87 results about "Query transformation" patented technology

Systems and processes for operating an intelligent automated assistant are provided. An example method includes, at a computer system that is configured to communicate with a display generation component and an input device: detecting an audio input including a query; in response to detecting the audio input including the query: retrieving contextual data related to the query; in accordance with a determination that the query includes a request of a first type: converting the query to a rewritten query based on the contextual data related to the query; and providing the rewritten query to a first digital assistant component; and in accordance with a determination that the query includes a request of a second type different from the request of the first type, providing the query and the contextual data related to the query to a second digital assistant component different from the first digital assistant component.

The invention relates to the technical field of prompt optimization engineering, in particular to an embedded clustering multi-path recall large model question and answer method, system and device and a medium, and the method comprises the following steps: preprocessing a multi-source text to generate an associated paragraph, and converting the associated paragraph into a semantic vector; executing clustering and adjusting a clustering center based on a matching strategy to form a vector library; receiving queries, converting the queries into semantic vectors and retrieving related units in parallel; the recall result is comprehensively evaluated on the basis of a credibility perception attention mechanism in combination with semantic matching and timeliness score, the semantic matching score is calculated by a local bge-ryanker-v2-m3 model, the timeliness score is quantized through a date difference attenuation function, and finally high-quality content is weighted and screened to be input into a large language model to generate question and answer output. And the result accuracy, timeliness and service adaptability are improved.

The invention discloses a big language model enhanced data consanguinity analysis method and device and a medium, and relates to the technical field of data consanguinity, and the method comprises the following steps: obtaining metadata and a source code, and carrying out data preprocessing on the metadata and the source code to obtain a graph database; based on the graph database, semantic task nodes are determined through data enhancement of LLM interaction; obtaining user query data, and performing query conversion processing on the user query data according to the semantic task nodes to obtain question answers corresponding to the user query data; obtaining abnormal warning data, and performing root cause tracing on the abnormal warning data to determine diagnosis context data; and performing multiple rounds of LLM diagnosis on the diagnosis context data to obtain a repair data stream. Through the method, the technical problem that an existing data blood relationship technology highly depends on manpower is solved.

The present disclosure is related to techniques for converting a natural language utterance to a logical form query and deriving a natural language interpretation of the logical form query. The techniques include accessing a Meaning Resource Language (MRL) query and converting the MRL query into a MRL structure including logical form statements. The converting includes extracting operations and associated attributes from the MRL query and generating the logical form statements from the operations and associated attributes. The techniques further include translating each of the logical form statements into a natural language expression based on a grammar data structure that includes a set of rules for translating logical form statements into corresponding natural language expressions, combining the natural language expressions into a single natural language expression, and providing the single natural language expression as an interpretation of the natural language utterance.

Disclosed are techniques for an AI system with a large language mode (LLM) with improved accuracy and reliability in solving mathematical problems. An initial query is transformed into a template query by replacing the original input values with variables. Multiple prompts are sent to the LLM, each being different from one another, and contextually related to the template query. Multiple results are responsively received from the LLM, each result including an analytical expression to solve the mathematical problem. Each of the expressions is evaluated using a numerical evaluation tool with variables of the expression being assigned a common set of randomly sampled values. A consensus is achieved when the evaluated expressions satisfy a consensus condition, such as when all outputs match consistently over N experiments or trials. After the consensus condition is reached, the original inputs are evaluated with one or more of the expressions, and the solution is output.

The invention relates to an assembly type bridge modeling method based on a large model and an RAG technology. The method comprises the steps that a bridge standard component library is established based on an assembly type bridge standard image set; calling a large language model, and generating standardized knowledge statements based on the bridge standard component library; a word embedding method is adopted to convert the normalized knowledge statement into vectors, and the vectors are stored in a vector database; converting an input natural statement query into a vector by adopting a word embedding method, and retrieving in a vector database to obtain a normalized knowledge statement related to the query; performing parameter analysis and optimization on the retrieved knowledge statements based on a large language model by utilizing an RAG technology so as to generate component parameters; and calling a component modeling algorithm based on each component parameter to generate a component three-dimensional model, and assembling the component three-dimensional model to obtain a fabricated bridge model. According to the method, component parameter sorting, knowledge statement intelligent combination, efficient semantic retrieval, parameter optimization, three-dimensional model automatic generation and the like are organically integrated, and the modeling efficiency and quality are improved.

A method, computer program product, and computing system for processing a natural language query concerning data stored within an electronic database. The natural language query is converted into a database command query using a generative AI model. A flagged ambiguity is generated by flagging an ambiguity associated with the natural language query using the generative AI model. User feedback concerning the flagged ambiguity is obtained. The database command query is revised by processing the natural language query, the database command query, and the flagged ambiguity using the generative AI model.

A system for query execution planning over ontology-based databases and related methods are disclosed. The system is programmed to receive an ontology query from a user account against an ontology having access controls, and transform the ontology query into a set of database queries, including a plurality of joins. The system is programmed to compute the amounts of data processing associated with executing the plurality of joins in different orders on a sample of the databases representing the ontology, considering how much data in the ontology can be accessed by the user account under the access controls, and determine an execution plan corresponding to a preferred amount of data processing. Furthermore, the system is programmed to execute the set of database queries on the databases according to the execution plan, and transmit a reply to the ontology query to the user device based on a result of the execution.

A system and method for aggregating insights from disparate proprietary information systems is disclosed. The system includes an insight aggregation server configured to receive a resource data mapper from each target entity of a plurality of target entities, each target entity having a target entity database. The resource data mapper maps its respective database to a virtual information system (VIS). The server is also configured to receive an insight request from a requesting entity in natural-language text form and transform it into a VIS-aligned query using a query interpreter engine, then transform the VIS-aligned query into target entity queries using a query mapper engine and the resource data mappers. Each target entity query is sent to the target entity it is aligned with, verified for authorization, and executed by that target entity database. The execution results from all target entities are then aggregated and provided to the requesting entity.

A system for balancing query execution against ontology-based databases among multiple user accounts and related methods are disclosed. The system is programmed to receive database queries transformed from ontology queries from user accounts. The system is further programmed to manage execution of the database queries to enable fair utilization of computing resources among the user accounts, based on tracked usage of computing resources of each user account or estimated costs of pending database queries considering access controls associated with the ontology. Managing execution of the database queries comprises preempting a complex database query for another database query associated with a user account having a current top priority in query execution.

A query associated with an entity is received. The query is transformed into a generic data request that excludes proprietary information. The generic data request is transmitted to at least one external artificial intelligence model. External data responsive to the generic data request is received. The external data is combined with proprietary data associated with the entity to generate a response, and the response is provided to the entity.

Disclosed embodiments provide a framework for automatically generating media promotions according to real-time media analytics and that can be presented to different users of a peer-to-peer music recommendation service. In response to a user query to generate a promotion for a song, the service converts the query into a set of embeddings. Using user profile data and historical music data corresponding to the song and obtained based on the set of embeddings, the service generates music analytics corresponding to the song and recommendations for different music promotions associated with the song. The service can implement these music promotions and track the efficacy of these music promotions as users engage with the music promotions and the song.

A machine-readable medium stores instructions that, when executed by a processor, cause the processor to execute operations. The operations include receiving information identifying a database table and preprocessing the table. The preprocessing includes extracting primary and foreign key relationships and generating sample data by combining frequency-based sampling of common values with random sampling. The operations also include generating, using an LLM, a unified metadata schema. The generating includes processing the table and the sample data using domain-specific prompts and outputting the unified metadata schema. The operations include embedding and indexing the unified metadata schema and converting a natural language question output from an end-user device into a SQL query. The converting includes identifying relevant metadata in the unified metadata schema matching query intent and generating the SQL query using the filtered metadata. The operations also include executing the SQL query and providing query results to the end-user device.

The invention discloses a method and device for improving the read-write performance of a database, and relates to the technical field of database optimizing.The method comprises the following steps that firstly, a database read-write request initiated by a service system is intercepted, and query conditions in the request are analyzed; 2, performing shunt query according to the type of the query condition: if the query is single primary key or primary key list query, routing the request to a key value pair database and reading data; and if the query is composite condition query. According to the method, the database request is intercepted, and the original query of a relational database is converted into the query of a key value pair database or a full-text retrieval database, so that the respective advantages of the key value pair database in a single key value query scene and the full-text retrieval database in a complex query scene are fully exerted; the problem that an existing relational database is large in data volume and slow in query is solved, and the problem that all data cannot be queried at a time due to data separation caused by an existing data fragmentation scheme is solved.

A method of searching a content scene includes receiving an image file of content; dividing the image file into scene units to generate scene images, and storing the scene images in a first database; extracting vector data of the scene images by using an embedding model, and storing the vector data in a second database; receiving a query for an image search by using a search tool, and converting the query into a vector to detect data having high similarity from the vector data of the second database; and extracting a scene image corresponding to the data having high similarity among the scene images from the first database, and providing the scene image as a search result of the search tool.

A method for performing data encryption and application-agnostic querying of encrypted data includes identifying, via a processor, selected data for encryption. Encryption is applied to the selected data, to produce encrypted data. A query is received at the processor, the query originating from a software application. The query is translated into a modified query compatible with the encrypted data. The processor causes execution of the modified query, to produce query results. The query results include a subset of the encrypted data. The query results are sent to the software application without decrypting the subset of the encrypted data.

Systems and processes for operating an intelligent automated assistant are provided. An example method includes, at a computer system that is configured to communicate with a display generation component and an input device: detecting an audio input including a query; in response to detecting the audio input including the query: retrieving contextual data related to the query; in accordance with a determination that the query includes a request of a first type: converting the query to a rewritten query based on the contextual data related to the query; and providing the rewritten query to a first digital assistant component; and in accordance with a determination that that query includes a request of a second type different from the request of the first type, providing the query and the contextual data related to the query to a second digital assistant component different from the first digital assistant component.

A method for displaying a search result to a user in a client device is provided. The method includes receiving, in a server, a search query from a user, the search query including a string of text characters. The method also includes converting the search query into a sequence of numbers based on a semantic content of the string of text characters, the sequence of numbers defining a vicinity in a multidimensional space, identifying a text string associated with a point within the vicinity in the multidimensional space, ranking the text string according to a similarity value with the search query, and providing a link to a media file associated with the text string to the user as a search result. A system, a memory storing instructions which, when executed by a processor cause the system to perform the above method, and the processor are also provided.

In one embodiment, a method for a cache-generated frequently asked questions page includes converting a received query into a set of embeddings and performing a semantic searching operation based on information contained in the set of embeddings against a cache of question and answer pairs. The method further includes returning a stored answer to the received query responsive to a determination that a particular question and answer pair in the cache of question and answer pairs meets a threshold similarity level for the information contained in the set of embeddings, the stored answer derived from the particular question and answer pair and performing a large language model operation to generate an answer to the query responsive to a determination that no question and answer pair in the cache of question and answer pairs meets the threshold similarity level for the information contained in the set of embeddings.

A system is provided.SOLUTION: A system comprising: means for automatically collecting answer data published by each local government; means for converting the collected data into a text format and performing data cleaning; means for generating an embedding from the cleaned text data using a generated AI model; means for registering the generated embedding in a database and updating an index; means for providing an interface for answer data search to a user; means for receiving a search query of the user, converting the query into an embedding, and searching the database; and means for displaying a search result to the user.SELECTED DRAWING: Figure 1

A computerized-method for matching customer queries across diverse digital channels with a response in a multichannel contact center. The computerized-method includes: (i) continuously receiving queries from customers via digital communication channels; in each preconfigured time-window: (ii) converting each customer query in the received queries into a high-dimensional vector representation and scoring the customer query to yield a similarity score by operating a semantic embedder module; (iii) clustering each customer query based on the high-dimensional vector representation and the similarity score by operating a AIQA module to yield clusters of customer queries with semantic similarity; (iv) matching each cluster of customer queries with the response based on a preconfigured threshold by operating a CVSE; (v) automatically generating a notification for each customer query based on the matched response by operating a notification module; and (vi) automatically sending the notification to each customer that is associated with the customer query.

Embodiments described herein includes systems and methods for enhancing the outcomes of electronic searches targeting preexisting electronic objects, each previously segmented into data chunks and encoded into representative numeric vectors via a first embedder, with data stored in a knowledge base. The system includes a second embedder that translates queries into corresponding numeric vectors compatible with the first embedder's outputs. A search engine retrieves data records from the knowledge base by comparing similarity scores between query and object vectors. A processor introduces a bias to these vectors based on a calculated distance function, resulting in biased vectors that refine search results. An output device presents the processed search outcomes, optimizing relevance by leveraging biased vectors within a constrained data record set.

The invention discloses a data processing method, computer equipment, a readable storage medium and a program product, and relates to the technical field of data processing.The data processing method comprises the steps that initial data is acquired; obtaining a conversion configuration rule; querying a generation logic for generating target data by using the initial data in the conversion configuration rule; and calling a transfer function corresponding to the generation logic from the transfer function set as a target function, and executing the target function on the initial data to obtain target data. The technical problem of data processing mode solidification caused by hard codes is solved, and the technical effect of improving data processing flexibility so as to improve data processing performance is achieved.

In some aspects, the present disclosure provides a method of querying a database. In some embodiments, the method comprises receiving a natural language (NL) query from a user. In some embodiments, the method comprises translating the NL query into a domain-specific language (DSL) query comprising instructions for selecting and returning a ranked result from the database to the user. In some embodiments, the translating is based on a joint embedding space of NL queries and DSL queries. In some embodiments, the method comprises selecting the ranked result from the database using the DSL query. In some embodiments, the method comprises returning the ranked result to the user.

The application relates to the technical field of electric digital data processing, and discloses a big data fast indexing and querying system based on general surgery diagnosis and treatment characteristics, which comprises a data stream acquisition module, a topological sequence reorganization module, a physical space mapping module, an index key synthesis module and a preloading execution engine; the topological sequence reorganization module analyzes heterogeneous diagnosis and treatment data streams and reorganizes the data streams into logically continuous patient whole-course data aggregates; the physical space mapping module sequentially maps the aggregates to a continuous physical address space of a bottom-layer storage; the index key synthesis module generates composite index items according to physical address offsets among data blocks; and the preloading execution engine drives the bottom-layer storage to burst read, the application converts cross-modal diagnosis and treatment correlation queries into one-way sequential reading of the storage, reduces the track delay and access overhead in the searching process, and guarantees the searching response delay certainty under the condition that the data volume continuously grows.

Systems and processes for operating an intelligent automated assistant are provided. An example method includes, at a computer system that is configured to communicate with a display generation component and an input device: detecting an audio input including a query; in response to detecting the audio input including the query: retrieving contextual data related to the query; in accordance with a determination that the query includes a request of a first type: converting the query to a rewritten query based on the contextual data related to the query; and providing the rewritten query to a first digital assistant component; and in accordance with a determination that the query includes a request of a second type different from the request of the first type, providing the query and the contextual data related to the query to a second digital assistant component different from the first digital assistant component.

This invention provides a system and method for providing cross-microservice query processing. [Solution] A system providing an object service framework 202 that supports the use of microservices A210 that interact with each other or request access to each other's data to process queries, wherein each microservice can be independently developed, deployed and evolved, and interacts with other microservices through contracts and interfaces defined as public APIs and exposed through the framework. The framework is used to provide a cross-microservice layer that automatically translates queries that combine objects from different microservices into a single database query optimized for use in that database.

A method, computer program product, and computing system for processing a dataset of query-answer pairs. Synthetic variations of queries are generated and each of the synthetic variations of queries are mapped to a corresponding answer from the dataset. An embedding dataset is generated by transforming the synthetic variations into synthetic query embeddings and the queries into query embeddings. A first set of embeddings is defined for storage in a semantic cache and a second set of embeddings are defined and are not stored in the semantic cache. A separate distance threshold is assigned to each embedding of the first set of embeddings and a pairwise distance between each query and the synthetic variations is determined. Distance thresholds for respective pairwise distances between a query and synthetic variations of the query are generated. Subsequent queries are processed using the semantic cache and the distance thresholds.

The invention discloses an LLM-based query semantic caching method oriented to an access scene, electronic equipment and a medium. The method comprises the following steps: acquiring a full amount of historical query and a corresponding domain-specific language; converting the total historical query into a historical query vector; screening the historical query vectors, and constructing a query semantic cache based on the screened historical query vectors and the corresponding domain-specific languages; obtaining a current user query, and converting the current user query into a current user query vector; retrieving in the query semantic cache based on the current user query vector, and if the current user query vector hits the query semantic cache, constructing a cue word according to a historical query vector obtained by matching and a corresponding domain-specific language; in response to the cue word, the large language model outputs a final domain-specific language.