Abstract: A graph includes nodes representing applications and tags describing subjective qualities of the applications. The system generates tags for applications using a large language model (LLM). The system receives the name of an application and generates a prompt for an LLM based on the name. The prompt includes a request for one or more tags associated with the application. The system provides the prompt to the LLM for execution and receives, as output from the LLM, candidate tags. The system inputs the candidate tags into a classifier trained to classify candidate tags into known tags, tags that already exist in a graph. The system receives, as output from the classifier, known tags. The system updates the graph to include a node corresponding to the application, the node linked to the known tags with one or more edges.

Abstract: Techniques are described herein that are capable of responding to a query in a developer tool using semantically related keywords in relevant code chunks. A user-generated query regarding a location of an element in a codebase of a software development project is received. The codebase is parsed into code chunks. Semantically related keywords, including keywords from the user-generated query and other keywords that are semantically related to the keywords, are identified. Relevant code chunks are selected from the code chunks based on satisfaction of a relevancy criterion regarding the user-generated query. Execution of an instruction is triggered, which causes a visual representation of a response to the user-generated query to be generated. The execution of the instruction causes the visual representation to include at least portions of the relevant code chunks and further causes at least a subset of the semantically related keywords to be highlighted in the portions.

Abstract: Disclosed herein are system, method, and/or computer program product aspects, and/or combinations thereof, for a runtime-configurable question-and-answer system that dynamically determines question flow and ordering without hard-coded logic. The system includes a domain-agnostic evaluation engine that evaluates matcher expressions against a context object, a matcher expression evaluation system that determines question visibility and behavior using configurable expressions, a context object builder that aggregates data from multiple sources, and a tiered priority comparator that determines question ordering through a five-tier comparison algorithm enabling both iteration and grouping behaviors. The system also includes a container question architecture for hierarchical data collection, an auto-answer staging system for propagating answers, and a schema-agnostic data integration system for operating on untyped key-value data structures without code changes.

Abstract: A user provides a question to be answered from detailed, dense or otherwise complex documents to a processing system that converts the question to a structured query language query and generates an embedding from the question, augmented by temporal data, synopses, themes, or other relevant information or data. The embedding is compared to embeddings generated from documents of a knowledge base to identify documents that are relevant to the question, and to rank such documents for their relevance. Highly ranking documents are combined with the query and provided to a language model that returns an answer to the question. A source for the answer is identified in at least one of the documents. The answer and the identified documents are presented to the user.

Abstract: The embodiments of the present disclosure address unresolved problems of assigning weightage to information sources in a GenAI model for responding to user queries on flood. Embodiments herein provide a method and system for responding to multidimensional user queries on flood with remote sensing and auxiliary data integration. Herein, the user query is responded by analyzing big geospatial vector database comprising spatially distributed flood inundation maps and flood probability maps along with other auxiliary datasets in vector form provided to the GenAI model. The other auxiliary datasets include flood event history, terrain information, river and stream network, floodplain map, climatic data, previous damage reports, soil and land use data. These auxiliary datasets will be continuously updated time-to-time.

Abstract: Obtain, using at least one hardware processor, data characterizing a physical system governed by a physical conservation law. Apply, using the at least one hardware processor, contrastive learning to the data to automatically capture system invariants of the physical system. Employ, using the at least one hardware processor, a neural projection layer to guarantee that a corresponding dynamic machine learning model preserves the captured system invariants. Optionally, predict performance of the physical system using the corresponding dynamic machine learning model.

Abstract: Embodiments may be associated with a data source and a data service tool. A performance optimizer may determine a new type of data job to be executed based on a job execution parameter, perform a first execution of the new type of data job (such that data operations are performed at the data service tool), and collect first performance results. The performance optimizer then performs a second execution of the new type of data job (such that data operations are pushed down and performed at the data source) and collects second performance results. The first and second performance results are compared, and a result storage is updated with an indication of whether subsequent executions of the new type of data job will perform data operations at the data service tool or at the data source. The indication stored in the result storage may comprise, for example, a pushdown flag.

Abstract: A quantum processing system and method of operating the same are disclosed. The system includes a first qubit comprising a first unpaired electron bound to a first pair of donor clusters embedded in a semiconductor substrate at a distance from the semiconductor surface, each donor cluster in the first pair of donor clusters including at least one donor atom. The system further includes a second qubit comprising a second unpaired electron bound to a second pair of donor clusters embedded in the semiconductor substrate at a distance from the semiconductor surface, each donor cluster in the second pair of donor clusters including at least one donor atom. In addition, a microwave resonator is located between the first qubit and the second qubit, wherein a first end of the microwave resonator is coupled to the first qubit and a second end of the microwave resonator is coupled to the second qubit. A photon of the microwave resonator couples the first qubit and the second qubit.

Abstract: A method and system for selecting an information provider to a user query. An information provider selection method may include verifying LLM results created based on a large language model (LLM) from a prompt of a user; and reflecting correlation between content of each of a plurality of information providers and the LLM results and then selecting from among the plurality of information providers, at least one information provider to provide an instance of content for the prompt of the user.

Abstract: A method includes obtaining, at a first data provider, a first query generation request. The method also includes determining whether a first query, that is to be generated based on the first query generation request, is approved. In response to a determination that the first query, that is to be generated, is approved, the method also includes generating the first query. The method further includes sharing the generated first query with a second data provider.

Abstract: A technique suggests resources within a particular environment. The technique operates by receiving a query via a search interface presentation, and using a prefix tree data structure to retrieve candidate resource descriptors that match the query. The candidate resource descriptors are data items that describe different types of candidate resources. The technique further includes: generating feature information that describes the candidate resource descriptors; using a machine-trained ranking model to generate scores associated with the candidate resource descriptors, based on the feature information; sorting the candidate resource descriptors based on the scores, to provide sorted resource descriptors; and generating output information that represents a selected set of resource descriptors drawn from the sorted resource descriptors, for presentation via the search interface presentation.

Abstract: Systems and methods for rearranging tags on a graphical user interface (GUI) based on known and unknown levels of web traffic are disclosed. To provide users with real estate listings that have popular home attributes with respect to a given region, the system uses known user interaction information to determine predicted user interaction information for real estate listing phrases (e.g., tags) that are associated with unknown user interaction information. The system then ranks the real estate listing phrases based on each real estate listing phrase's user interaction information. Based on the ranked real estate listing phrases, the system generates for display the highest ranked real estate listing phrase in association with a real estate listing being associated with the real estate listing phrase.

Abstract: An application management method includes collecting a plurality of objects in an application instance used for serverless computing and generating a base tree according to a reference hierarchical relationship of the plurality of objects; performing internal memory object rearrangement on a plurality of application instances according to the base tree; and performing internal memory merging on the plurality of rearranged application instances.

Abstract: The present disclosure provides an information recommendation method and apparatus, a computer device and a storage medium. The method includes: presenting a search page in response to a first search request triggered on a multimedia content present page, wherein the multimedia content includes related information of a commodity dimension; presenting, in a preset area of the search page, a recommendation word used for guiding to search for a target attribute of a target object, wherein the target object is an object indicated by the related information, and the recommendation word is generated based on the target object and description information of the target attribute; and in response to a second search request triggered for the recommendation word, acquiring and displaying a search result of the target object under the target attribute.

Abstract: Systems, computer program products, and methods are described herein for automatically building dynamic queries for identifying data in unstructured datasets. The present disclosure is configured to receive a plurality of query templates associated with an alert type(s); identify an unstructured database note(s) based on a user identifier; apply the unstructured database note(s) and the plurality of query templates to an unstructured notes search engine; generate, by the unstructured notes search engine, at least one raw score for the at least one unstructured database note and for each alert type(s); transform, by the unstructured notes search engine, the at least one raw score to a relevancy score using a quantile transformation; and determine a highest relevancy score for each of the at least one unstructured database note for the user identifier.

Abstract: Embodiments of a system may comprise databases and a processor that receives a first filter item and a database filter item, generates a first database based on the first filter item, integrate data from the first database into the user database to create an updated plurality of user records, generate a second database based on a selected set of records, in the updated plurality of user records, corresponding to the database filter item, determine metrics that correspond to the second database, generate a model to segregate the second database using the metrics, receive criteria, compare the segregated second database with the criteria to remove records that do not meet the criteria, cause a subsequent update to the updated second database to integrate data from the event database to create an updated diminished second database, and generate a notification including information included in the updated diminished second database.

Abstract: Aspects of the subject disclosure may include, for example, receiving a user-generated query from user equipment. In response to the user-generated query, obtaining consumption data within a geographic region of the user equipment, determining an environmental profile of the user equipment from the consumption data, and generating content for presentation at the user equipment that is responsive to the user-generated query and relevant to the environmental profile. Other embodiments are disclosed.

Abstract: A system and method are disclosed for processing input data in a multi-phase data processing pipeline. The system receives input data associated with an identifier and a plurality of attributes. Based on the identifier and attributes, the system determines one or more control requirements relevant to a first phase of the pipeline. For each control requirement, a corresponding function is selected and executed, producing control requirement results that are stored. The system modifies the input data in response to the control requirement results and according to the requirements of the first phase. The system stores the modified input data in a data store. A payload is generated containing the modified input data, the set of control requirement results, and the attributes. The system determines a subsequent phase based on the current phase and transmits the payload to that next phase for further processing.

Abstract: Disclosed in some examples are methods, systems, and machine readable mediums which utilize volume to improve the ordering of search results for various information retrieval systems. This improves relevance as volume is a proxy for interest. As volume changes over time, the relevance of a particular result to a particular search query will increase or decrease over time.

Abstract: A compute task agent stored in non-transitory memory and executing on an information handling system processor detects a compute task having performance parameters that include a time criticality factor, compare the compute task parameters and energy parameters associated with each of plural information handling systems and select an information handling system to execute the compute task based at least in part on the compute time and carbon footprint of each of the plural information handling systems.