Abstract: Metadata about files present at clients is collected. The metadata includes values for a set of features associated with the files. The values are normalized and centroids are calculated. For each file, a comparison is performed of a normalized value of a feature associated with a file against a respective centroid calculated for the feature. Based on the comparison, the file is or is not backed up. A machine learning model is applied to files that have been backed up to tier the backed up files.

Abstract: A request to update a database system based on a natural language input document may be received. An input metadata extraction prompt may be determined based on the natural language input document and a prompt template including a fillable portion. The input metadata extraction prompt may be determined at least in part by filling the fillable portion with natural language input text selected from the natural language input document. The prompt template and the input metadata extraction prompt may each include natural language instructions to generate novel text identifying data values characterizing the natural language input document and corresponding to one or more database fields in the database system. A completed metadata extraction prompt may be determined by executing the natural language instructions via a generative language model to generate the novel text. A database query updating the database system may be determined based on the novel text.

Abstract: Systems and methods for improving query creation and AQM are provided. A user interface is provided that allows an analyst to generate and test queries. After the analyst provides a query, one or more subsets of previous call center interactions are selected to test the provided query using methods such as a large language model or string vectorization. Once the subsets of interactions are selected, an LLM is used to evaluate the query against the subset. The evaluations may indicate interactions which were positive and which interactions were negative and may include quotes from the interactions that support the evaluations. The evaluations are presented to the analyst for review, and the analyst may revise the query in view of the evaluations. Once the analyst is satisfied with the performance of the query, the query may be used by the LLM to perform AQM for new interactions in the call center.

Abstract: A transaction which targets an object store employing an open table format (OTF) may be detected by a database execution engine. Next, the database execution engine performs a determination step to determine which OTF enhancement levels to apply to the detected transaction. Then, the database execution engine applies one or more OTF enhancement levels to the transaction based on the determination step. Next, the database execution engine causes the transaction to be processed with the applied one or more OTF enhancement levels. Then, the database execution engine returns a result of the transaction processing to a computing device.

Abstract: A host computer is configured to issue one or more unmap commands to a file system of a storage device, the file system being shared by a plurality of host computers including the host computer, by performing the steps of: acquiring unmap privilege information from the storage device, the unmap privilege information indicating whether or not an unmap privilege is available to the host computer; in response to determining that the unmap privilege is available, transmitting a request to update an unmap privilege file stored in the storage device to indicate that the host computer has the unmap privilege; and then issuing to the file system, the one or more unmap commands to deallocate storage space from one or more files of the file system.

Abstract: Systems and methods for event tracking are disclosed. In one aspect, a set of venues is generated. A set of events that have occurred at one or more venues in the set of venues may be generated. One aspect includes querying a user media database associated with a user, and extracting metadata from one or more media files in the user media database. A match between at least a portion of the metadata and one or more events from the set of events may be determined. In an aspect, responsive to the determining, an entry in a matched events database corresponding to the match is created. A list of events attended by the user may be prepared. The list of events may include the matched events.

Abstract: A preferred aggregate store for a multidimensional database receives and stores intermediate data generated as part of a larger query for avoiding repetitive or redundant data retrievals incurring costly data paths. Aggregates include intermediate tables and sets of data, often generated from a join of two or more distinct data tables, combined for generating a query result. In the event an aggregate is called for, certain storage locations may be preferable to others due to network distance, fees for storage and processing, as in the case of cloud storage, or write accessibility. Designation of a preferred aggregate store ensures that aggregates called for by the query processing are stored in a beneficial location for cost and efficiency.

Abstract: Systems, devices, and methods are provided for object oriented versioning and management. Techniques described herein may relate to determining a first event associated with a first binder, wherein the first event encodes a first set of elements, determine a second event associated with a second binder, wherein the second event encodes a second set of elements, and determine a version of a data object by at least: determining a hierarchal relationship between the first binder and the second binder, determining, based at least in part on the first event, a first state, determining, based at least in part on the first state and the second event, a second state, and generating the version of the data object according to the second state. A data object may be a file, object, document, etc.

Abstract: A semantic search system integrates with an AI platform to provide advanced search capabilities by leveraging automatically generated ontologies and knowledge graphs. The system employs natural language processing, machine learning, and large language models to create, update, and align ontologies from diverse data sources. It supports context-aware query interpretation, personalized results, and complex reasoning by incorporating user context, feedback, and domain knowledge. The system optimizes search performance and efficiency through indexing techniques, distributed computing, and continuous learning. With a modular architecture and scalable infrastructure, the semantic search system enables users to retrieve relevant, meaningful, and context-specific information from vast amounts of structured and unstructured data.

Abstract: A method for optimizing a prompt engineering includes graphically presenting a target manipulation interface to a user, wherein different creation modes for the prompt engineering are displayed on the target manipulation interface, and each creation mode supports a structured creation of the prompt engineering, and in response to the user's selection operation of the different creation modes, implementing the structured creation of the prompt engineering with the creation mode selected by the user. The scheme of the present disclosure can provide a solution for optimizing prompt engineering so as to assist users in creating prompt engineering efficiently and with high quality.

Abstract: Aspects of the subject disclosure may include, for example, receiving a user prompt relating to one or more tickets stored in a database, transmitting the user prompt to an LLM to derive a database access query, after the transmitting, obtaining the database access query from the LLM, sending the database access query to a query service to retrieve ticket-related data from the database, based on the sending, obtaining retrieved ticket-related data from the query service, and causing the LLM to generate a response to the user prompt using the retrieved ticket-related data. Other embodiments are disclosed.

Abstract: Embodiments of the present disclosure provides a method and a system for data query. The method may include obtaining a query request; determining a first query condition based on the query request; obtaining a field query result relating to a connection field by querying, based on the first query condition, in a full-text retrieval system, wherein the full-text retrieval system may store one or more indexes; determining a second query condition based on the field query result; and obtaining a target query result by querying, based on the second query condition, in a target type database, wherein the target type database may store one or more target type data tables, and the one or more indexes may be associated with data in the one or more target type data tables via the connection field.

Abstract: A system for assisting a customer is provided. The system includes a database comprising multimedia files, where one or more tags are associated with one or more of the multimedia files. The system further includes a virtual agent server 100 configured to receive input from a first user (customer) and a second user (customer service representative). Further, the virtual agent server 100 processes the received input to understand a context of the input. Subsequently, the virtual agent server 100 identifies one or more multimedia files based on the context and the tags associated with the multimedia files. Subsequently, the virtual agent server 100 shares at least one of the identified multimedia files with at least one of the first user and the second user to enable better understanding between the first user and the second user.

Abstract: A composite AI system and method for advanced reasoning and automation that integrates symbolic knowledge graphs and algorithms with non-symbolic, or connectionist, models such as neural embeddings. A hierarchical architecture enables dynamically distributed, cooperative reasoning through layperson and expert-led challenge-based verification, model blending, model fitness and retraining and selection, comprehensive feedback loops at individual model or model blend or process flow with or without supervision, and specialized routing of processing to account for various operational risk, regulatory, legal, privacy, or economic considerations. Models, datasets, knowledge bases, simulations and simulation components, and embeddings are iteratively refined using knowledge graph elements and model, process, simulation or flow/process optimal hyperparameters which are recorded and tracked. Extraction of symbolic representations from connectionist models links them to curated ontologies of facts and principles.

Abstract: Embodiments of the present disclosure provide a method for book pushing, a method for generating a book recommendation text, an apparatus, and an electronic device. The method for book pushing comprises: obtaining a first book; determining, according to related features of the first book, a target book in at least one second book, the second book and the first book being written by the same author; determining, according to contents of the target book and/or the first book, a recommendation text; generating, according to the recommendation text and related information of the target book, a book recommendation text of the target book; and pushing the book recommendation text to the reader. The method establishes, according to the related features of the first book currently read by the reader, correlations with the target book, and generates the book recommendation text containing the recommendation text.

Abstract: A processor uses a snapshot virtual device as a storage destination for data of a primary volume and a snapshot volume, compresses data stored in the snapshot virtual device and stores the compressed data in a compression virtual device, and stores the data stored in the compression virtual device in a storage device. When a write request is received from a host, the processor switches, according to a size of an address range of a write destination, between overwriting processing of overwriting an area on the snapshot virtual device which is allocated to large-size data and new allocation processing of allocating a new area on the snapshot virtual device to the address range of the write destination for small-size data, and compresses a plurality of pieces of small-size data stored in the new area and collectively stores the plurality of pieces of small-size data in the compression virtual device.

Abstract: In accordance with an embodiment, described herein are systems and methods for supporting slowly changing dimensions and metadata versioning in a multidimensional database, comprising. A system can comprise a computer that includes one or more microprocessors, and a multidimensional database server executing on the computer, wherein the multidimensional database server supports at least one hierarchical structure of data dimensions. A data dimension can slowly change over time. When such changes occur, metadata associated with the data dimension can be updated. Advantageously, a current snapshot of the data structure can allow searching of previous changes to the slowly changing dimension based upon the metadata.

Abstract: Systems and methods are disclosed comprising techniques for record-to-event conversion, such as retrieving at least one alphanumeric record associated with a monitored digital communication transmitted among two or more users, generating a time-enumerated data structure that stores an event entry set for the monitored digital communication, selectively identifying at least one discrete event for the monitored digital communication, generating one or more relevance scores for the at least one discrete event, identifying at least one valid discrete event from the at least one discrete event, generating an event attribute set for the at least one valid discrete event, updating the normalized event attribute set for a new event entry within the event entry set of the time-enumerated data structure, and transmitting the updated time-enumerated data structure within an elapsed duration after retrieving the at least one alphanumeric record.

Abstract: A method for managing file system entity (FSE) open requests in a shared namespace. According to an embodiment, the method includes (a) receiving, by a controller of a first storage system (FSS), a second storage system (SSS) transfer request for transferring to the SSS a responsibility to manage SSS given FSE open requests, the SSS given FSE open requests are generated by SSS users; (b) determining, by the controller of the FSS, whether to grant the SSS transfer request, wherein the determining is based on whether there is a current granted given FSE open request. When it is determined to grant the SSS transfer request the method includes (c) transferring the responsibility to manage the SSS given FSE related open requests to the SSS; and (d) updating, by the controller of the FSS, a FSS transfer data structure to reflect the transferring of the responsibility.

Abstract: Systems, computer program products, and methods are described herein for query interface response synthesis via machine learning and progressive query data decomposition. The present disclosure includes receiving a document, parsing retrievable text in the document to identify a query in the retrievable text, decomposing the query, using a generative AI model comprising a large language model, into a sub-query sequence, wherein the sub-query sequence comprises a plurality of sub-queries, the plurality of sub-queries within the sub-query sequence successively increasing in complexity, retrieving, using a retriever, data records corresponding with a user identifier, transmitting the data records to the generative AI model, generating, within a first persistent dialogue session of the generative AI model, successive responses according to the sub-query sequence, and collating the successive responses into collated response data.