78 results about "Personalized search" patented technology

The invention belongs to the technical field of knowledge retrieval, and discloses a multi-modal large model-based dynamic vector knowledge base construction and retrieval method, which comprises the following steps of: obtaining a multi-source heterogeneous modal data set, and carrying out preprocessing and modal standardization processing on the multi-source heterogeneous modal data set to obtain a standardized multi-modal data set; performing feature extraction and semantic vector representation generation by using the pre-trained multi-modal large model, and constructing a multi-modal knowledge vector set; semantic association analysis and hierarchical clustering are carried out on the multi-modal knowledge vector set, and a structured vector knowledge base is constructed; performing semantic similarity calculation and relation modeling on the vector knowledge base to form a vector relation network; intention analysis and vector representation are performed based on mixed modal query information input by a user, and efficient similarity retrieval is realized in combination with a vector relation network; dynamic optimization is carried out through user feedback, personalized retrieval result adjustment is achieved, and the problem of limitation of a traditional retrieval system during multi-modal data processing is effectively solved.

The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating personal responses through retrieval-augmented generation. In particular, the disclosed systems can generate a query embedding from a query generated by an entity and determine data context specific to the entity by comparing the query embedding with a plurality of vectorized segments of content items associated with the entity. The disclosed systems can provide the data context to a large language model and generate a personalized response informed by the data context. Subsequently, the disclosed systems can provide the personalized response for display on a client device associated with the entity.

The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating personal responses through retrieval-augmented generation. In particular, the disclosed systems can generate a query embedding from a query generated by an entity and determine data context specific to the entity by comparing the query embedding with a plurality of vectorized segments of content items associated with the entity. The disclosed systems can provide the data context to a large language model and generate a personalized response informed by the data context. Subsequently, the disclosed systems can provide the personalized response for display on a client device associated with the entity.

The invention discloses an internet mass data accurate search method and system based on an AI technology, and relates to the technical field of internet, the method comprises the following steps: receiving a query text input by a user, using a natural language processing technology to identify the input query text, and generating a structured query vector; based on the structured query vector, constructing a knowledge graph to obtain a rich semantic context graph; a knowledge transfer learning technology is introduced, historical search data and behavior characteristics of a user are analyzed, and a personalized search model is constructed; monitoring the real-time interaction behavior of the user, judging the cognitive load of the user, and generating an adaptive search interface; initiating a plurality of query requests by using the personalized search model, and outputting a personalized search result set through filtering and sorting; according to the method, the knowledge graph is constructed and the rich semantic context graph is generated, so that the system can identify entities and multiple relationships thereof, more relevant search results are provided, and a user is promoted to discover potential requirements.

The invention relates to the field of distributed information retrieval, and particularly discloses a memory architecture vector approximate retrieval method based on a graph neural network, which comprises the following steps of: constructing and dynamically maintaining a historical query-hit vector association graph for modeling a deep semantic relationship between a historical query and a successful retrieval result; inputting the features of the current query vector, the information of the current query vector subjected to neighborhood sampling and feature aggregation in the graph and the service scene label into a lightweight graph neural network, and predicting the approximate retrieval tolerance level of the query; on the basis of the prediction result, an optimal retrieval strategy is generated in a self-adaptive mode; and in combination with asynchronous result return and a progressive refinement mechanism based on residual error reordering, a user is responded at the first time, and continuous optimization and pushing of a better result are realized. According to the method, a query-level personalized retrieval strategy is realized, the retrieval precision, the response delay and the system resource consumption are effectively balanced, and the method is suitable for a large-scale high-dimensional vector retrieval scene.

The invention relates to the technical field of information, in particular to a personalized search information recommendation method based on user behavior analysis, which mainly comprises the following steps: acquiring interactive behavior data of a user in real time; the method comprises the following steps: automatically extracting keyword tags of various contents through a natural language processing technology, and constructing a content keyword tag system; according to the content keyword tag system, extracting keyword tags associated with user behaviors from the interactive behavior data; in combination with the accumulated value of each type of behavior and the preset weight value, calculating the matching degree between the keyword tag and the user, and generating a matching degree set; performing variance operation on the matching degree set corresponding to the keyword tag to obtain sensitivity corresponding to the user content; and generating recommendation information of the search content of the user according to the sensitivity. According to the method, high-precision and real-time response personalized search content recommendation can be realized by analyzing user behaviors.

An information search method, apparatus, and computer-readable storage medium for providing intelligent search recommendations based on content marking behavior. The method displays a content detail interface and receives marking operations selecting content segments within target content. Marking identifiers are displayed for the selected segments. Based on segment detail information from current and previous marking operations, recommended search information is generated and displayed. Users can select target recommended search information through search operations, and corresponding search results are displayed. This approach enables personalized search suggestions derived from user marking patterns and content interaction history, improving search relevance and user experience.

The invention provides a handheld bank personalized search recommendation method and system, electronic equipment and a storage medium, and is suitable for a handheld bank APP to obtain a pre-constructed collaborative knowledge graph; obtaining a historical user query, and extracting a historical query suggestion set related to the historical user query from the collaborative knowledge graph; forming a plurality of training triads according to each user in the user set, the historical user query and a historical query suggestion set related to the historical user query, and training a to-be-trained personalized search recommendation model according to a scoring function learned by a training set constructed by each training triad to obtain the personalized search recommendation model; and when a query currently input by a target user in the search session of the handheld bank APP is detected, calculating the recommendation degree between the query and each entity in the handheld bank APP by using the personalized search recommendation model, screening out to-be-recommended entities from the entities according to the recommendation degree of each entity, and outputting each to-be-recommended entity.

In one aspect, a method for determining personalized search results with respect to mandatory constraints and qualitative preferences on search criteria representable via a DAG includes collecting input from users or software systems; transforming the inputs into the mandatory constraints and preferences on search criteria, wherein the search criteria is partially ordered and representable through the DAG; determining weights for the search criteria using a function, and associating the weights with the nodes of the DAG to determine a partial ordering of such weights equivalent to an order of the DAG nodes, where any node at level “k” has a weight “w” such that sum of all or any finite subset of the weights of the nodes at levels below “k” is always less than “w”, the level being defined by a topological order of the DAG; and determining search results that satisfy the mandatory constraints on the search criteria.

The present invention belongs to the field of knowledge retrieval technology. The present invention discloses a dynamic vector knowledge base construction and retrieval method based on a multimodal large model, comprising: obtaining a multi-source heterogeneous modal data set, and performing preprocessing and modality normalization processing on the data set to obtain a standardized multimodal data set; using a pre-trained multimodal large model to perform feature extraction and generate semantic vector representations to construct a multimodal knowledge vector set; performing semantic association analysis and hierarchical clustering on the multimodal knowledge vector set to construct a structured vector knowledge base; performing semantic similarity calculation and relationship modeling on the vector knowledge base to form a vector relationship network; performing intent analysis and vector representation based on mixed modal query information input by a user, and combining the vector relationship network to achieve efficient similarity retrieval; performing dynamic optimization through user feedback to achieve personalized retrieval result adjustment, effectively solving the limitations of traditional retrieval systems when processing multimodal data.

The invention relates to the technical field of data asset management, and discloses a data asset intelligent retrieval and visualization display platform, which comprises a data asset intelligent retrieval and visualization system, and the data asset intelligent retrieval and visualization system comprises a central processing unit. The input end of the central processing unit is electrically connected with the output end of a data analysis and mining module; according to the intelligent retrieval and visual display platform for the data assets, a user can quickly position required data resources in manners of keyword search, label screening and the like, the data retrieval efficiency is greatly improved, meanwhile, an intelligent retrieval algorithm can provide personalized search results according to the search history and preference of the user, and the user experience is improved. According to the method and the system, the retrieval accuracy is further improved, the platform performs classified management on the data assets, and a corresponding label is marked on each data set, so that a user is helped to better understand the meaning and the purpose of the data, and a more accurate matching result can be provided during retrieval.

This invention relates to a personalized search and recommendation method for smart TVs, specifically in the field of film and television recommendation. It utilizes a deep neural network model to generate embedding feature vectors for each film and television program in a media resource library. User profiles are obtained based on MAC addresses or voiceprint IDs, and embedding feature vectors for user-preferred films and television programs are generated using the same deep neural network model. A film and television knowledge graph is constructed, with the relationships between knowledge graph nodes serving as the reasoning for recommendations to the user. The method obtains the first- and second-degree neighbor film and television IDs for any given film and television program. When a user inputs a search term, the first- and second-degree neighbor film and television IDs are obtained using the corresponding film and television ID. The distance between the embedding feature vector of each film and television ID in the first- and second-degree neighbor programs and the embedding feature vector of the user-preferred films and television programs is calculated. These distances are then sorted from smallest to largest, and the top N films and television programs are selected for recommendation to the user. This invention solves the problem of weak correlation between search recommendation results and specific user preferences in existing technologies. This invention is applicable to personalized film and television recommendation.

The invention discloses a personalized search method and system for an electric power knowledge base, and relates to the technical field of electric power informatization and intelligent search, and the method comprises the steps: generating a user interest vector representing the current search intention of a user through a weight adaptive algorithm, and constructing a user interest model for the electric power field; receiving a query request input by a user, and retrieving from the power knowledge base based on the query request to obtain a corresponding initial search result set; constructing a queried power field polysemy model based on formal concept analysis (FCA); calculating the similarity between the interest vector and each semantic category based on the user interest vector; reordering the documents in the initial search result set according to the similarity; and selecting a feature word from the semantic category with the highest similarity as an expansion word. According to the method, through user interest modeling and semantic category matching, accurate sorting of the power knowledge base results is achieved, the retrieval individuation degree is improved, and the search accuracy and the user experience are improved.

The application realizes a personalized search and explanation generation method based on unified prompt perception through a method in the field of artificial intelligence. The user, the submitted query and the user's behavior sequence are taken as input, the unified personalized product search and explanation generation prompt perception framework is input, the search task and the explanation task are output, and the unified personalized product search and explanation generation prompt perception framework is composed of three parts: a base pre-training language model, a personalized retrieval component and an explanation generation component. The application proposes a unified training framework for personalized product search and explanation generation based on prompt perception, and designs specific prompts for each task in a unified manner, and the model finally outputs a natural language form of explanation while outputting the target product.

In one embodiment, a computer implemented method for generating personalized search results is disclosed. The method may include processing, via a processor, a search query of a user, modifying, via the processor, the search query based on educational competency data of the user, generating, via the processor, a search result based on the modified search query by performing a search operation in a knowledge space based on the modified search query to retrieve one or more content items of the knowledge space corresponding to the modified search query, generating, via the processor, a user interface configured to display the search result; and transmitting, via the processor, the user interface to a user device associated with the user.

The invention discloses an electricity price and electricity charge policy knowledge base search system considering user types, and the system comprises a user type classification module which is used for collecting user information and dividing users into different types of users according to the user information; the electricity price and electricity charge keyword generation and optimization module is used for determining basic keywords according to user types, performing semantic extension and adding associated vocabularies; the search execution module is used for constructing an index structure in the electricity price and electricity charge policy knowledge base, selecting a proper search algorithm according to the user type, and searching in the knowledge base based on the optimized keyword; and the search result processing module is used for sorting and screening the search results according to the user types so as to output accurate and personalized search results. The invention further discloses a corresponding method. By implementing the invention, the search efficiency and the search precision can be improved.

The present invention discloses an accurate search method and system for massive Internet data based on AI technology, which relates to the field of Internet technology. It includes receiving a query text input by a user, and using natural language processing technology to identify the input query text to generate a structured query vector; based on the structured query vector, constructing a knowledge graph to obtain a rich semantic context graph; introducing knowledge transfer learning technology to analyze the user's historical search data and behavioral characteristics to construct a personalized search model; monitoring the user's real-time interaction behavior, judging the user's cognitive load, and generating an adaptive search interface; using the personalized search model to initiate multiple query requests, and after filtering and sorting, outputting a personalized search result set. By constructing a knowledge graph and generating a rich semantic context graph, the system of the present invention can identify entities and their multiple relationships, thereby providing more relevant search results and promoting users to discover potential needs.

The invention discloses an intelligent multi-modal document fusion and personalized retrieval system and method, and relates to the technical field of document fusion and personalized retrieval, the intelligent multi-modal document fusion and personalized retrieval system comprises a document fusion module, a personalized retrieval module and a personalized recommendation module, and the personalized recommendation module analyzes basic keywords, style keywords and emotion keywords of each document to obtain a personalized recommendation result; therefore, fusion of the documents is realized, uniformity of contents, styles and emotions of the fused documents is guaranteed, and description portraits are performed on the user based on historical reading records of the user, so that document recommendation is performed on the user according to the description portraits and search keywords of the user during search of the user, and user experience is improved. According to the method, content relevance, expression suitability and emotional resonance of the documents and user retrieval are guaranteed, meanwhile, the reading preference of the user is analyzed, typesetting of all recommended documents is set according to the reading preference, and personalized recommendation for the user is achieved.

The invention provides an orchestrable RAG retrieval system and method, and the system comprises a retrieval module which is used for obtaining a user question and retrieving retrieval information related to the user question from a pre-constructed database; the generation module is used for generating answers of the user questions based on the retrieval information; and the arrangement control module is used for arranging at least one of the parameters, the execution sequence and the data processing flow of the retrieval module and the generation module according to the retrieval requirement of the user to generate a retrieval strategy. According to the method and the device, a user can arrange at least one of the parameters, the execution sequence and the data processing flow of the retrieval module and the generation module through the arrangement control module, so that the retrieval strategy meeting the service scene of the user is generated, and then the retrieval strategy meeting the service requirement of the user is used for retrieval. And the system can meet personalized retrieval requirements in different business scenes.

The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating personal responses through retrieval-augmented generation. In particular, the disclosed systems can generate a query embedding from a query generated by an entity and determine data context specific to the entity by comparing the query embedding with a plurality of vectorized segments of content items associated with the entity. The disclosed systems can provide the data context to a large language model and generate a personalized response informed by the data context. Subsequently, the disclosed systems can provide the personalized response for display on a client device associated with the entity.

The invention relates to the technical field of machine learning, in particular to a learning content pushing method, system and device and a readable storage medium, and the method comprises the steps: obtaining a multi-modal data source, and constructing a hierarchical index knowledge graph through cross-modal semantic feature extraction; collecting user behavior data in real time, and generating a knowledge state feature sequence; dynamically aligning the query vector with the knowledge graph through a graph structure alignment calculation module, calculating and aggregating according to semantic similarity, and generating a personalized retrieval weight; dynamically adjusting a graph query path according to the weight, and retrieving and pushing a matched knowledge set; and finally, according to the knowledge structured reconstruction degree and the data feedback of mastering the attenuation value, a query path optimization algorithm is adopted, and the graph index is updated online. The problem that an existing information retrieval system is insufficient in unstructured data processing capacity and cannot dynamically adapt to query intentions is solved, and the accuracy of data retrieval is improved.

The invention relates to a site information search method and device, a vehicle, a storage medium and a program product, and relates to the technical field of search, and the method comprises the steps: responding to a search request of a user for a target site, and outputting an information search result corresponding to the target site to the user, the information search result is obtained based on the current vehicle state data and the search request data. According to the method, the information search result more conforming to the current search scene can be searched according to the vehicle state data and the search request data, so that the information search result more meets the search intention of the user, personalized search is realized, and the search experience of the user is improved.

A computing system obtains text that relates to an experience of a user and determines a search intent based upon the text and a context of the user, where the context is determined based upon activity history of the user in a plurality of applications. The computing system identifies potential keywords in the text and identifies a search domain in a plurality of search domains based upon the potential keywords. The computing system computes a confidence score for each of the potential keywords based upon the search domain, the context, and prior search queries of the user. The computing system identifies keywords from amongst the potential keywords based upon the confidence scores and executes a search over an index based upon the keywords, where the index indexes user content of the user and content of an enterprise. The computing system presents search results for the search to the user.

Systems and methods for generating retrieval queries for a user. Such a method includes (i) receiving a search query from a user associated with an account profile, the account profile including a user history; (ii) generating, based on the search query, a context attribute summary indicative of at least one of (a) one or more content items of interest for the user or (b) predictions for future searches by the user; (iii) generating, based on the user history, a summarized user browsing history indicative of one or more past searches performed by the user; (iv) generating, using the context attribute summary and the summarized user browsing history as inputs to a trained language model, a plurality of retrieval queries; and (v) transmitting the plurality of retrieval queries to a search model to generate one or more recommendations associated with the search query for the user.

Disclosed are system, method and / or computer program product embodiments that retrieve items for a user based on a query using a two-tower deep machine learning model. An example embodiment provides input to a context tower, wherein the input includes the query and one or more of a query embedding corresponding to the query or a graph user embedding corresponding to the user. The context tower generates a context embedding in a vector space based on the input. The model determines a measure of similarity between the context embedding and each of a plurality of item embeddings in the vector space that are generated by an item tower and represent a plurality of candidate items. A relevancy score is calculated for each candidate item based on the measure of similarity between the context embedding and the corresponding item embedding. The relevancy scores are used for item retrieval and / or ranking.

The invention provides an AI-based search method, an AI-based search device, a computer readable storage medium and electronic equipment, and is applied to the technical field of artificial intelligence. The method comprises the steps that according to vector representation of a search term and vector representation of a structured abstract of an ith article, the ith search term association degree between the search term and the ith article is determined, and i is a positive integer; calculating a correlation degree between portrait information of a target user corresponding to the search word and the ith article to obtain an ith personalized correlation degree; according to the ith search word association degree and the ith personalized association degree, determining a score about the ith article; and sorting the articles according to the scores corresponding to the articles to obtain a search result. According to the method and the device, personalized search experience can be provided for each search user while the search accuracy is improved.

The invention relates to the technical field of intelligent medical treatment, in particular to an ankle joint exoskeleton auxiliary strategy generation method and device based on personalized search. The method comprises three core technologies of accurate gait phase detection based on IMU, personalized search space prediction based on ATLSTM, and real-time gait track generation based on PVT curve. The problems that in existing ankle joint exoskeleton personalized auxiliary strategy generation, a model-based method is high in complexity, a learning-based method needs a large amount of data and lacks real-time feedback, and human loop optimization causes slow convergence or local optimal pain points due to individual differences are effectively solved. According to the method, a complex human body dynamic model does not need to be constructed, data dependence and calculation cost are reduced, the loop optimization convergence speed of people can be remarkably increased by locking a personalized search space, a smooth dorsiflexion assisting track fitting an individual gait is generated, and man-machine collaboration, practicability and scene adaptability of exoskeleton are greatly improved.

Disclosed is a search system and associated methods for proactively searching disparate data sources in order to track in real-time the continuously changing attributes that are searchable and to generate personalized search results for different users based on machine-generated queries of relevant searchable attributes to each user without user-defined queries or user-initiated searches. The search system continuously searches the data sources for changes to a first set of searchable attributes with relevance to a first user and to a second set of searchable attributes to a second user. The search system generates and performs a first customized query of the first set of attributes identified with the changes and a second customized query of the second set of attributes identified with the changes, and provides the personalized search results from each query to the respective user in response to detecting that respective user accessing the search system.

The invention discloses a multi-unmanned aerial vehicle cooperative task allocation method with a self-evolution search capability, belongs to the technical field of emergency rescue, and aims to solve the problems that the multi-unmanned aerial vehicle cooperative task allocation method is easy to fall into local optimum and is weak in constraint processing capability. Comprising the steps that task modeling and parameter initialization are carried out, and an emergency rescue task is converted into a computable mathematical model; decoding the particles and executing deadlock detection and repair, and converting continuous solution vectors in particle swarm optimization into executable task allocation schemes meeting all rescue scene constraints; calculating a fitness value and a self-adaptive inertia weight of each particle to realize personalized search for different particles; convergence stagnation is monitored, intelligent variable neighborhood search and disturbance are triggered, and double-adaptive capacity of depth and neighborhood selection is achieved; updating the particles by using a self-adaptive inertia weight; and repeating the steps until the termination condition is met. According to the method, the solving quality and stability of a multi-unmanned aerial vehicle cooperative task allocation scheme under complex constraints can be remarkably improved.

This disclosure relates to a speech recognition method, apparatus, device, vehicle, and medium. The method includes: performing speech recognition on voice navigation information to obtain at least one candidate recognition result; determining an acoustic score for each candidate recognition result and a language score for each candidate recognition result; identifying target hot words contained in each candidate recognition result according to a preset hot word library and obtaining a target hot word score for the predetermined target hot words; determining a reference score for each candidate recognition result based on the acoustic score, language score, and target hot word score, and determining the target recognition result based on the reference score. In the embodiments of this disclosure, based on the speech recognition results combining language and acoustics, client-side hot words are introduced to determine the final recognition result. Since client-side hot words reflect personalized search habits, the influence of similar sounds can be removed, further improving the accuracy of the recognition results.