477 results about "Search words" patented technology

The present disclosure relates to the technical field of artificial intelligence, and provides a multimodal large language model training method, a correlation calculation method, and a label generation method. The multimodal large language model training method comprises: on the basis of a sample text feature vector, a sample image feature vector, and a sample first multimodal feature vector which are obtained by processing image information and text description information of a sample commodity by a pre-trained multimodal large language model, training the pre-trained multimodal large language model to obtain a multimodal large language model; and processing a sample search word, the image information and the text description information on the basis of the multimodal large language model to obtain a sample search word feature vector, a first multimodal feature vector and a sample second multimodal feature vector, and training the multimodal large language model to obtain a trained multimodal large language model. The trained multimodal large language model of the present disclosure can simultaneously learn image features related to the search word and the text description information, and thus the generated second multimodal feature vector is more accurate.

The invention discloses a medical large model analysis method and system based on multi-strategy deep slow thinking and a storage medium, and the method comprises the steps: obtaining a query input by a user, carrying out the deep analysis of the query through a context and semantic analysis technology, and generating a complete context-related search word; recalling related contents from a knowledge base according to the generated search word and judging whether error correction is needed or not: when the recalled contents are wrong or fuzzy, performing error correction by utilizing a lightweight language model, generating a new query after error correction, regenerating a new search word by the new query after error correction, and according to the newly generated search word, performing search on the new query after error correction; and performing network search and knowledge base recall, sorting the recalled knowledge according to the current query, sending the sorted knowledge and the query together to the natural language processing large model for processing, and returning a final answer to the user. And the quality and practicability of the natural language processing large model generation content are obviously improved.

The invention provides an information retrieval enhancement method and system based on a multi-path recall mode, and the method comprises the following steps: analyzing a user search term to obtain retrieval result data; performing multi-path recall on the retrieval result data to obtain recall information; sorting the recall information to obtain a sorting result; and reordering the ordering result to obtain a final retrieval result. According to the technical scheme, the search result data are obtained by analyzing the user search term; performing multi-path recall on the retrieval result data to obtain recall information; sorting the recall information to obtain a sorting result; reordering the ordering result to obtain a final retrieval result; according to the method, multiple information retrieval strategies are integrated in a flexible and expansible manner, so that the information retrieval precision and efficiency are improved, and the expandability of the information retrieval strategies is not lost.

The invention discloses a medical dialogue search term rewriting method and device, equipment and a storage medium. The method comprises the following steps: detecting whether current dialogue input is a question or has intention jump through a lightweight model for multi-round dialogue intention jump and question recognition; when it is detected that the current dialogue input is subjected to intention hopping or not questioning, the historical dialogue context is emptied, and the current input serves as independent query to be directly output; and when it is detected that the current dialogue input does not have intention hopping and the current dialogue input is a question, triggering the functions of substitution disambiguation and semantic completion, calling the fine-tuning and rewriting large model, and generating a standard medical question with complete semantics and standard terms, so that the context dependency relationship in the user dialogue can be accurately identified, and the user experience is improved. In addition, a large model can be called to complete deep semantic reconstruction when necessary, light model pre-judgment and large model accurate rewriting are combined, accuracy and efficiency are both considered, and the method is a key technical breakthrough for improving usability and specialty of a medical RAG system.

The invention provides a UGC retrieval method and system based on semantic information, electronic equipment and a storage medium, and relates to the field of search recommendation. The method comprises the steps of obtaining UGC information data and user search terms, and converting the UGC information data into UGC semantic feature data; performing multi-path recall retrieval according to the UGC semantic features and the user search terms to obtain a UGC candidate set related to the user search terms; carrying out reciprocal sorting fusion on a plurality of recall result candidate sets in the UGC candidate set to obtain a sorted recall result candidate set; the sorted recall result candidate set is rearranged through a BGE erank model, a rearrangement recall result candidate set and a rearrangement score of each UGC candidate item in the rearrangement recall result candidate set are obtained, and the rearrangement recall result candidate set and the rearrangement score of each UGC candidate item in the rearrangement recall result candidate set serve as a UGC retrieval result. Through the method, the correlation and the accuracy of retrieval results are improved.

To provide a system for efficiently providing information which a user requires.SOLUTION: A system comprises: reception means for receiving earth observation data sent from an earth observation satellite; analysis means including a generative AI for analyzing the received earth observation data; classification means for classifying the data analyzed by the analysis means to a prescribed category; integration means for integrating the classified data; generation means for generating real time information on the basis of the integrated data; and providing means for providing the generated information according to a search word.SELECTED DRAWING: Figure 1

Disclosed in the present invention is a knowledge graph-based unified fault search method for a specialized vehicle device. The method comprises: acquiring device maintenance related data, and taking a device as a core to establish association relationships between the device maintenance related data; acquiring a fault report, and parsing the fault report to obtain parsing result data; constructing a device fault graph on the basis of the device maintenance related data and the parsing result data; integrating the device fault graph into a knowledge graph platform; receiving a search term entered by a current user in a search box, acquiring search results corresponding to the search term, and displaying the search results on a search result page, wherein the search results comprise a result list, data classification statistics, search result sorting, a knowledge cloud picture, and associated recommendations; and providing in the search result page an operation entry for knowledge exploration, and viewing related knowledge exploration of the current knowledge by the user by triggering the operation entry for knowledge exploration. The method solves the problem in the prior art that the search results are not accurate enough.

The invention belongs to the technical field of natural language processing and knowledge engineering, and discloses a method, a system, equipment and a medium for automatically constructing a multi-field scientific knowledge base, and the method comprises the following steps: based on an input identifier list or a field search word, retrieving a full text of a literature, analyzing and converting the full text into a structured text; combining a pre-configured large language model with a field cue word, extracting key information in the structured text, and outputting structured data; the automatic script filters irrelevant, repeated or incomplete structured data according to a pre-configured filtering rule; performing standardization processing on the filtered structured data so as to realize the consistency and comparability of the data; and inserting the standardized structured data into an interactive knowledge base or database, establishing data association, and verifying association logic. The method supports cross-field rapid adaptation, solves the problems of low efficiency and high error rate of a traditional method, and can be widely applied to the fields of biomedicine, material science, synthetic biology and the like.

The invention relates to a software test case sharing and multiplexing method and system based on semantic understanding search, and belongs to the technical field of software testing. According to the method, defined entities, attributes of the entities and relationships among the entities are extracted from massive software test cases, a software test case knowledge graph is constructed, and the extracted knowledge is fused under the same framework specification to form a high-quality knowledge base. Meanwhile, word segmentation understanding based on semantic understanding is carried out on search words of the user, intention recognition, semantic ambiguity elimination and word meaning expansion are carried out on the search words after word segmentation through the constructed knowledge graph, search results are clustered and sorted according to service weights and provided for the user, and sharing and reuse from semantic search to software test cases are achieved. The testing efficiency and quality are improved, and repeated work and testing cost are reduced. Meanwhile, the method has high practicability and universality and can be applied to different software testing scenes and projects.

The invention discloses a position searching method and device based on implicit intention recognition, and relates to the technical field of information retrieval and intelligent recommendation. The method comprises the following steps: sampling from a historical log and constructing prompt words, and performing weighted voting labeling on keywords and resume pairs by utilizing a plurality of large language models to generate an intention recognition training sample; and the cue word is iteratively optimized through manual evaluation, so that the labeling accuracy is ensured. And training an intention recognition model by using the samples. In the online search stage, structural features of search terms and resumes of a user are extracted and input into the pre-training model to recognize the implicit job hunting intention of the pre-training model. Finally, personalized retrieval conditions are dynamically generated according to the intention recognition result, and related positions are recalled and sorted from the position database. According to the method, the accuracy and the individuation degree of position searching are effectively improved, and the user experience of job seekers is remarkably improved.

The invention discloses a search intention recognition method and device, equipment and a storage medium, and relates to the technical field of reinforcement learning, and the method comprises the following steps: generating training data based on an original corpus; performing supervision fine tuning processing on the lightweight language model based on the training data to obtain a fine tuning trained lightweight language model; performing strategy optimization on the lightweight language model subjected to fine tuning training through an improved GRPO reinforcement learning algorithm to obtain a lightweight language model subjected to reinforcement training; constructing a double-model hybrid architecture based on a short thinking chain model and a thinking chain-free model in the lightweight language model subjected to enhanced training; and outputting a final sequence of the related documents of the search terms of the user through the double-model hybrid architecture. According to the technical scheme of lightweight language model fine tuning, reinforcement learning optimization and double-model hybrid reasoning, the target search scene recognition accuracy is improved, the real-time response speed is high, and training time consumption and reasoning resource requirements are reduced.

An online system provides a search interface for a user to identify items. The search interface may present suggested search queries to the user, allowing the user to select a suggested search query rather than manually entering search terms to form a search query. To identify search queries most likely to be selected by the user, the online system gets a set of candidate search queries and generates a relevance score for each candidate search query by applying a trained query relevance model to each candidate search query. The scored candidate search queries are selected and ranked using the relevance scores, and the selected candidate search queries are displayed using the ranking in the search interface. The query relevance model is a transformer-based small language model receiving a user sequence of prior search queries and items with which the user interacted and the candidate search terms as input.

The invention discloses a unified construction method for an intention recognition system and a semantic vector recall system, relates to the field of computer processing, and aims at uniformly constructing the intention recognition and semantic vector recall system by aligning a user vector, a material implicit vector and an intention implicit vector in a natural semantic space. Besides, the material implicit vector is projected to the user vector in a vector projection mode, and the similarity between the material implicit vector and the user vector is calculated, so that long semantic information of visual content and short semantic information of user search terms are subjected to consistent alignment. Therefore, a plurality of functional modules on a whole search link are replaced, the research and development and operation cost is greatly reduced, and a search system is obviously improved in the aspects of user intention estimation and integrity and accuracy of preference material recall.

The invention provides an article recommendation method and device, and the method comprises the steps: determining a target word from a search word set; obtaining external platform domain data corresponding to the target word, matching the external platform domain data with the internal platform domain data, and determining the matching similarity between the external platform domain data and the internal platform domain data; and taking the internal platform domain data and the external platform domain data of which the matching similarity exceeds a first threshold value as target internal platform domain data and target external platform domain data, and constructing product word data based on the target internal platform domain data and the target external platform domain data so as to perform article recommendation based on the product word data. According to the embodiment, the hotspot trend can be responded in time, and the cold start period of the article related to the hotspot trend is shortened, so that the timeliness and accuracy of article recommendation are improved, and the user experience is improved.

The invention discloses an advertisement design display system and method based on big data. The system comprises a data acquisition layer for acquiring multi-source data sources; the semantic understanding layer is used for generating semantic vectors of search words and advertising words based on a BERT-Chine pre-training language model, calculating a quantitative semantic matching degree through cosine similarity, performing deep semantic understanding and synonym equivalence matching, performing intention classification on features through an XGBoost gradient promotion decision tree, and judging that a user is in an instant purchase, decision period or interest exploration state; the scene sensing layer is used for dynamically recognizing a scene where a user is located by using an LSTM-CRF time sequence model; the feature recombination layer is used for extracting explicit features and mining implicit correlation features; the deep matching layer is used for generating a comprehensive matching score of a 0-1 interval by fusing explicit features and implicit association features in combination with multi-task learning, and performing screening according to the comprehensive matching score; the value measurement layer is used for quantifying contributions of different advertisement contacts to final conversion; and the execution layer is used for carrying out advertisement rendering and putting.

A method, an apparatus, and a computer-readable storage medium for searching of electronic documents. A search query is encoded to form a search vector. The search query includes at least one search term and seeks information within a plurality of electronic documents. A knowledge graph structure is generated using at least one search term. The search term is associated with at least another term in a plurality of terms in the knowledge graph structure. The search query is modified using the other term to generate a modified search vector. A response to the search query is generated based on one or more responsive document vectors retrieved from the plurality of electronic documents and that are semantically similar to the modified search vector.

The objective of the present disclosure is to search for content in a content streaming system, and an operating method of a server may comprise the steps of: acquiring a search word; using a language model trained on the basis of synopsis information included in metadata of content items, so as to determine a first vector corresponding to the search word; determining similarity between the search word and a first content item on the basis of the first vector corresponding to the search word and a second vector of the first content item; and providing a content search list including information about at least one content item including the first content item selected on the basis of the similarity.

A computer-based method is provided for filtering search results, including first identifying a plurality of documents for review and then identifying an initial plurality of search term results potentially relevant to a search query, each search term result of the initial plurality containing an occurrence of a primary search term of a plurality of primary search terms. The method then proceeds to group identical search term results to define a plurality of groups of search term results. Representative search term result of each group are presented for evaluation. Upon receiving an indication from a user that the representative search term result is to be removed, the method then removes all search term results of the corresponding group to define a modified plurality of search term results. Each document from which any search result of the modified plurality of search term results is drawn is defined as a potentially relevant document.

A computer-implemented method executed using a computing device comprises digitally generating and storing a machine learning statistical topic model in computer memory, the topic model being programmed to model call transcript data representing words spoken on a call as a function of one or more topics of a set of topics, the set of topics being modeled to comprise a set of pre-seeded topics and a set of non-pre-seeded topics, and the one or more topics being modeled as a function of a probability distribution of topics; programmatically pre-seeding the topic model with a set of keyword groups, each keyword group associating a respective set of keywords with a topic of the set of pre-seeded topics; programmatically training the topic model using unlabeled training data; conjoining a classifier to the topic model to create a classifier model, the classifier defining a joint probability distribution over topic vectors and one or more observed labels; programmatically training the classifier model using labeled training data; receiving target call transcript data comprising an electronic digital representation of a verbal transcription of a target call; programmatically determining, using the classifier model, at least one of one or more topics of the target call or one or more classifications of the target call; digitally storing the target call transcript data with additional data indicating the determined one or more topics of the target call and / or the determined one or more classifications of the target call; accessing, in computer storage, a first digitally stored electronic document comprising a first text; receiving computer input specifying a search query comprising one or more search terms; processing the search query using the classifier model to output a query topic vector representing a thematic content of the search query; processing the first text using the classifier model to output and store in the computer memory a first plurality of topic vectors each representing a topic in the text; using the query topic vector and the first plurality of topic vectors, calculating a plurality of similarity values, each of the similarity values representing a similarity of the query topic vector to a particular topic vector among the first plurality of topic vectors; outputting a visual display that specifies one or more topic vectors among the first plurality of topic vectors having one or more corresponding similarity values that are greater than a specified threshold similarity value.

An electronic data analysis method including at least one server, the electronic data analysis method comprising the steps of: a) Receiving, from an electronic device associated with a user to an electronic data analysis system, a search query including one or more search query terms; b) Maintaining an electronic search term database in association with the electronic data analysis system, the search term database comprising a plurality of search terms; c) Identifying, using the electronic data analysis system, one or more relevant search terms from the plurality of search terms in the electronic search term database based on the one of more search query terms; d) Sending, using the electronic data analysis system, a search request related to the one or more relevant search terms to a plurality of data sources external to the electronic data system; e) Receiving, using the electronic data system, data associated with the one or more relevant search terms from the plurality of data sources; f) Assigning, using the electronic data system, the data retrieved from the plurality of data sources into a plurality of data visualisation categories; and g) Displaying, using the electronic data system, the plurality of data visualisation categories on the electronic device.

A method for voice-based interaction between a user (e.g., a shopper) and online stores includes capturing an initial voice input from a user and converting the voice input to text. The text is analyzed and initial search terms are created such as product name, product description, product category, product brand name, product manufacturer and retailer. One or more searches are conducted using the initial search terms to identify one or more retailers meeting the search terms. One or more identified online retailers are accessed and searches are executed at the one or more identified retailers, generating search results. The identified online retailers have a user interface allowing purchases of the identified product or item. The search results are returned to the user.

Devices, systems, and methods for tokenizing search attributes and terms of a search query for an index-based search. A method may include receiving, by a search service of a provider network, a first search query to search a first searchable document set, the first search query including a first search term in a first language; applying a first tokenization rule to identify the first search term in the first search query; determining that the first search term is in the first language; applying a second tokenization rule to tokenize the first search term based on the first search term being in the first language; causing a launch of a search instance by a managed compute service of the provider network, the search instance to execute a search function for a keyword-based text search using the tokenized first search term.

The invention provides a question answering method and device based on a large model, computer equipment and a storage medium, and belongs to the technical field of computers. The method comprises the steps that at least one target plug-in is determined from a plurality of candidate plug-ins based on input questions and search words of the candidate plug-ins associated with a large model, and the search word of each candidate plug-in is used for indicating question features used for requesting corresponding services; the matching degree between the search word of the at least one target plug-in and the question meets a matching condition; based on the at least one target plug-in, calling a service interface of a service corresponding to the at least one target plug-in, and based on the service interface corresponding to the at least one target plug-in, obtaining service data from a server side corresponding to the at least one target plug-in; and processing the service data corresponding to the at least one target plug-in through the large model to obtain an answer to the question, and outputting the answer. According to the method, the problem processing efficiency is improved on the basis of ensuring that the large model can accurately process the problem.

The invention discloses a multi-vector library parallel retrieval method and device based on retrieval enhancement, and relates to the technical field of retrieve.The method comprises the steps that query input is subjected to parallel retrieval of multiple vector libraries in a local knowledge base, and a first set number of retrieval results are obtained; the local knowledge base comprises a second set number of vector libraries, and each vector library comprises documents of a preset field; and taking the first set number of retrieval results as enhanced retrieval words, combining the query input with the enhanced retrieval words, and taking the combined content as the input of a large language model to obtain a final retrieval result. The accuracy of information retrieval can be improved.

To improve usability of a user.SOLUTION: The document information includes a document display name of a document file corresponding to a search condition, a list of detected text sentences including a search word and characters before and after the search word in a text file, most frequent image data corresponding to a page in which the search word is detected most frequently, and a jump button that can be linked to a document address.SELECTED DRAWING: Figure 10

A search engine of a data exchange may receive a query comprising a set of search terms, retrieve a plurality of data listings based on the search terms of the query, compare a first embedding generated by a large language model (LLM) from the search query to second embeddings generated by the LLM for each of the plurality of data listings to determine a respective relevance for each of the plurality of data listings to the search query, and rank the plurality of data listings based on the respective relevance for each of the plurality of data listings to the search query.

A system generates domain-expert agents for a particular domain. The system generates a hierarchy of topics for the domain by forming structured query inputs and requesting a machine learning-based language model to produce topics and associated sets of search terms. A knowledge store is built for the domain by identifying, for each topic, facts represented symbolically and / or in natural language. For at least one topic, programs comprising instructions for executing domain-specific procedures are generated and stored as symbolic and / or natural language programs. The knowledge store is evaluated to determine an expertise level for a domain-expert agent. If the knowledge store meets a threshold of knowledge, a deployment package is created comprising the knowledge store, and the domain-expert agent is deployed. The deployed agent utilizes the knowledge store together with a machine learning language model to address and solve problems specific to the domain.

The invention provides a multi-task modeling method in a game content search association field. The method comprises the following steps: constructing a multi-task modeling model; the multi-task modeling model comprises an input layer, an embedding model, a vector splicing model, an expert network layer, a gating network layer, a gating weighted fusion layer, a multi-task tower layer and an output layer; obtaining a training sample set; each training sample in the training sample set comprises a user current search term query, a user historical search term sequence, a user basic feature set and a user real behavior tag set; and training the multi-task modeling model by adopting the training sample set. According to the method, multi-task modeling can be carried out in the field of game content search association, so that the click preference of the user for the candidate words can be predicted more accurately, and the conversion efficiency of subsequent content consumption is improved.

The invention provides an article generation method and device based on a generative model, equipment and a medium, and relates to the technical field of artificial intelligence, in particular to the technical field of natural language understanding and artificial intelligence content generation. According to the implementation scheme, an article generation request is input into a first generative model, article structure description information generated by the first generative model is obtained, and the article structure description information comprises information of a plurality of text content modules; determining a plurality of search terms based on the information of the plurality of text content modules; searching on the basis of each search term in the plurality of search terms by utilizing a search engine; determining a plurality of text materials based on a search result corresponding to each search term in the plurality of search terms; inputting the article generation request and a plurality of text materials into a second generative model; and determining a target article based on an output result of the second generative model.