Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

32 results about "Search engine query" patented technology

A search engine query is a request for information that is made using a search engine. Every time a user puts a string of characters in a search engine and presses "Enter", a search engine query is made.

Generating narrative query responses utilizing generative language models from search-based autosuggest queries

This disclosure describes a query gateway system that provides an efficient and flexible framework for providing context-retained autosuggest queries from an autosuggest query system (e.g., a search engine query experience) to a generative language model system (e.g., an AI chat experience). For instance, the query gateway system establishes a framework to leverage the features and services of the autosuggest query system and automatically provides context-retained queries to the generative language model system using separate user interfaces that do not disrupt user navigation or require manual duplicative user input. Additionally, the query gateway system incorporates additional enhancements, including an AI chat eligibility model and a query reformulation model, to improve the computational efficiency and accuracy of the AI chat system.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Address error correction method fusing large language model and map positioning

The invention discloses an address error correction method fusing a large language model and map positioning, and the method comprises the following steps: 1, recognizing address entity data from texts in different input modes through a deep learning NER method; 2, querying the address entity data through a map API search engine to generate a candidate address list; 3, calculating the candidate address list by adopting the comprehensive similarity evaluation score to obtain an optimal matching address; 4, judging whether the optimal matching address is consistent with the address entity data and the original address information in the text or not; if the conditions are met, ending; otherwise, entering the next step; step 5, according to the address entity data and the matching address, carrying out an error correction process on a wrong address in the original text; according to the method, the address text accuracy of the AI model in the text conversion process of different input modes can be improved.
Owner:TIANJIN UNIV

Generating narrative query responses utilizing generative language models from search-based autosuggest queries

This disclosure describes a query gateway system that provides an efficient and flexible framework for providing context-retained autosuggest queries from an autosuggest query system (e.g., a search engine query experience) to a generative language model system (e.g., an AI chat experience). For instance, the query gateway system establishes a framework to leverage the features and services of the autosuggest query system and automatically provides context-retained queries to the generative language model system using separate user interfaces that do not disrupt user navigation or require manual duplicative user input. Additionally, the query gateway system incorporates additional enhancements, including an AI chat eligibility model and a query reformulation model, to improve the computational efficiency and accuracy of the AI chat system.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Determining flow paths of packets through nodes of a network

A search engine queries a network model for behavior of the entire network, such as data flow, based on combinations of multiple network elements. The search engine provides the state information and / or predicted behavior of the network by searching network objects in a graph-based model or a network state database that satisfy constraints given in a search query. The search engine provides the state information and / or predicted behavior based on regular-expression or plain language search expressions that do not provide packet header information. The search engine parses such search expression into a sequence of atoms that encode forwarding paths of interest to the user. A flow path through the modeled network can be generated dynamically, within the context of the search queries.
Owner:VMWARE INC

Computer implemented method for improving search engine queries

A computer implemented method for improving search engine queries including receiving a text corpus, determining a list of n-gram candidates, each being a series of consecutive words of said text corpus, the number of said consecutive words within said series being an integer n superior or equal to two, modifying at least partially said text corpus based on said list of n-gram candidates, performing a machine learning embedding on the resulting text corpus, for each element in said list of n-gram candidates, computing a score based on the embedding of said element and the embeddings of the words making up said element, adding one or more of the n-gram candidates to a search engine queries items list based on their respective scores.
Owner:DASSAULT SYSTEMES SA

Method and system for relieving large model illusion

The invention relates to a method and system for relieving large model illusion, and belongs to the technical field of computers. The method comprises the following steps: identifying and analyzing the intention of a question input by a user through a first-level agent, and judging whether an answer is obtained by calling a local knowledge base, a search engine or the capability of a large model; if a search engine is called, pulling the question through a first-level agent, and inputting the content of each webpage, website information, the question input by the user and a prompt cue word into a large model to obtain an answer, wherein the previous set number of webpages are related to the content inquired by the search engine; if a local knowledge base is called, analyzing the question through a secondary agent and generating a query instruction corresponding to the question, performing interactive query with professional databases of industries to which at least two questions with different query modes belong through the query instruction to obtain a query result, and inputting the question input by a user, a prompt prompt word and the query result into a large model to obtain an answer; if the capacity of the large model is called, an answer is obtained through the large model according to the question.
Owner:XJ ELECTRIC CO LTD +2

Extension of machine learning language models using search engine results

System comprising one or more computers and one or more storage devices that store instructions which, when executed by the one or more computers, cause the one or more computers to perform operations that include: Obtaining query data that constitutes a question; Generating a search engine query for a search engine from the query data; Obtaining a large number of documents identified by the search engine in response to processing the search engine query; Generating a multitude of conditioning inputs, each representing at least one section of one or more of the obtained documents, from the multitude of documents; for each conditioning input generated from a multitude of inputs, processing a network input generated from (i) the question data and (ii) the conditioning input using a neural network to produce a network output that represents a candidate response to the question; and Generating response data that represents a final answer to the question from the network outputs representing the respective candidate responses.
Owner:DEEPMIND TECH LTD

Generating narrative query response from search-based auto-suggestion query using generative language model

The present disclosure describes a query gateway system that provides an efficient and flexible framework for providing context-preserved auto-suggestion queries from an auto-suggestion query system (e.g., a search engine query experience) to a generative language model system (e.g., an AI chat experience). For example, a query gateway system establishes a framework to automatically provide context-preserved queries to a generative language model system using features and services of an automatically suggested query system and using a separate user interface that does not interfere with user navigation or requires manual replication of user input. Additionally, the query gateway system incorporates additional enhancements, including an AI chat eligibility model and a query reformulated model, to improve the computational efficiency and accuracy of the AI chat system.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Data processing system for generating entries in data structures from network requests

A data processing system for searching network requests to extract values of parameters in the network requests includes a shared memory that stores data structures, wherein each of the data structures is stored in association with a value of a key, and wherein each of the data structures includes one or more entries for storage of data representing a network request. A parser engine parses a particular network request for values of parameters and for a value of a key. A search engine queries the shared memory for a particular data structure stored in association with the value of the key. A logic engine detects an absence of a particular entry, in the particular data structure, that stores data representing the particular network request, generates an entry in the particular data structure, and stores in the generated entry the values of the parameters.
Owner:GOOGLE LLC

Method, device and equipment for evaluating hotspot technology based on generative artificial intelligence

The present application relates to the technical field of hotspot technology evaluation, and particularly relates to a hotspot technology evaluation method, device and equipment based on generative artificial intelligence, which responds to a hotspot technology keyword, queries technical literature corresponding to the hotspot technology keyword and metric data corresponding to the technical literature through a target search engine; analyzes an importance centrality index of the hotspot technology keyword compared to the technical literature through a preset importance evaluation model; calculates hotness data of the technical literature according to the importance centrality index and the metric data; generates a hotspot technology hotness data change curve based on the hotness data; performs hotspot technology prediction evaluation based on the hotspot technology hotness data change curve, and generates a hotspot technology evaluation report, which analyzes a hotspot technology keyword input by a user through a generative artificial intelligence model, and provides efficient hotspot technology analysis results.
Owner:OPTICS VALLEY LABORATORY +1

Tool function calling method, device and equipment and computer readable storage medium

The invention discloses a tool function calling method, device and equipment and a computer readable storage medium. The method comprises the steps that cue words and tool function query conditions are obtained; when the tool function query condition contains a target function identification code, querying target tool function information from a search engine according to the target function identification code; when the tool function query condition only contains target grouping information, querying target tool function information from a search engine according to the cue word and the target grouping information; generating calling configuration information according to the target tool function information; and performing large language model reasoning based on the cue word and the calling configuration information. According to the method and the device, the calling configuration information is dynamically generated based on the tool function query condition and the cue word, so that on-demand calling of the tool function is realized during large language model reasoning.
Owner:CHINA ELECTRONICS CLOUD DIGITAL INTELLIGENCE TECH CO LTD

Method and device for improving relevance of query results of Elasticsearch engine

The invention discloses a method and device for improving relevance of query results of an Elasticsearch engine, and relates to the technical field of search engine data process.The method comprises the steps that a search request sent by a client side is received; performing word segmentation processing on a query statement in the search request to obtain term lexical items and term lexical item attribute information; obtaining type information of each term lexical item based on the token stream; different weights are given to original search terms and synonyms of the original search terms in each term lexical item type, and the weights of the original search terms are larger than the weights of the synonyms of the original search terms; a BooleanQuery auxiliary class constructor is used for constructing the TermAnder Boost object, the position increment information and the offset information into a BooleanQuery object with weight information, and the BooleanQuery object is used for constructing the TermAnder Boost object and the position increment information into the BooleanQuery object with the weight information; and performing combined query on the search request. According to the invention, different service requirements and search precision requirements are met, and the complexity and performance loss of the system are reduced.
Owner:BEIJING RONG CLOUD NETWORK TECH CO LTD

Automated attribute scraping for security feature implementation prediction

Automated attribute scraping for security feature implementation with a single trained machine model across security features improves prediction quality and efficiency of predictions. A security feature implementation prediction system (system) generates search engine queries for each security feature based on high importance tokens for the security feature. The system ranks URLs returned from each search engine query for relevance, then preprocess and inputs content for top-ranked URLs into the trained machine learning models. The system identifies implemented security features output based on confidence values output by the trained machine learning model and identifies sentences that describe the implementations in corresponding content for top-ranked URLs.
Owner:PALO ALTO NETWORKS INC

AI digital analysis portable full-color night vision camera

The invention relates to the field of full-color night vision cameras, in particular to an AI digital analysis portable full-color night vision camera which comprises a camera body and an AI digital analysis unit, one end of the camera body is provided with a front cover, and the inner side of the front cover is provided with a distance sensing plate, a low-light-sensation chip and a display screen module; the AI digital analysis unit is provided with an AI digital analysis database and a search engine; and the display screen module of the camera main body is connected with the AI digital analysis unit, so that the AI digital analysis unit can analyze the image sensed by the low-light-sensation chip. When a search engine queries a specific reminding character string in the AI digital analysis database, sound and light reminding is immediately carried out. AI digital analysis database calibration character strings queried by a search engine of the digital analysis unit can be classified and stored with the images at the same time, and are used as search parameters when the images are queried. According to the method, related parts in a heap of images can be inquired by using numbers or characters in the images without inputting in advance, and the method is convenient.
Owner:SHENZHEN YOULIAN YOUPIN TECH CO LTD

Search engine query optimization method, device, and electronic device

The present application provides a search engine query optimization method, device, electronic device, and computer-readable storage medium; the method includes: obtaining a search engine's historical query record, the historical query record including multiple query statements, generating a syntax tree based on the terms included in the query statements; adjusting the execution order of the terms in the syntax tree based on the amount of information included in the inverted list corresponding to each term in the syntax tree; searching based on the syntax tree after the execution order is adjusted, and determining the execution order of each term in the syntax tree based on the search results, and the execution order minimizes the overall search cost; wherein the syntax tree is used for the search engine to search when receiving the query statement. Through the present application, search consumption can be reduced.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD

Systems and methods for real-time translation of aquatic sensor measurements to probable causes via combination of cause-and-effect queries and language model based semantic similarity

The invention provides a system for real-time and on-site analysis of water quality issues utilizing advanced algorithms, machine learning, and AI-based assessment, the system employing a state-of-the-art rover equipped with advanced sensors to detect issues and anomalies in an aquatic biome and supply collected data to computing units, also deployed locally on the rover, which then operate to assess the collected data by employing advanced algorithms to generate search engine queries, identify and extract pertinent terms from search results, assess likely causes of detected issues and anomalies, and provide real-time, on-site reports and analysis of findings.
Owner:CHOUDHURY PRAYRONA

Augmenting machine learning language models using search engine results

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting machine learning language models using search engine results. One of the methods includes obtaining question data representing a question; generating, from the question data, a search engine query for a search engine; obtaining a plurality of documents identified by the search engine in response to processing the search engine query; generating, from the plurality of documents, a plurality of conditioning inputs each representing at least a portion of one or more of the obtained documents; for each of a plurality of the generated conditioning inputs, processing a network input generated from (i) the question data and (ii) the conditioning input using a neural network to generate a network output representing a candidate answer to the question; and generating, from the network outputs representing respective candidate answers, answer data representing a final answer to the question.
Owner:GDM HOLDING LLC

Tag-based search method, device, server and storage medium

The present application relates to blockchain and artificial intelligence. The embodiment of the present application provides a tag-based search method, device, server and storage medium, the method comprising: receiving a user search request sent by a terminal, the user search request carrying a first set of tags for user search; parsing a second set of tags obtained according to the first set of tags by a first search engine to obtain a parsing result, the parsing result including a search condition that can be recognized by a second search engine; querying at least one user information matching the parsing result from a first database according to a tag set of each user among multiple users by the second search engine, the tag set of each user including at least one tag of the user, the first database including user information of each user among the multiple users; obtaining a user search result according to the at least one user information, and returning the user search result to the terminal. The present application can improve the accuracy of user search.
Owner:CHINA PING AN LIFE INSURANCE CO LTD

Generating narrative query responses utilizing generative language models from search-based autosuggest queries

This disclosure describes a query gateway system that provides an efficient and flexible framework for providing context-retained autosuggest queries from an autosuggest query system (e.g., a search engine query experience) to a generative language model system (e.g., an AI chat experience). For instance, the query gateway system establishes a framework to leverage the features and services of the autosuggest query system and automatically provides context-retained queries to the generative language model system using separate user interfaces that do not disrupt user navigation or require manual duplicative user input. Additionally, the query gateway system incorporates additional enhancements, including an AI chat eligibility model and a query reformulation model, to improve the computational efficiency and accuracy of the AI chat system.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Augmenting machine learning language models using search engine results

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting machine learning language models using search engine results. One of the methods includes obtaining question data representing a question; generating, from the question data, a search engine query for a search engine; obtaining a plurality of documents identified by the search engine in response to processing the search engine query; generating, from the plurality of documents, a plurality of conditioning inputs each representing at least a portion of one or more of the obtained documents; for each of a plurality of the generated conditioning inputs, processing a network input generated from (i) the question data and (ii) the conditioning input using a neural network to generate a network output representing a candidate answer to the question; and generating, from the network outputs representing respective candidate answers, answer data representing a final answer to the question.
Owner:GDM HOLDING LLC

A pre-trained code-enhanced answer recommendation method for programming question-and-answer communities

This invention relates to a pre-trained code-enhanced answer recommendation method for programming question-and-answer communities, comprising two stages: a training stage and a recommendation stage. The training stage can be further divided into a tag recommendation pre-training stage and a question-and-answer classification fine-tuning stage. In the tag recommendation pre-training stage, the title, body, and code information from the question are used as input, and the question labels are used as ground truth for learning. In the fine-tuning stage, the pre-trained model is reused to encode information from both the question and the answer, and finally, the feature vectors of the question and the answer are mapped to a classification space. In the recommendation stage, for a new question, a search engine is first used to query similar question titles, and the top Q titles are selected as candidate questions and candidate answers. The candidate answers and the new question are then used as input to the fine-tuned model to obtain the confidence probability of each question-and-answer pair. A weighted summation method is used to calculate the matching score of the question and answer pairs, and the top Q' after sorting are the final recommended answers.
Owner:CHONGQING UNIV

Generating narrative query responses utilizing generative language models from search-based autosuggest queries

This disclosure describes a query gateway system that provides an efficient and flexible framework for providing context-retained autosuggest queries from an autosuggest query system (e.g., a search engine query experience) to a generative language model system (e.g., an AI chat experience). For instance, the query gateway system establishes a framework to leverage the features and services of the autosuggest query system and automatically provides context-retained queries to the generative language model system using separate user interfaces that do not disrupt user navigation or require manual duplicative user input. Additionally, the query gateway system incorporates additional enhancements, including an AI chat eligibility model and a query reformulation model, to improve the computational efficiency and accuracy of the AI chat system.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Systems and methods for real-time translation of aquatic sensor measurements to probable causes via combination of cause-and-effect queries and language model based semantic similarity

PCT designated stage expiredWO2024253874A9Web data indexingWithdrawing sample devicesLinguistic modelAquatic biota
The invention provides a system for real-time and on-site analysis of water quality issues utilizing advanced algorithms, machine learning, and AI-based assessment, the system employing a state-of-the-art rover equipped with advanced sensors to detect issues and anomalies in an aquatic biome and supply collected data to computing units, also deployed locally on the rover, which then operate to assess the collected data by employing advanced algorithms to generate search engine queries, identify and extract pertinent terms from search results, assess likely causes of detected issues and anomalies, and provide real-time, on-site reports and analysis of findings.
Owner:CHOUDHURY PRAYRONA

A method for converting patent search expressions into search engine query statements

The application discloses a kind of methods for converting patent search expression into search engine query statement, comprising: obtaining the patent search expression to be processed;Utilize the pre-constructed tokenizer to parse the string corresponding to the patent search expression, obtain the multiple tokens parsed;Based on the syntax structure of patent search expression, the multiple tokens are processed into the list of standard syntax nodes;According to the list of standard syntax nodes, generate standard syntax tree;Utilize the pre-constructed, and the syntax converter matched with target search engine, convert standard syntax tree into the query statement of target search engine.Wherein, patent search expression, tokenizer is constructed based on the extensible syntax structure of pre-defined patent search expression.This application can convert patent search expression into the query statement of corresponding search engine, can be applicable to a variety of search engines, can realize patent data heterogeneous search, can adapt to different data format and data storage mode, and the adaptability and scalability are high.
Owner:SHAANXI RONGSHENG INTELLECTUAL PROPERTY PLATFORM CO LTD

Ticket price query method and device and electronic equipment

PendingCN119127954A
The invention discloses a ticket price query method and device and electronic equipment, and relates to the technical field of aviation and the field of aviation ticket price search. The method comprises the steps that a target component obtains a ticket price query request of a user terminal; when it is detected that the ticket price query request is a call request of a session mode, the target component calls a ticket price search engine to query to obtain N data sets, and after the ticket price search engine queries one data set each time, the ticket price determination result of the data set is transmitted back to the target component; by executing X times of target operations, the target component returns ticket price determination results of the N data sets to the user terminal in X batches, and the target operations of different execution sequences are used for processing different data sets. According to the method and the device, the technical problems that in the prior art, when many ticket price search results exist, the time for the user terminal to return the search results is too long, and the search efficiency is low are solved.
Owner:TRAVELSKY TECHNOLOGY LIMITED

Method, device and equipment for evaluating hotspot technology based on generative artificial intelligence

The invention relates to the technical field of hotspot technology assessment, in particular to a hotspot technology assessment method, device and equipment based on generative artificial intelligence, by responding to a hotspot technology keyword, technical literatures corresponding to the hotspot technology keyword and measurement data corresponding to the technical literatures are inquired through a target search engine; analyzing an importance centrality index of the hotspot technical keyword relative to the technical literature through a preset importance evaluation model; calculating popularity data of the technical literature according to the importance centrality index and the measurement data; generating a hotspot technology popularity data change curve based on the popularity data; and performing hotspot technology prediction evaluation based on the hotspot technology popularity data change curve, generating a hotspot technology evaluation report, analyzing a hotspot technology keyword input by a user through a generative artificial intelligence model, and providing an efficient hotspot technology analysis result.
Owner:OPTICS VALLEY LABORATORY +1

To-do work order optimization method and system

The embodiment of the invention provides a to-be-processed work order optimization method and system. According to the method, firstly, corresponding to-be-handled models are created for to-be-handled work order types, index fields covering necessary information are configured for all the models, and it is ensured that data storage is adaptive to efficient query; thirdly, designing an exclusive target interface for each work order type, and establishing a precise data interaction channel; secondly, writing the data into a database, and asynchronously writing the data into a search engine with a data writing function to lay a data foundation for efficient query; then, the query source logic of the to-be-optimized application page is changed into search engine query from database query, so that migration of a query mode is achieved; and finally, configuring a system main switch and each work order type independent switch, performing database query during default closing and performing search engine query during opening, and greatly reducing database query pressure by virtue of strong full-text search and real-time analysis capabilities of a search engine while flexible switching is performed, so that the query efficiency is remarkably improved.
Owner:INSPUR TIANYUAN COMM INFORMATION SYST CO LTD

Generating narrative query responses utilizing generative language models from search-based autosuggest queries

This disclosure describes a query gateway system that provides an efficient and flexible framework for providing context-retained autosuggest queries from an autosuggest query system (e.g., a search engine query experience) to a generative language model system (e.g., an AI chat experience). For instance, the query gateway system establishes a framework to leverage the features and services of the autosuggest query system and automatically provides context-retained queries to the generative language model system using separate user interfaces that do not disrupt user navigation or require manual duplicative user input. Additionally, the query gateway system incorporates additional enhancements, including an AI chat eligibility model and a query reformulation model, to improve the computational efficiency and accuracy of the AI chat system.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Business query method and device, equipment, medium and program product

The invention provides a business query method and device, equipment, a medium and a program product, relates to the technical field of computers, and can solve the problems of low data synchronization efficiency and low overall resource utilization rate of a system during business query. According to the specific technical scheme, the method comprises the steps of storing structured service data of a service system in a target database; periodically initiating query to a target database through a data synchronization service in the business system to obtain the changed structured business data to obtain change information; packaging the change information into preset format data through data synchronization service, and sending the preset format data to a target search engine; updating an unstructured business data index in the target search engine according to the preset format data; and through the target search engine, based on the updated unstructured business data index, querying to obtain a business data record set corresponding to a query request of the client, and returning the business data record set to the client. The method is used for performing fuzzy query on service data.
Owner:CHINA CONSTRUCTION BANK +1

A dynamic modeling method and system for enterprise-level massive power data search engine

The present invention relates to a method for dynamic modeling of a massive power data search engine at an enterprise level, comprising the following steps: step S1: collecting power data based on sensors or meters, integrating the collected power data into network devices, configuring sFlow agents on the network devices, and regularly generating sFlow data packets; step S2: encrypting and transmitting sFlow data packets to a data storage platform based on TLS / SSL protocols; step S3: the data storage platform uses HBase as a distributed database and uses Elasticsearch to build a full-text index; step S4: dynamically modeling power data using machine learning and data mining algorithms, and using streaming computing and real-time data processing technology to update and optimize the dynamic modeling results in real time; step S5: displaying dynamic modeling results and search engine query results through data visualization technology, so that users can perform data analysis and decision-making. The present invention realizes real-time collection, processing and analysis of power data, and ensures high performance and availability of the system.
Owner:STATE GRID INFO TELECOM GREAT POWER SCI & TECH