166 results about "Query transformation" patented technology

A knowledge fusion multi-modal interaction method and apparatus based on an improved alignment method. The method comprises: acquiring multi-modal data (S101); constructing a query transformation model (S102); on the basis of a multi-stream feature extraction method, performing improved processing on a vision transformer to obtain a multi-scale vision transformer (S103); on the basis of a joint text method, training the multi-scale vision transformer to obtain a target vision transformer (S104); freezing the target vision transformer, and on the basis of the target vision transformer, performing vision-text alignment training processing on the query transformation model to obtain a target query transformation model (S105); connecting the target query transformation model to a language model to obtain a knowledge fusion multi-modal interaction model (S106); and inputting the multi-modal data into the knowledge fusion multi-modal interaction model to obtain an interaction result (S107). In the embodiments of the present invention, the knowledge fusion multi-modal interaction model aligns visual representation with text representation, so that the mutual information between the visual representation and the text representation can be maximized, and the present invention can be widely applied to the technical field of artificial intelligence.

A knowledge management system may generate a plurality of prompts based on divisions of documents of unstructured text, each prompt relevant to a division of unstructured text. At least one prompt is generated such that a corresponding division of unstructured text is a response to said at least one prompt. The system may generate prompt embeddings for the plurality of prompts corresponding to the plurality of documents of unstructured text. The system may generate prompt-embedding clusters to group similar prompts from one or more documents of unstructured text. The system may receive a query. The system may convert the query to one or more query embeddings. The system may identify one or more prompts that are relevant to the query based on comparing the one or more query embeddings to the prompt embeddings. The system may identify one or more documents in one or more prompt-embedding clusters.

The invention discloses an intelligent automobile question and answer method based on a large model and retrieval enhancement generation, and the method comprises the steps: 1, receiving a user query, carrying out the preliminary retrieval of a user query vector through a mixed index retrieval module, and generating a candidate result; 2, judging whether the relevancy of the retrieval result meets a preset threshold value or not, and triggering query conversion enhancement and re-retrieval when the relevancy of the retrieval result does not meet the preset threshold value; thirdly, retrieval results are rearranged according to the correlation degree; and step 4, the system generates a query related prompt word, combines the original user query as input, and generates and returns a question and answer result. The invention further discloses a system for implementing the method, and the system has wide application value.

A data processing system implements receiving, via a user interface of a client device, a query to a large language model (LLM) working in conjunction with an embedding model comprising a corpus of artifacts. The system further implements converting the query into a query embedding, transforming the query embedding into a transformed query embedding using a first transformation function that adds a first residual term to the query embedding, the first residual term being specific for a task associated with the query, measuring a first similarity between the transformed query embedding and corpus element embeddings in an embedding space of the embedding model, determining first top-rated corpus element(s) associated with the corpus element embeddings based on the first similarity, incorporating the first top-rated corpus element(s) into the query as a prompt to the LLM to generate a response to the query, and providing, via the user interface, the response.

A system is adapted to automatically report the trustworthiness of an entity. The system includes a processor and a computer readable medium carrying instructions. The instructions include receiving unstructured data pertaining to an entity from public sources, and receiving structured data pertaining to the entity from at least two databases. The instructions also include merging the structured data and the unstructured data into a single document; splitting the single document into chunks; creating embeddings corresponding to the chunks; and storing the embeddings in a vector store. The instructions also include receiving a natural language user query regarding trustworthiness of the entity; converting the query to a query embedding; based on the query embedding and a similarity calculation, fetching a relevant embedding from the vector store; with a large language model (LLM), generating a query response regarding the trustworthiness of the entity; and communicating the query response to the user.

A method for managing a framework includes: receiving, by a GUI, a query that is sent to a first module; analyzing, by the first module, the query to infer intention; making, by the first module, a determination that the intention is not searching for an object in a database; sending, by the first module, the query to a second module; transforming, by the second module, the query into a vector that is sent to a third module; performing, by the third module and using the vector, a search for a nearest image in the database; identifying, by the third module, a path associated with the nearest image, which is sent to an analyzer, in which the analyzer further sends the path to a fourth module; and fetching, by the fourth module and based on the path, an image from a store, which is sent to the GUI.

Certain aspects of the disclosure are directed to searching programming code repositories. In examples, a method is provided that includes receiving a natural language search query via a graphical user interface; converting the natural language search query into a vector representation; determining a proximity score between the vector representation of the natural language search query and at least one vector representation corresponding to a machine learning model generated natural language description of a programming code segment; and providing a search result corresponding to the programming code segment based on the proximity score.

A system and method of using generative AI to convert NL queries to database commands for accessing one or more databases. The method includes receiving a natural language (NL) request for information associated with a private network. The method includes providing the NL request to an artificial intelligence (AI) model trained to identify, from a plurality of access objects associated with a plurality of databases and a plurality of event types, a particular access object that provides access to one or more event datasets associated with the NL request. The method includes generating, by a processing device and using the AI model, a database request associated with the particular access object based on the NL request.

Systems and methods for processing search queries are provided. A method, according to one implementation, includes a step of receiving a query from a user interface, the query including one or more questions or commands pertaining to datasets stored in a relational database. The method also includes a step of generating a prompt having instructions related to how a Large Language Model (LLM) is to handle a complex query having one or more cascading dependencies. Also, the method includes a step of providing the prompt, datasets, and query to an LLM with instructions to convert the query into Structure Query Language (SQL) code.

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.

The invention relates to a quick file retrieval method, a product, computer equipment and a storage medium. The method comprises the following steps: performing vectorization representation on text content in an original document to generate a document vector; clustering and grouping the original documents according to the similarity between the document vectors to form a plurality of document clusters; setting the dynamic priority of the original documents in each document cluster according to the updating frequency and / or query frequency of the original documents in the document clusters; establishing an index structure for the document vectors, and adjusting the order of the document vectors in the index structure according to the dynamic priority of the original document; when the query initiated by the user is responded, the query of the user is converted into a query vector, and the original document related to the query of the user is obtained by calculating the similarity of the document vectors in the index structure after the query vector and the document vectors are sequenced. Retrieval efficiency can be effectively improved, documents with high dynamic priorities can be quickly searched, and system response delay or resource consumption is reduced.

In some examples, a method of optimising vector embedding for natural language processing comprises receiving a query from a user, converting the received query into a set of search criteria, determining, using the search criteria, a set of data files from multiple data files, wherein the set of data files comprises a first data file, determining whether a vector embedding associated with the first data file exists, and, in response to determining that a vector embedding associated with the first data file does not exist, generating a vector embedding associated with the first data file and adding the vector embedding associated with the first data file to a vector database.

A system includes a computing server having a processor and memory. The memory is configured to store code including instructions. The instructions, when executed by the system, cause the system to perform steps including receiving a query from a user device, identifying a first interface of a plurality of interfaces on which to execute the query, converting the query into a first format suitable for use with the first interface, executing the query in the first format on a first target system that uses the first interface such that the query is transmitted to the first target system in the first format and the first target system processes the query by retrieving or modifying requested data, and receiving the results of the executed query from the first target system. A graphical user interface is in communication with the computing server and configured to display the received results.

The embodiment of the invention discloses a training method and device of a certificate anti-counterfeiting detection model, a computer readable storage medium, electronic equipment and a computer program product. The training method of the certificate anti-counterfeiting detection model can comprise the following steps: training an initial certificate feature extraction model comprising a video encoder and a query converter of which at least part of parameters are in a frozen state by utilizing a first training sample comprising a first certificate image sequence and a description text for a first certificate sample, and obtaining a target certificate feature extraction model capable of learning visual representation most related to the certificate description text. Training an initial certificate anti-counterfeiting detection model containing a target certificate feature extraction model and a large language model of which the parameters are in a frozen state by utilizing a second certificate image sequence containing a second certificate sample and a second training sample of a preset prompt word, and obtaining a target certificate anti-counterfeiting detection model capable of generating a certificate anti-counterfeiting detection result in a text form.

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.

A system is adapted to automatically identify patterns of potentially suspicious activity, and includes a processor configured to receive, with a user interface, a natural language user query regarding a potentially suspicious transaction, entity, or event. The processor converts the query to a structured query, and fetches relationship data related to the transaction, entity, or event from a relationship repository. For each relationship in the relationship data, the processor constructs a database query based on the structured query, retrieves a record from a query database, fetches customer data from a customer database, and aggregates all of this data into a preliminary prompt. With a prompt composer, the processor receives attributes from an attributes repository, and aggregates the attributes and the preliminary prompt to compose a response prompt. A large language model generates a natural language response related to the potentially suspicious transaction, entity, or event based on the response prompt.

A system and method for enhancing query responses from large language models without retraining by converting a query into a query vector; using a proximity metric to measure a proximity from the query vector to a plurality of vector embeddings stored in a vector database; ranking the plurality of vector embeddings based on proximity to the query vector; mapping the query to a homogenized context vector from a plurality of homogenized context vectors; using an augmented proximity metric to convert the proximity to an augmented proximity for each vector embeddings; performing an augmented ranking to refine the vector embeddings to those most relevant to the query; creating a prompt for a large language model comprising the query and the text data corresponding to refined vector embeddings as context; and feeding the prompt to the large language model to generate a response to the query.

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 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 embodiment of the invention discloses a large model training method for query conversion, a database query method, computer equipment and a computer readable storage medium. The training method comprises the steps of obtaining an original large model and a training record set; and processing all the training records to obtain the first prompt statement, the second prompt statement, the first output and the target SQL query so as to train the original large model, and deploying the trained original large model as a natural language conversion module in the database management system. According to the database query method, a historical query cache module and a natural language conversion module are newly added in a database management system. The historical query cache module is used for executing text vectorization, vector indexing and nearest neighbor retrieval according to an input query; the natural language conversion module is used for collecting related forms and fields according to input queries and converting the input queries into SQL (structured query language) queries. According to the method and the device, the natural language query can be more accurately converted into the SQL query by using fewer computing resources.

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.

A computer-implemented method for improving a predictive response of a machine learning-based virtual dialogue agent includes identifying an unfilled dialogue slot associated with an active dialogue between a user and the machine learning-based virtual dialogue agent, obtaining subsequent dialogue input data based on prompting the user for the unfilled dialogue slot, and computing a value of the unfilled dialogue slot based on the obtaining of the subsequent dialog input, wherein computing the value of the unfilled dialogue slot includes computing, via a question-answering machine learning model, a slot answer inference comprising the value of the unfilled dialogue slot based on an input of a machine learning-derived query and machine learning-derived context computed for the unfilled dialogue slot.

A server system is communicatively connected to a plurality of computing devices and one or more databases. The server system receives one or more queries from a computing device. The one or more queries specify a data source. The server system determines a level of security applicable to a user of the computing device. The server system translates the one or more queries into one or more logical queries according to semantics of the data source, and transmits the logical queries to a query pipeline of the server system. The server system executes the one or more queries against a first database of the one or more databases to retrieve query results from the data source. The server system applies the determined level of security to the query results to obtain one or more data sets, and returns the one or more data sets to the computing device.

The invention provides a data query method and device, electronic equipment and a storage medium. The method comprises the steps that a target SQL query statement is split, a plurality of target sub-queries are obtained, and the target SQL query statement is a statement used for conducting data query in a relational database; according to all the conditions in each target sub-query, a target graph query corresponding to each target sub-query is obtained through conversion, and the target graph query is a graph structure used for indicating the relation between any two conditions in all the conditions in the corresponding target sub-query; querying in a relational database through each target graph query to obtain a sub-query result corresponding to each target graph query; and obtaining a target query result corresponding to the target SQL query statement based on all the sub-query results. By means of the method and device, the problems that when SQL query is converted into graph query in the prior art, the workload of manually writing the conversion rule is large, and complex query is difficult to deal with are solved.

A method may include storing a vector space representation of a set of concepts in a semantic ontology, wherein locations of the set of concepts in the vector space are based on weights of a neural network trained using triples from the semantic ontology; presenting a semantic search user interface including: a text input portion to receive a search query from an input device; a suggested search portion; and a search results portion; receiving, from a user computing device, the search query; converting, using at least one processor, the search query into a vector; computing, using the at least one processor, a set of possible concepts related to the search query based on a distance between the vector and other concepts in the vector space representation; and presenting the set of possible concepts related to the search query in the suggested search portion of the semantic search user interface.

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.

The invention discloses a data management method integrating real-time analysis and offline analysis. The method comprises the following steps: storing data by adopting an LSM-Tree structure; a WAL log in the LSM-Tree structure is replaced with a change log; the change log is aligned with the SST data file of the LSM-Tree by using the snapshot, and the message is queried according to the snapshot; positioning a snapshot, positioning a log file, reading log data and recording offset; and the query of real-time calculation of the intermediate data is converted into the query of the SST data file of the LSM-Tree. According to the invention, the problem that the existing data processing framework of the combined and offline data and the real-time data lacks one of the functions of realizing real-time analysis and offline analysis and reducing the operation and maintenance cost at the same time is solved.

Systems and methods for compressing and querying data for real-time analytics. The system can receive log data and generate an intermediate representation by parsing a log template and variables from the log data into a columnar format. The method includes generating a compressed intermediate representation associated with an index type and storing the compressed intermediate representation in the columnar format based on the index type. The method includes receiving a search query and analyzing the search query to identify a user defined function. The method includes parsing the search query to convert the search query into one or more predicates that satisfy the search query. The method includes filtering the compressed log data based on the one or more predicates and providing a query result.

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.