WO2025232004A1 - Procédé et dispositif d'optimisation de résultat de recherche de niveau d'entreprise basé sur un grand modèle, et support - Google Patents

Procédé et dispositif d'optimisation de résultat de recherche de niveau d'entreprise basé sur un grand modèle, et support

Info

Publication number
WO2025232004A1
WO2025232004A1 PCT/CN2024/108653 CN2024108653W WO2025232004A1 WO 2025232004 A1 WO2025232004 A1 WO 2025232004A1 CN 2024108653 W CN2024108653 W CN 2024108653W WO 2025232004 A1 WO2025232004 A1 WO 2025232004A1
Authority
WO
WIPO (PCT)
Prior art keywords
search
search results
user
question
search result
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2024/108653
Other languages
English (en)
Chinese (zh)
Inventor
郑伟波
周祥国
霍亮
仪思奇
丁一凡
吕柏成
杜宏伟
黄文超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Inspur General Software Co Ltd
Original Assignee
Inspur General Software Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Inspur General Software Co Ltd filed Critical Inspur General Software Co Ltd
Publication of WO2025232004A1 publication Critical patent/WO2025232004A1/fr
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9538—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/60—Protecting data
    • G06F21/604—Tools and structures for managing or administering access control systems

Definitions

  • This application relates to the field of electronic digital data processing technology, specifically to an enterprise-level search result optimization method, device, and medium based on a large model.
  • search engine technology is widely used in Internet services.
  • enterprise-level search engines are playing an increasingly important role in information retrieval, data analysis, and knowledge management within organizations.
  • Search engines contain a vast amount of information. To ensure users obtain the information they need, search results need continuous optimization to improve the search experience and efficiency.
  • common optimization methods rely primarily on user clicks and selections, optimizing search result rankings based on user actions. However, this approach depends on massive amounts of user behavior data.
  • internal enterprise search differs by orders of magnitude in terms of user traffic, making it difficult to provide accurate enterprise-level search result rankings.
  • this application proposes an enterprise-level search result optimization method based on a large model, comprising:
  • the enterprise search engine returns a list of search results consisting of multiple search results corresponding to the user's requested search question;
  • the search question is input into a preset language model, and the language model performs semantic analysis on the search question to obtain the answer to the search question.
  • the search results list is adjusted to obtain the adjusted merged search results list
  • corresponding search matching weights are assigned to the fused search results list; wherein, the search matching weights are positively correlated with the order of the search results in the fused search results list;
  • the fused search results list is pushed to the user.
  • user operation data is collected from the user in response to the search result. Based on the user operation data, the user operation weight corresponding to the search result is calculated.
  • the fused search results list is readjusted to obtain the target search results.
  • the search results list is adjusted based on the answer to the question to obtain an adjusted fused search results list, specifically including:
  • the question answer and multiple search results in the search results list are vectorized to obtain the corresponding question answer vector and search result vector;
  • the order of multiple search results in the search results list is adjusted according to the descending order of the cosine similarity to obtain the adjusted fused search results list.
  • the method before readjusting the fused search results list based on the user operation weight and the search matching weight, the method further includes:
  • the association strength between the user's job position and the associated business is determined according to the set of search questions and the set of business questions.
  • the fused search results list is readjusted based on the user operation weight and the search matching weight to obtain the target search results, specifically including:
  • For each search result determine the product between the user action weight corresponding to the search result and the user relevance coefficient, and sum the product with the search matching weight to obtain the search result.
  • the target weight corresponding to the result
  • the order of multiple search results in the fused search results list is readjusted according to the target weight from high to low to obtain the target search results.
  • determining the specified associated service to which the search question belongs and the user relevance coefficient corresponding to the specified associated service specifically includes:
  • determining the subordinate search problems that are dependent on the search problem among all search problems specifically includes:
  • the two historical search problems are used as nodes, and the search order is used as the direction of the edge to construct a search dependency graph corresponding to the historical search problems.
  • the user operation data includes the total number of clicks made by the user on the fused search results list during a single search, and the browsing time of the search results.
  • the user operation weight corresponding to the search results is calculated, specifically including:
  • the number of second search results corresponding to multiple search results in the merged search results list is determined, and the user operation weight corresponding to the search results is calculated using the following formula, based on the number of first search results, the number of second search results, the total number of clicks, and the browsing time:
  • w op represents the user action weight
  • M represents the number of first searches
  • m represents the number of second searches
  • R represents the total number of clicks
  • t represents the browsing time.
  • semantic analysis of the search question is performed using the language big model to obtain the answer to the search question, specifically including:
  • the search problem is vectorized using the large language model to obtain the corresponding search problem vector.
  • the search question vector is compared with the vector data in the enterprise knowledge vector library to determine the similarity between the search question vector and the vector data;
  • This application embodiment provides an enterprise-level search result optimization device based on a large model, the device comprising:
  • At least one processor At least one processor
  • a memory communicatively connected to the at least one processor
  • the memory stores instructions that can be executed by the at least one processor, which enable the at least one processor to perform an enterprise-level search result optimization method based on a large model as described above.
  • This application provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:
  • An enterprise-level search result optimization method based on a large model as described in any of the preceding items.
  • the enterprise-level search result optimization method based on a large model proposed in this application can bring the following benefits:
  • This approach generates question-and-answer results based on a large language model.
  • it can better understand user intent and filter out search results with higher similarity and better match the user's actual needs. It optimizes the order of search results, improves search matching accuracy, and avoids over-reliance on the influence of user action data on search results.
  • Collecting user action data in response to search results and calculating user action weights allows for a better understanding of user preferences and behavioral patterns. This enables further optimization of search result ranking based on user action weights, making the search engine results more aligned with user expectations.
  • Figure 1 is a flowchart illustrating an enterprise-level search result optimization method based on a large model provided in an embodiment of this application;
  • Figure 2 is a schematic diagram of the structure of an enterprise-level search result optimization device based on a large model provided in an embodiment of this application.
  • an enterprise-level search result optimization method based on a large model includes:
  • S101 Through the enterprise search engine, return a list of search results consisting of multiple search results corresponding to the search question requested by the user.
  • An enterprise search engine is a search engine system customized to meet the internal information retrieval needs of an enterprise. Its purpose is to help employees quickly and accurately find the information they need, improve work efficiency and collaboration capabilities. These search engines are typically used for internal knowledge management, document retrieval, employee training, and other aspects of an organization.
  • the server can then use the search engine to return a list of search results corresponding to the user's requested search query.
  • Search queries typically exist in the form of multiple search keywords, but in some cases, they can also be a complete search statement.
  • the search results in the final search results list are arranged in descending order of relevance to the search query. For example, if a user's search query is "Project A budget sheet," the enterprise search engine will retrieve documents or text information containing the two keywords mentioned above and arrange them in descending order of relevance to form the search results list.
  • S102 Input the search question into the preset language model, and process the search question through the language model. Semantic analysis is performed to obtain the answer to the search question.
  • a large language model refers to a large-scale neural network model trained using deep learning technology, used to process natural language processing tasks. It can learn the syntax, semantics, and contextual information of a language, helping computers better understand and generate text. Available language models include GPT-3, BERT, and XLNet. Therefore, based on a deep understanding of semantics, the large language model can automatically generate answers to questions, thus providing data references for subsequent optimization of the search results list.
  • a large language model first vectorizes the search question to obtain a corresponding search question vector. Then, this vector is compared with vector data in an enterprise knowledge vector library to determine the similarity between them. Based on this similarity, specified vector data with a similarity greater than a preset similarity can be selected from the enterprise knowledge vector library. Semantic analysis is then performed on the specified vector data and the search question vector to deeply understand the user's search intent. Finally, the large language model can generate the corresponding answer to the search question based on this intent.
  • the language model can generate rich and diverse answers to questions, potentially including information or perspectives not covered by search engines. This can supplement search results and provide users with more comprehensive information. Therefore, after generating answers based on the language model, it's necessary to compare them with the search results provided by the search engine. Based on the comparison results, the search results list should be adjusted to obtain a refined, merged search results list. Comparing the answers generated by the language model with the search results list can identify potential omissions, errors, or duplicates in the search results list, allowing for corresponding adjustments and optimizations, thereby improving the quality and accuracy of the search results.
  • both the question answer and the search results exist in text form.
  • multiple search results in the question answer and search result lists need to be vectorized to obtain corresponding question answer vectors and search result vectors.
  • the cosine similarity between each search result vector and the question answer vector needs to be calculated.
  • the cosine similarity reflects the similarity between search results provided by two different retrieval methods; the higher the similarity, the stronger the similarity.
  • the higher the accuracy of the search results the greater the likelihood that they will meet the user's needs. Therefore, the order of multiple search results in the search results list needs to be adjusted according to the descending order of cosine similarity to obtain the adjusted fused search results list.
  • S104 Assign corresponding search matching weights to the fused search results list according to the preset weight calculation model; wherein, the search matching weights are positively correlated with the order of the search results in the fused search results list.
  • the merged search results list combines the analysis results of the search engine and the language big data model, resulting in the final order of search results. Search results appearing earlier in the list are more likely to meet the user's actual search needs. Therefore, a pre-defined weighting calculation model is used to assign corresponding search matching weights to the merged search results list. These search matching weights reflect the degree of match between the search results order and the user's actual needs, and are positively correlated with the order of the search results in the merged search results list. In other words, the search matching weights for search results decrease sequentially according to their order.
  • the weight calculation model only considers the earlier, more similar search results when assigning search matching weights. Therefore, it is necessary to filter out a preset number of search results with a similarity greater than a preset threshold or those that are among the earlier results in the merged search results list. Assuming that the final number of highly similar search results is five, the weight calculation model can assign search matching weights to each search result according to the idea of average distribution, assigning weight values of 1, 0.8, 0.6, 0.4, and 0.2 respectively. It should be noted that the preset threshold and preset number can be set according to actual search needs, and this application does not limit them.
  • S105 Push the integrated search results list to the user. For each search result in the integrated search results list, collect user operation data in response to the search results, and calculate the user operation weight corresponding to the search results based on the user operation data.
  • the list After assigning search matching weights to the merged search results list, the list needs to be pushed to users. Upon receiving the search results, users will perform actions such as clicking and browsing.
  • the server needs to collect user action data for each search result in the merged search results list and calculate the corresponding user action weight based on this data. This user action data reflects user satisfaction and relevance with the search results. By calculating the user action weights, the ranking of search results can be optimized and adjusted to provide a search experience that better meets user needs.
  • user action data considers the total number of clicks and browsing time on search results.
  • the standard search capabilities of the enterprise's search engine need to be evaluated. This process can be achieved using default search criteria. Generally, search criteria use words with high frequency, such as " ⁇ ", " ⁇ ", and " ⁇ ”. Record the standard search results returned by the enterprise search engine and the number of first search results corresponding to those standard results. Simultaneously, determine the number of second search results corresponding to multiple search results in the merged search results list. Based on the number of first search results, the number of second search results, the total number of clicks, and the browsing time, the user action weight corresponding to the search results can be calculated. This process can be achieved using the following formula:
  • w op represents the user action weight
  • M represents the number of first searches
  • m represents the number of second searches
  • R represents the total number of clicks
  • t represents the browsing time.
  • the relevance of the user's job title to the search query must also be considered.
  • search engines can more quickly locate the job title or business that best matches the search query. This not only improves search efficiency but also increases user satisfaction with the search results. Therefore, the greater the relevance between the job title and the search query, the higher the match between the final search results and the user's search needs.
  • Each job title corresponds to different related businesses.
  • the related businesses for a sales position may be market research, sales data analysis, and customer relationship management; the related businesses for R&D personnel may be programming skills training, software development processes, and technical documentation writing.
  • Different search queries belong to different related businesses.
  • searching for sales data for a certain product belongs to the related business of sales data analysis
  • searching for a system user guide belongs to the related business of skills training. Due to the large number and wide scope of search queries, when evaluating the relevance between a job title and a search query, it can be transformed into an evaluation of the relevance between the job title and related businesses. Therefore, the relevance of a search query to a job title can be determined based on the relevance between the related businesses to which the search query belongs and the job title.
  • the relevance between job positions and related business activities can be represented by a user relevance coefficient.
  • a search scenario includes the background, purpose, and search conditions of the user's query request.
  • a search scenario could be a user searching for product documents or a user searching for employee training materials. Because different job positions involve different product types and training skills, the search questions generated in different search scenarios will also differ. Similarly, different related business activities within a search scenario will generate different search questions.
  • the related business activity might be related to market research.
  • the search query can be to search for the market share of products currently in circulation and user feedback information.
  • the related business is sales data analysis
  • the corresponding search query can be to search for sales documents of a certain product within a specified period.
  • the association rule can be represented as: and M represents the job position, and N represents related business functions. Let represent the empty set, and ... and confidence level These two attributes.
  • the strength of the correlation between a user's job position and related business functions can be calculated, as shown in the following formula:
  • j represent the fitness function used to calculate the strength of the association between a user's job position and related business functions, where j represents the number of job positions.
  • min_sup represents the minimum support
  • min_conf represents the minimum confidence.
  • the mapping relationship between the preset correlation strength and user correlation coefficient After obtaining the correlation strength between job positions and related businesses through the above correlation rules, it is necessary to obtain the mapping relationship between the preset correlation strength and user correlation coefficient. In this way, based on the mapping relationship, the user correlation coefficient that matches the correlation strength can be determined when the correlation strength is clear.
  • a search query may relate to multiple specific related services. For example, when searching for sales data of a product, both market research and sales data analysis might involve sales data. Therefore, it's necessary to more precisely pinpoint the specific related services based on the dependencies between the user's search queries.
  • search question determines the primary related business to which the search question belongs. If there are multiple primary related businesses, it's necessary to identify all search questions requested by the user within a preset time period, as well as any dependent search questions within those search questions.
  • users will retrieve a lot of related information when searching for information. For example, when searching for product sales data, they first search for product sales data. If the sales data is poor, they need to understand the reasons for the poor sales. This can be achieved by obtaining user feedback data, etc. Therefore, searching for user feedback data depends on the search question of searching for product sales data. This is understandable. Yes, while search questions and related search questions with dependencies may belong to different related businesses, those with overlapping related businesses are likely to have a stronger correlation with the search question.
  • the related business can be directly designated as the specified related business corresponding to the search question. Therefore, after identifying the related search question, the second related business to which the related search question belongs is determined. Then, from the first and second related businesses, the related business with the highest frequency of occurrence is selected as the specified related business to which the search question belongs.
  • the determination of auxiliary search questions is based on a search dependency graph.
  • the search dependency graph consists of search questions and directed edges connecting different search questions. The direction of the edges represents the dependency relationship between different search relationships.
  • a dependency relationship means that the formulation of one search question depends on the formulation of another search question, and the search order of the two is relatively fixed. Therefore, the search question at the endpoint of a directed edge depends on the search question at the starting point.
  • the search dependency graph needs to be constructed based on pre-collected search log data. After collecting the search log data, it is necessary to determine whether there is a search order dependency between any two historical search questions based on the search order among the historical search questions in the search log data.
  • any two historical search questions are used as nodes, and the search order is used as the direction of the edge to construct the search dependency graph corresponding to the historical search questions.
  • auxiliary search questions that have a dependency relationship with the user's proposed search question can be determined from all search questions.
  • the server After determining the user relevance coefficient corresponding to the search question, the server combines the user relevance coefficient, user action weight, and search matching weight to recalculate the target weight corresponding to each search result. Then, the merged search results list is readjusted according to the order of the target weights to obtain the target search results.
  • the product of the user action weight and the user relevance coefficient is determined, and this product is summed with the search matching weight to obtain the target weight for the search result.
  • This target weight is a comprehensive weight that takes into account factors such as the question answer provided by the language model, user action interest, and question relevance, thus more comprehensively reflecting the matching degree between the search results and the user's actual needs. Therefore, the order of multiple search results in the merged search results list is readjusted according to the target weight from high to low to obtain the target search results.
  • the server controls the front-end interface to adjust the order of the search results and displays the adjusted target search results to the user in real time, enabling the user to obtain search results that better meet their search needs in a timely manner, improving the user's search efficiency and accuracy.
  • Figure 2 is a schematic diagram of the structure of an enterprise-level search result optimization device based on a large model provided in an embodiment of this application. As shown in Figure 2, it includes:
  • At least one processor and,
  • At least one processor-communication-connected memory wherein,
  • the memory stores instructions that can be executed by at least one processor, and the instructions, when executed by at least one processor, enable at least one processor to:
  • the enterprise search engine returns a list of search results consisting of multiple search results corresponding to the user's requested search question;
  • the search question is input into a pre-defined language model, which performs semantic analysis on the search question to obtain the answer to the search question.
  • the search results list is adjusted to obtain the adjusted merged search results list
  • corresponding search matching weights are assigned to the fused search results list; wherein, the search matching weights are positively correlated with the order of the search results in the fused search results list.
  • the integrated search results list is pushed to the user.
  • user action data is collected based on the user's feedback on the search results.
  • the user action weight corresponding to the search result is calculated.
  • the merged search results list is readjusted to obtain the target search results.
  • This application provides a non-volatile computer storage medium storing computer-executable instructions, which are configured as follows:
  • the enterprise search engine returns a list of search results consisting of multiple search results corresponding to the user's requested search question;
  • the search question is input into a pre-defined language model, which performs semantic analysis on the search question to obtain the answer to the search question.
  • the search results list is adjusted to obtain the adjusted merged search results list
  • corresponding search matching weights are assigned to the fused search results list; wherein, the search matching weights are positively correlated with the order of the search results in the fused search results list.
  • the integrated search results list is pushed to the user.
  • user action data is collected in response to the search results.
  • the search results are calculated.
  • the merged search results list is readjusted to obtain the target search results.
  • the devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.
  • this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and/or one or more block diagrams.
  • These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and/or one or more block diagrams.
  • a computing device includes one or more processors (CPUs), input/output... Interface, network interface, and memory.
  • Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash random access memory
  • Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
  • PRAM phase-change memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • RAM random access memory
  • ROM read-only memory
  • EEPROM electrical

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Automation & Control Theory (AREA)
  • Evolutionary Computation (AREA)
  • Bioethics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Computer Security & Cryptography (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

La présente demande se rapport au domaine technique du traitement de données numériques électriques. Sont divulgués un procédé et un dispositif d'optimisation de résultat de recherche de niveau d'entreprise basé sur un grand modèle, et un support. Le procédé consiste : au moyen d'un moteur de recherche d'entreprise, à renvoyer une liste de résultats de recherche constituée d'une pluralité de résultats de recherche correspondant à une requête de recherche demandée par un utilisateur ; à réaliser une analyse sémantique sur la requête de recherche au moyen d'un grand modèle de langage, de façon à obtenir une réponse correspondant à la requête de recherche ; sur la base de la réponse à la requête, à ajuster la liste de résultats de recherche pour obtenir une liste de résultats de recherche de fusion ajustée ; sur la base d'un modèle de calcul de pondération prédéfini, à attribuer des pondérations de correspondance de recherche correspondantes à la liste de résultats de recherche de fusion ; pour chaque résultat de recherche dans la liste de résultats de recherche de fusion, à acquérir des données d'opération d'utilisateur renvoyées par l'utilisateur pour le résultat de recherche, et, sur la base des données d'opération d'utilisateur, à calculer une pondération d'opération d'utilisateur correspondant au résultat de recherche ; et, sur la base des pondérations d'opération d'utilisateur et des pondérations de correspondance de recherche, à réajuster la liste de résultats de recherche de fusion pour obtenir un résultat de recherche cible.
PCT/CN2024/108653 2024-05-09 2024-07-30 Procédé et dispositif d'optimisation de résultat de recherche de niveau d'entreprise basé sur un grand modèle, et support Pending WO2025232004A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410564668.2 2024-05-09
CN202410564668.2A CN118152645B (zh) 2024-05-09 2024-05-09 一种基于大模型的企业级搜索结果优化方法、设备及介质

Publications (1)

Publication Number Publication Date
WO2025232004A1 true WO2025232004A1 (fr) 2025-11-13

Family

ID=91293261

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/108653 Pending WO2025232004A1 (fr) 2024-05-09 2024-07-30 Procédé et dispositif d'optimisation de résultat de recherche de niveau d'entreprise basé sur un grand modèle, et support

Country Status (2)

Country Link
CN (1) CN118152645B (fr)
WO (1) WO2025232004A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118152645B (zh) * 2024-05-09 2024-07-30 浪潮通用软件有限公司 一种基于大模型的企业级搜索结果优化方法、设备及介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111949898A (zh) * 2020-08-28 2020-11-17 平安国际智慧城市科技股份有限公司 搜索结果排序方法、装置、设备及计算机可读存储介质
WO2021051587A1 (fr) * 2019-09-17 2021-03-25 平安科技（深圳）有限公司 Procédé et appareil de tri de résultats de recherche basés sur une reconnaissance sémantique, dispositif électronique et support d'informations
CN112632394A (zh) * 2020-12-31 2021-04-09 启业云大数据(南京)有限公司 基于企业用户搜索行为特征的企业级搜索方法及搜索引擎
CN113254810A (zh) * 2021-06-17 2021-08-13 浙江口碑网络技术有限公司 搜索结果输出方法、装置、计算机设备及可读存储介质
CN118152645A (zh) * 2024-05-09 2024-06-07 浪潮通用软件有限公司 一种基于大模型的企业级搜索结果优化方法、设备及介质

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160196490A1 (en) * 2015-01-02 2016-07-07 International Business Machines Corporation Method for Recommending Content to Ingest as Corpora Based on Interaction History in Natural Language Question and Answering Systems
CN112417133A (zh) * 2020-11-25 2021-02-26 上海创米科技有限公司 排序模型的训练方法和装置
CN116610853A (zh) * 2022-02-08 2023-08-18 中兴通讯股份有限公司 搜索推荐方法、搜索推荐系统、计算机设备及存储介质
US11768843B1 (en) * 2022-05-24 2023-09-26 Microsoft Technology Licensing, Llc Results ranking with simultaneous searchee and searcher optimization
CN116501960B (zh) * 2023-04-18 2024-03-15 百度在线网络技术（北京）有限公司 内容检索方法、装置、设备及介质
CN116775853A (zh) * 2023-06-28 2023-09-19 唯思电子商务(深圳)有限公司 一种基于大语言模型的企业内部搜索引擎方法
CN116738065B (zh) * 2023-08-15 2024-04-19 浙江同信企业征信服务有限公司 一种企业搜索方法、装置、设备及存储介质
CN117453725A (zh) * 2023-10-31 2024-01-26 数据空间研究院 基于大模型的关键词扩充与多信息融合数据要素搜索方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021051587A1 (fr) * 2019-09-17 2021-03-25 平安科技（深圳）有限公司 Procédé et appareil de tri de résultats de recherche basés sur une reconnaissance sémantique, dispositif électronique et support d'informations
CN111949898A (zh) * 2020-08-28 2020-11-17 平安国际智慧城市科技股份有限公司 搜索结果排序方法、装置、设备及计算机可读存储介质
CN112632394A (zh) * 2020-12-31 2021-04-09 启业云大数据(南京)有限公司 基于企业用户搜索行为特征的企业级搜索方法及搜索引擎
CN113254810A (zh) * 2021-06-17 2021-08-13 浙江口碑网络技术有限公司 搜索结果输出方法、装置、计算机设备及可读存储介质
CN118152645A (zh) * 2024-05-09 2024-06-07 浪潮通用软件有限公司 一种基于大模型的企业级搜索结果优化方法、设备及介质

Also Published As

Publication number Publication date
CN118152645A (zh) 2024-06-07
CN118152645B (zh) 2024-07-30

Similar Documents

Publication Publication Date Title
US20250328593A1 (en) Techniques for presenting content to a user based on the user's preferences
US11093860B1 (en) Predictive model importation
US10491662B2 (en) Dynamically organizing cloud computing resources to facilitate discovery
US8694540B1 (en) Predictive analytical model selection
Arias et al. A framework for recommending resource allocation based on process mining
US20090228353A1 (en) Query classification based on query click logs
US10606874B2 (en) Adjusting search results based on user skill and category information
US20120158687A1 (en) Display entity relationship
RU2744029C1 (ru) Система и способ формирования обучающего набора для алгоритма машинного обучения
WO2018053966A1 (fr) Estimation du taux de clics
US20190258723A1 (en) Domain-based search engine
US20250335799A1 (en) Multi-pass processing for artificial intelligence chatbots
Crescenzi et al. Crowdsourcing for data management
Panziera et al. Quality-driven extraction, fusion and matchmaking of semantic web api descriptions
Truică et al. TextBenDS: a generic textual data benchmark for distributed systems
WO2025232004A1 (fr) Procédé et dispositif d'optimisation de résultat de recherche de niveau d'entreprise basé sur un grand modèle, et support
Asprino et al. A large visual question answering dataset for cultural heritage
IL248313A (en) Research on data-driven preference and semantic processing
US20100161361A1 (en) Performing enterprise planning and economics analysis for reservoir-related services
US20250278578A1 (en) Intermediary routing and moderation platform for generative artificial intelligence system interfacing
CN117033744B (zh) 数据查询方法、装置、存储介质以及电子设备
Feddoul et al. Semantic relatedness as an inter-facet metric for facet selection over knowledge graphs
US20260072944A1 (en) System and method for automated data warehouse creation and extension from user natural language requests
CN118860978B (zh) 一种针对企业查询功能的关键词搜索方法、设备及介质
US12353492B1 (en) Machine learning system and method for targeted growth projection of market inquiry results

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24940357

Country of ref document: EP

Kind code of ref document: A1