4044 results about "Information retrieval" patented technology

A system and a method for verifying authenticity of a physical copy and a digital copy of a document are disclosed. The method comprises registering a document in a repository by storing details related to the document in a location of the repository. A symbology for the document is generated. The symbology is an identifier of the location of the repository comprising the document. The symbology is associated with either a physical or a digital copy of the document. The digital copy of the document is printed to generate a printed copy. The printed copy or the physical copy of the document is scanned to generate a scanned image. The document and the details related to the document present at the location of the repository are accessed. The scanned image is compared with the document stored in the repository to determine the authenticity of either the physical copy or the digital copy of the document.

A content editor or a plugin thereto automatically generates authorship tokens that identify content authored by a human author or an artificial author. The authorship tokens are applied to the work while the work is being produced. Thus, subsequent review of the work can identify regions produced by a human author and other regions produced by an artificial intelligence.

Systems and methods for enhanced conversational performance of large language models using adaptive retrieval-augmented generation are disclosed. A method may include: (1) receiving a query from a user; (2) retrieving a plurality of summaries of historical conversations from a database of historical conversation summaries similar to the query; (3) generating a first prompt comprising the query and the plurality of summaries; (4) submitting the first prompt to a first large language model (LLM); (5) receiving, from the first LLM, a first response; (6) presenting the first response to the user; (7) generating a second prompt for a summary of the query and the first response; (8) submitting the second prompt to a second LLM; and (9) saving a second response to the second prompt from the second LLM to the database of historical conversation summaries, wherein the second response comprises the summary.

Methods and systems for retrieving relevant information in response to an input question. The method includes obtaining text content related to the input question and partitioning the content into one or more paragraphs based on predefined rules. The method further involves extracting one or more evidence spans that are relevant to the input question by inputting the text content and the question into a trained language model. A semantic search is then performed on both the paragraphs and the extracted evidence spans, ranking the candidate passages based on their relevance to the input question. Each candidate passage may comprise either a paragraph or an evidence span that addresses the question. The disclosed methods and systems improve the quality and relevance of retrieved information by combining heuristic-based content partitioning with machine learning-based evidence extraction.

Examples described herein relate to techniques for facilitating selection of stickers for inclusion in messages within the context of an interaction system. According to some examples, message content is detected and a set of candidate stickers is identified based on the message content. A search icon is dynamically replaced with a representation of respective ones of the set of candidate stickers. At a first point in time, the search icon represents a first candidate sticker of the set of candidate stickers. At a second point in time, the search icon represents a second candidate sticker of the set of candidate stickers.

Disclosed herein, is a method and system for selecting a LLM for response generation to user queries. The method includes receiving a user query from a user device. The method includes determining, for the user query, a query type from a set of query types through a fine-tuned text classification model. The method includes retrieving a plurality of document embeddings based on the user query and the query type from a vector database through a semantic search technique. The method includes preparing a prompt using the user query and the plurality of document embeddings. The method includes inputting the prompt to an LLM selected from a set of LLMs based on the query type. The method includes generating, via the selected LLM, a response to the user query based on the prompt.

The invention provides an object retrieval method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a retrieval target which comprises at least one seed object; extracting semantic features of each seed object from the description text of each seed object; according to the semantic features of the seed objects, a candidate object set similar to the retrieval target semantics is recalled from a candidate object library; under the condition that the data volume of the candidate object library is smaller than a threshold value, sorting the recalled candidate object sets by utilizing the attribute tags of the seed objects; and determining a similar object recommendation list corresponding to the retrieval target from the candidate object set according to the sorting result. According to the method, the deep semantics of the unstructured text and the concrete index of the structured tag are integrated, so that the problems of single matching dimension and insufficient accuracy caused by only depending on single tag matching are avoided, and the accuracy and comprehensiveness of similar object retrieval are remarkably improved.

Provided are system, apparatus, device, method and / or computer-program product embodiments, combinations and / or sub-combinations thereof for using an AI model to facilitate natural language interactions with databases. An example method can include receiving a natural language prompt associated with a user and identifying tables in a database based on the natural language prompt. The method can further include determining a table schema(s) of each of the tables identified, generating, using a large language model, a query to the tables in the database based on the natural language prompt and the table schema(s), and obtaining, using the query, data from at least one table of the tables in the database. The method can include generating, using the large language model or another large language model, a response to the natural language prompt based on the data obtained from the at least one table of the tables in the database.

A computer-implemented method for improved schema matching of two databases is disclosed. The method can receive a schema of a source table from a first database and a schema of a plurality of target tables from a second database, identify one or more matching tables among the plurality of target tables based on comparison of the schema of the source table and the schema of the plurality of target tables using a large language model, obtain first sample attribute data from the source table and second sample attribute data from a selected matching table, and identify one or more pairs of matching attributes between the source table and the selected matching table based on comparison of the first sample attribute data and the second sample attribute data using the large language model. Related systems and software for implementing the method are also disclosed.

A computerized method is provided for using large language models to integrate data from multiple sources including technical metadata (e.g. column and table names) with a dictionary of standard abbreviations employed in the metadata, representative data from the columns rows of the table, a business glossary of terms in the data, and representative queries used to interrogate the data, to create a non-technical or natural language description of business value of the table and its columns and data.

The invention discloses a webpage data collection method and a related device, and relates to the technical field of data processing.The webpage data collection method comprises the steps that a webpage data collection knowledge base containing data collection modes of various webpages is constructed in advance; a data acquisition mode matched with the webpage is obtained from a webpage data acquisition knowledge base, and the data acquisition mode defines that an analysis mode of each field in the webpage is analyzed based on multi-modal features (at least two of DOM structure fingerprint features, visual position features and semantic features of the fields); according to the method, the analysis accuracy of the webpage data can be greatly improved, so that stable and efficient execution of a webpage data acquisition task is guaranteed.

The invention provides a large model retrieval enhancement generation method fused with a multi-source knowledge base, and relates to the technical field of large model retrieval enhancement generation. The method comprises the steps that firstly, user query is analyzed, multiple implied independent retrieval intentions are recognized and separated, and a knowledge source identifier is distributed to each retrieval intention subtask based on a mapping rule; according to the method, related evidence fragments are acquired in parallel from a heterogeneous knowledge source library in a targeted manner, multi-level relation analysis is further performed on the original evidence fragments by introducing a cross validation engine, so that a structured evidence conflict graph is constructed, and then the evidence conflict graph is intelligently processed by applying a game theory excitation algorithm. The method comprises the following steps: obtaining an evidence set with internal consistency, forming a guide signal through structured analysis, and finally, inputting original user query, the synthesized evidence set and the guide signal into a large language model in combination with a pre-constructed cue word template to generate a final answer under constraint, so as to realize retrieval enhancement generation fused with multi-source knowledge base retrieval.

Hybrid content item chunking techniques for retrieval augmented generation (RAG) systems are disclosed. The techniques employ a dual approach, combining size-based and semantic chunking with layout-based chunking. The techniques analyze content for layout indicators, creating two sets of chunks that are then merged into a hybrid set. This hybrid set is loaded into a database for subsequent searches. The techniques offer several technical advantages, including improved handling of diverse document types, potential for parallel processing, and enhanced capture of both semantic meaning and structural layout. By maintaining size constraints and adapting to various formats, the techniques provide a more comprehensive representation of document content. The techniques overcome limitations of single-method approaches, potentially leading to more accurate information retrieval, improved context preservation, and enhanced RAG system performance across varied document types.

The invention relates to the field of content recommendation, in particular to an intelligent content recommendation method and system of an intelligent display all-in-one machine. The method comprises the following steps: identifying user login information, extracting a user historical log, performing data cleaning, and generating an abnormal cleaning log; analyzing a time sequence watching behavior of the user according to the exception cleaning log, and constructing a user interest evolution portrait; identifying a current input instruction, performing deep semantic analysis, and generating a current content type demand; performing intelligent content recommendation based on the user interest evolution portrait and the current content type demand to obtain a recommendation result; and performing split-screen display processing on the recommendation result to generate a split-screen demonstration display page. The recommendation accuracy of the user preference content is improved in a targeted manner, the user experience is enhanced, and the intelligent level and the multi-scene adaptability of the display all-in-one machine are improved.

The invention discloses a knowledge question-answering method and system based on a large language model and a semantic abstract. The system comprises a tree structure abstract generation subsystem which comprises a knowledge base configuration module, a file management module, a document analysis module and a knowledge block management module and is used for automatically generating tree structure hierarchical knowledge blocks for large manual documents or multi-chapter manual documents; the dual-channel retrieval engine subsystem comprises a question rewriting module, a semantic abstract retrieval module, a detail knowledge block retrieval module, a father-son retrieval module and a prompt word construction module, and all the modules work cooperatively to ensure that semantic abstract knowledge blocks and detail knowledge blocks related to the question of the user are retrieved. According to the method, by introducing the semantic abstract based on the tree structure and the two-channel retrieval, perception of global knowledge and accurate extraction of local fine-grained knowledge can be achieved at the same time, and then the ability of a knowledge base question-answering system in processing the general and inductive problems is improved.

Embodiments of the disclosed technologies are capable of generating, using a machine learning model and a prompt, first content recommendations. The prompt comprises a search query and historic information associated with an entity. The first content recommendations are presented. The embodiments describe receiving a selection of a content recommendation of the first content recommendations. The embodiments describe generating, using the machine learning model and a second prompt, second content recommendations. The second prompt comprises a second search query and second historic information associated with the entity. The embodiments describe generating a ranked order of the second content recommendations using a history of entity interactions including the selection of the content recommendation of the first content recommendations. The embodiments describe determining context-aware recommendations by optimizing a permutation of the ranked order of the second content recommendations. The embodiments describe causing the context-aware recommendations to be presented.

Embodiments described herein related to systems and methods for generating comments in a page of a content collaboration platform. In some examples, the user interface of the platform is configured to display a page within a content region. The content region includes a comment control that, upon user selection, causes a prompt to be generated and submitted to a generative output engine via an Application Programming Interface (API). The prompt may include a portion of the content selected by a user and user-specific data, such as a user role. This data is used as context to the prompt alongside a predefined query. The output from the generative output engine may be used to generate a set of suggested comments, which are displayed in a comment interface within the content region of the content collaboration panel.

Systems and methods for retrieving information from a corpus of documents that is relevant to a query. The method comprises: generating a first plurality of chunks by subdividing each document in the corpus of documents into one or more chunks of a first size; generating a second plurality of chunks by subdividing each document in the corpus of documents into one or more chunks of a second, larger, size; using an information retrieval system to identify, from the second plurality of chunks, a set of chunks of the second size that are relevant to a query; and using the information retrieval system to identify, from a subset of chunks of the first plurality of chunks, a set of chunks of the first size that are relevant to the query. The subset is based on the set of chunks of the second size that are relevant to the query.

The invention relates to the technical field of literature processing, and discloses a literature review generation method and system, electronic equipment and a storage medium, and the method comprises the steps: receiving a research theme input by a user, and forming a reference literature set; according to the number of literatures in the reference literature set, a clustering strategy is selected, a structured review is generated based on a clustering result, and generation of the structured review comprises generation of alternative titles, construction of a multi-level outline, generation of research status paragraphs according to the outline and generation of brief reviews; receiving editing operation of a user on the outline, the research status paragraph and the brief review in the process of generating the structured review, and performing quality evaluation and optimization processing on the research status paragraph and the brief review; and when the current paragraph is researched to be generated, the reference literature is matched and the reference mark is inserted, a standard reference literature list is generated, and a traceability link from the in-text reference to the original literature is established. According to the method, literature review with a rigorous structure and coherent logic can be generated, and disordered stacking of information is avoided.

The embodiment of the invention provides a question and answer generation method and device combined with knowledge search, a storage medium, electronic equipment and a computer program product, and relates to the technical field of artificial intelligence. The method comprises the following steps: obtaining a user query, wherein the user query comprises question information proposed by a user; based on the user query, a corresponding target reasoning template is matched from a structured reasoning template library, and historical queries and structured reasoning templates associated with the historical queries are stored in the structured reasoning template library; determining a search instruction based on the user query and a knowledge search strategy indicated by the target reasoning template; performing knowledge search according to the search instruction to obtain knowledge information related to the user query; and generating an answer for the user query based on the knowledge information through a first large language model. According to the embodiment of the invention, the reliability of the answer generated by the large language model can be improved.

The invention discloses a document information input method and device and a storage medium, and relates to the technical field of electronic digital data processing.The document information input method comprises the steps that a document type is determined according to characters obtained by recognizing a to-be-processed document; calling a large language model to extract an entity in the character, and associating an entity relationship, a service intention, a context and a context relationship corresponding to the entity as reference information of the entity; constructing an extraction problem based on a field in a business data structure file corresponding to the document type; and in combination with the reference information, extracting a target field from the entity through the extraction question. According to the method and the device, the technical effect of efficiently and accurately converting the fragmented characters into the structural data available to the business system can be realized.

Systems and methods are described for receiving a query of a user. A first portion of the query is identified for which resolution is dependent on access to data of a third party. A connection type between the user and the third party is determined. In response to the connection type being of a predetermined type, access to the data of the third party is provided. The data of the third party is retrieved. The first portion of the query is resolved using the data of the third party.

Systems and method for generating a response to a query. The method includes using a first large language model (LLM) to generate synthetic information related to a query; generating an amended query based on the synthetic information related to the query; using an information retrieval system to retrieve, from a plurality of chunks, a set of chunks that are relevant to the amended query, wherein each chunk of the plurality of chunks is all or a portion of a document in a corpus of documents; using a second LLM to rank the set of chunks based on a relevance to the query; selecting a subset of chunks from the set of chunks based on the ranking; and using a third LLM to generate a response to the query based on the subset of chunks.

There are provided systems and methods for identifying relevance of documents for automated retrieval models using large language models. An online transaction processor or other service provider may provide computing services and platforms to entities, which may include chatbots, information retrieval systems, question-and-answer systems, and the like. To provide better retrieval model training and refinement, the service provider may generate training data from user interaction logs, which may include user feedback that may be used to determine if documents are relevant to queries, and therefore should be retrieved for answering those queries by automated retrieval models. An LLM may be used as a judge to determine whether chatbot responses reference certain document. If not references, the query may be analyzed to determine whether certain retrieved documents are relevant. Data pairs may be generated for the training data from these processes and used for model refinement.

The embodiment of the invention provides a data query method and system. The data query method comprises the steps that a data query request associated with a target field is received; identifying query intention information corresponding to the data query request, and constructing a query prompt word corresponding to the data query request according to the query intention information; the query prompt word is input into a target distillation model to be processed, a data query sequence corresponding to the data query request is obtained, and the data query sequence comprises a data query statement and a data query reasoning chain associated with the data query statement; and executing the data query statement to obtain data query information, and reading target data in a target data table associated with the target field based on the data query information to serve as a response of the data query request.

A semantic robotic device system stores a semantic goal and semantic profiles having semantic artifacts. A processor is configured to infer further semantic artifacts in rapport with semantic goals based on an application of semantic artifacts from a semantic profile and an affirmative semantic resonance in rapport with semantic artifacts. The processor is configured to generate thin client presentation data as a representation of semantic artifacts in association with first and second identities, and causes at least one transceiver to transmit the thin client presentation data to a remote device.

Aspects of the present disclosure relate to an online resource that can initiate a conversation between a user and an automated assistant. The online resource receives from the user a query including a plurality of sub-queries, determines a context for each of the sub-queries, identifies a plurality of queries from the user during the conversation between the user and the automated assistant, and obtains responses to the sub-queries from a plurality of selected agents. The online resource determines a similarity score for each response by comparing the response with at least the context for the corresponding sub-query, summarizes the responses based at least in part on the similarity scores, and generates an answer to the query by combining the response summaries based at least in part on an alignment between the response summaries and their corresponding sub-queries.

The invention discloses a data query method and device, a nonvolatile storage medium and electronic equipment. The method comprises the following steps: determining domain information corresponding to a to-be-processed document; determining a preset cleaning rule base corresponding to the field information, and identifying and correcting an error text in the to-be-processed document according to the preset cleaning rule base; segmenting the to-be-processed document after the error text is corrected to obtain a plurality of text blocks, and storing the text blocks and text block vectors corresponding to the text blocks into a database; and after a query instruction sent by a target object is received, determining a target text block corresponding to the query instruction according to the query vector and the text block vector corresponding to the query instruction, and generating a query result according to the target text block. The technical problem that the documents cannot be effectively corrected due to the fact that the same set of universal cleaning rules is adopted for all the documents in the prior art is solved.

The embodiment of the invention provides a content recommendation method and device and a double-tower content recommendation model training method and device, and the content recommendation method comprises the steps: obtaining the content information of to-be-recommended content and the user information of a target user in response to a content recommendation task; the user information and the content information are input into a double-tower content recommendation model, recommended content for the target user is obtained, the double-tower content recommendation model comprises a user tower and a content tower, the user tower is used for extracting user features based on the user information, and the content tower comprises a feature adaptation layer; the feature adaptation layer is used for obtaining target content features corresponding to a task target of the content recommendation task based on the content information, and the recommendation content is obtained by decoding based on the target content features and the user features. The content representation can be dynamically adjusted according to the task target through the feature adaptation layer, so that the same content presents differentiated feature expression under different tasks, and the adaptation precision of the recommendation result to the specific task target is improved on the premise of not changing the double-tower structure.