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 an effect of the category on the negative behavioral propensity.

Methods, systems, apparatuses, and computer program products are directed to the generation of a global index structure. Agents executing on different data sources locally pre-process (e.g., format, filter, compress, encode, serialize etc.) data generated thereby and index such data. The agents also manage the resources thereof to perform the pre-processing and indexing operations. Each index generated by an agent is formatted as a plurality of index nodes. The index nodes and pre-processed data are provided to backend server(s) that maintain the global index structure and store the data in a globally distributed file system, which aid in unexpected disaster recovery. The backend server(s) generate the global index structure based on the index nodes. As new index nodes are received by the backend servers, the backend servers merge the newly-received index nodes with the global index structure. Global index structure traversal techniques for retrieving search keys are also described herein.

A database index management system uses one or more machine learning models to analyze a query log in relation to a database. A machine learning model may identify a query pattern and/or a change in the query pattern from the query log, identify a column associated with the query pattern, and identify an addition, removal, or modification of an index related to the identified column. The database index management system may perform one or more additions, removals or modifications of indices of the database based on query patterns identified in the query log. The database index management system continuously improves database performance in response to changing database usage patterns over time.

A machine-learning model may be previously trained with a supervised learning algorithm to identify whether a pair of labels provided as input are similar. A locality sensitive hashing forest (LSH) may be generated for the set of candidate labels. When a user later identifies an input label (e.g., by search query, by interface selection, etc.) the input label may be used to query the LSH forest to identify a subset of the candidate labels. This subset may be used to generate respective pairs comprising the input label, one of the subset candidate labels, and a corresponding feature set generated for the pair. This data may be provided to the model to identify a degree to which the pair of labels are similar. The user may be provided one or more recommendations including similar terms identified from the model's output.

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.

A semiconductor device that can reduce power consumption while improving the accuracy of learning and inference is provided. The semiconductor device is connected to data lines PBL, NBL, and comprises a product operation memory cell 1 for storing data of ternary value and performing a product-sum operation between a stored data and an input data INP and a data in the data lines PBL, NBL.

In an approach for a conversational search in a content management system, a processor trains a deep learning model to learn semantic analysis of a plurality of user queries to identify intents and entities in the user queries. A processor analyzes the content management system to extract content keywords to generate a domain ontology. A processor augments the domain ontology based on the identified intents and entities in the user queries by the deep learning model. A processor tags the content keywords with metadata based on the domain ontology. A processor maps the intents and entities extracted from a current user query of a user to the content keywords extracted from the content management system to form a metadata keyword. A processor searches the content management system for a content based on the metadata keyword. A processor returns a search result for the current user query.

A device, system and process for controlling document access using hierarchical paths is provided. A query, received from a requesting device, comprises: a search string for searching a document database; and an identifier associated with a user. A security permissions database is accessed using the identifier to receive permissible hierarchical document access paths indicating document access permissions associated with the identifier. A modified query includes the permissible hierarchical document access paths. The modified query used to access an index of the document database, the index comprising: a searchable content portion, and corresponding hierarchical document access paths, of a document. Document identifiers are received that identify only the documents having: respective searchable content portions that include the search string of the modified query; and at least one respective corresponding hierarchical document access path encompassed by the permissible hierarchical document access paths. The document identifiers are provided to the requesting device.

A data processing method, device and system are provided, to count the transportation number of times for a forklift transporting goods. Specifically, current state information of a target component (for example, a pallet fork) of a to-be-detected apparatus (for example, a forklift) is acquired. If the current state information indicates that the target component carries a transportation object, the transportation number of times for which the to-be-detected apparatus transports the transportation object is updated when it is detected that the transportation object is moved away from the target component. If the current state information indicates that the target component carries no transportation object, history state information of the target component is analyzed, and the transportation number of times for which the to-be-detected apparatus transports the transportation object is updated based on an analysis result.

One variation of a method for automatically redistributing plants throughout an agricultural facility includes, at a mobile robotic system: delivering a first module—defining a first array of plant slots at a first density and loaded with a first set of plants in approximately a second growth stage—from a grow area within a facility to a transfer station within the facility; delivering a second module—located within the facility and defining a second array of plant slots at a second density less than the first density—to the transfer station; and following transfer of a first subset of plants from the first array of plant slots in the first module into the second array of plant slots in the second module at the transfer station, delivering the second module to the grow area in the facility.