilizing an optimization machine learning model, the first aspect of the user profile, and a second aspect of the user profile. The software object is optimized with respect to at least one competitive interest between the user associated with the user profile and an entity associated with the software object. The prediction system outputs the software object to a client computing device of the user.

Abstract: Extracting and surfacing information corresponding to individual logical topics from enterprise data stores that are separated across multiple geographic regions. A clustering service creates, by utilizing machine learning toolkits that are agnostic to the region in which data is stored, individual topics that have references to multiple shards of data that are stored in different geographic regions. The clustering service also shards the knowledge base state according to the regions from which pieces of data for the particular logical topic was extracted. For example, a first shard containing information extracted from a first document may be stored in a first region whereas a second shard containing information extracted from a second document may be stored in a second region.

Abstract: Systems and methods for determining a query for a data store are described. A natural language text may be analyzed using heuristic processing and one or more machine learning models. Query parameters may be determined from the heuristic processing and machine learning and combined to form a query in a query language. In the heuristic processing, parsing rules may be used to remove conditional terms to generate a base question. The base question may be input to the one or more machine learning model to generate a base query which may be combined with query parameters related to the conditional terms.

Abstract: The present disclosure relates to processing operations configured for intelligent management of a synchronization interval usable to synchronize data for an application/service between local data storage and distributed data storage. A classification prediction for a synchronization interval may be generated that is used as prediction for modifying the synchronization interval when a plurality of computing devices, linked to one or more user accounts, are used to access content. For instance, a suggestion is made as to whether a synchronization interval should be made faster, slower or even remain unchanged when a user account is accessing content. This may occur based on analysis of contextual factors described herein, thereby enabling a synchronization prediction component to make a best possible prediction for setting a synchronization interval. Artificial intelligence processing may be trained to generate the classification prediction for a synchronization interval.

Abstract: Data is received that specifies a term generated by user input in a graphical user interface. Thereafter, the term is looked up in a dictionary in which there are multiple classes for terms. The term can be classified based on a first class having a top ranked effective count for the term within the dictionary when a ratio of the first class relative to a second class having a second ranked effective count for the term in the dictionary is above a pre-defined threshold. In addition, the term is classified using a machine learning model when the ratio of the first class relative to the second class is below the pre-defined threshold. Data can be provided which characterizes the classifying. Related apparatus, systems, techniques and articles are also described.

Abstract: Embodiments are directed to generating metrics based on visualizations. A dashboard that may be associated with source visualizations display a current value of metrics from source visualization models. A classifier may automatically use characteristics from the source visualizations to determine metrics for the source visualization. The source visualization models may be sample to provide values of the metrics across time, at a sampling rate determined by a metric profile. The sampled values may be stored with time values in a metric data store such that the time values may correspond to when the values sampled from the visualization. Metric visualizations may be generated based on the values and the time values such that the metric visualizations display previously sampled values of the metrics.

Abstract: Systems and methods include requesting, from a first application system, of a first one or more combinations of search parameters for identifying a data subject identifier of the first application system, transmission of a first query to the first application system including values of search parameters of a first one of the first one or more combinations of search parameters, the values associated with a first data subject, reception of a first data subject identifier of the first application system in response to the first query, transmission of a second query to the first application system including the first data subject identifier, and reception of data of the first application system associated with the first data subject identifier in response to the second query.

Abstract: A system for intelligently processing queries for cloud-based network file stores includes a file store that stores groups of documents that are associated with files, a non-transitory storage medium that stores instructions, and a processor. The processor may execute the instructions to receive a ticket based on a communication associated with a query to the file store, pull data for the ticket, check a sender of the communication, identify a file using the data, and/or analyze the communication using an artificial intelligence engine to generate a recommendation. The processor may monitor changes to the recommendation made before being sent in order to update the artificial intelligence engine for the changes.

Abstract: A centralized system may collect and aggregate assessments from multiple websites. An aggregate score may be calculated for the resource that cumulatively considers assessments from a plurality of different websites from which assessments are received from users. Text descriptions associated with each of the assessments may be provided to a machine-learning system that uses a trained model to assign identifiers to the assessments as they are received. These identifiers may include common words or text that are descriptive of different facets of user experiences related to receiving and using the resource. After selecting one or more identifiers, assessments associated with that identifier may be included or excluded from the display. Additionally, the overall aggregate score for the resource may be recalculated by removing components of that score that are based on assessments with identifiers that have been selected for exclusion.

Abstract: Performance measures are predicted for queries to prioritize query performance at a database system. A trained machine learning model for the database system may be applied to a query to determine a predicted performance measure for the query. The predicted performance measure may be compared with other predicted performance measures for other waiting queries to determine a priority for executing the query.

Abstract: Embodiments are directed to methods and systems for capturing data of a database record related to an event. Each record can comprise a record of a service provided to a consumer by a service provider of a plurality of service providers and a records management and processing system can comprise an intermediary between systems of the plurality of service providers and systems of a plurality of responsible entities. The records management and processing system can predict possible missing data in one or more records of the plurality of records in the database, select at least one record of the one or more records of the plurality of records predicted to have possible missing data, and initiate, for each selected record, a workflow for further processing of each selected record. The further processing can be directed to collecting the missing data.

Abstract: At least one table included in first content may be determined. The at least one table includes a first plurality of rows and a first plurality of columns. It may be determined that a first term indicative of a personal name is included in a first row of the first plurality of rows and a first column of the first plurality of columns. A second row of the first plurality of rows that includes at least a first personal name in the first column and a first item of personal identifying information in a second column of the first plurality of columns may be identified. First data indicative of the first personal name and the first item of personal identifying information may be extracted. The first data may be added to a first profile associated with the first personal name.

Abstract: A system for application selection using behavioral propensities includes a computing device configured to identify a negative behavioral propensity associated with a human subject, generate, using category training data including a plurality of applications and a plurality of correlated categories, and using a classification algorithm, an application category classifier, wherein the application category classifier inputs applications and outputs categories of the applications, receive an application to be loaded to a device operated by the human subject, identify, using the application category classifier, a category of the application, wherein identifying the category includes determining, a plurality of application data elements, classifying each application data element of the plurality of application data elements to an application data object of a plurality of application data objects using an object classifier, and inputting the plurality of objects to the application category classifier, and determine