Information retrieval method and device and storage medium

Abstract

The invention relates to an information retrieval method and device and a storage medium, relates to the technical field of information retrieval, and aims to at least solve the problem of low retrieval efficiency in related technologies. The method comprises the following steps: based on a synonym library, performing synonym conversion and combination processing on keywords of information input by a user to obtain a target search word; the synonym library comprises a preset abbreviation word, a preset full name word and an association relationship between the preset abbreviation word and the preset full name word; and according to the target retrieval word, performing retrieval in a preset data index database to obtain target index information used for being displayed for the user.

Description

Technical Field

[0001] The present disclosure relates to the field of information retrieval technology, and in particular to an information retrieval method, device and storage medium. Background Art

[0002] As an independent Java Archive (JAR) package, the information intelligent retrieval tool can be easily integrated into any system with similar requirements to achieve simple, convenient and fast information retrieval functions. In the related retrieval method, the index information displayed to the user is usually determined by matching the string of user input information. The index information obtained by this retrieval method has low accuracy, low retrieval efficiency, and reduced user experience. Summary of the invention

[0003] The present invention provides an information retrieval method, device and storage medium to at least solve the problem. The technical solution of the present invention is as follows:

[0004] According to a first aspect of an embodiment of the present invention, there is provided an information retrieval method, which performs synonym conversion and merging processing on keywords input by a user based on a synonym library to obtain a target search term; the synonym library includes preset abbreviations, preset full names and associations between preset abbreviations and preset full names; according to the target search term, a search is performed in a preset data index library to obtain target index information for display to the user.

[0005] In one implementation, based on a synonym library, keywords in user input information are converted and merged into synonyms to obtain target search terms, including: segmenting the user input information to obtain keywords; screening out target keywords that are the same as the keywords from preset abbreviations and preset full names in the synonym library; and determining associated words and keywords associated with the target keywords in the synonym library as target search terms based on association relationships.

[0006] In another implementation, the method further includes: when a target keyword identical to the keyword is not screened out from preset abbreviations and preset full names in the synonym library, determining the keyword as the target search term.

[0007] In another implementation, before searching in a preset data index library according to the target search term to obtain the target index information for display to the user, the method also includes: in response to the user's operating instructions on the search page of the terminal device, sending an instruction to the terminal device to display a first information configuration control; the first information configuration control is used to input retrieval requirement information; in response to a confirmation instruction for the retrieval requirement information input on the first information configuration control, determining a target retrieval mode according to the input retrieval requirement information; the retrieval requirement information includes retrieval speed information and / or retrieval accuracy information and / or retrieval mode information.

[0008] In another implementation, according to the target search term, a search is performed in a preset data index library to obtain target index information for display to the user, including: using a target search mode, querying and matching the target index term with the preset index information in the preset data index library to obtain target index information matching the target index term; the target search mode includes one or more of the following: precise query retrieval mode, information abbreviation query retrieval mode and fuzzy query retrieval mode; the information matching degree of the precise query retrieval mode is higher than the information matching degree of the information abbreviation query retrieval mode, and the matching degree of the information abbreviation query retrieval mode is higher than the information matching degree of the fuzzy query retrieval mode; the information matching degree is the matching degree of the preset index term associated with the target index term in the index information and the target index term.

[0009] In another implementation, according to the target search term, a search is performed in a preset data index library to obtain target index information for display to the user, including: querying and matching the target index term with the preset index information in the preset data index library according to the precise query retrieval mode, the information abbreviation query retrieval mode and the fuzzy query retrieval mode to obtain first retrieval information, second retrieval information and third retrieval information respectively; obtaining the target index information based on the first retrieval information, the second retrieval information and the third retrieval information.

[0010] In another implementation, the priorities of the first search result, the second search result, and the third search result are sequentially decreased; target index information is obtained based on the first search information, the second search information, and the third search information, including: according to the priorities of the first search information, the second search information, and the third search information, the first search information, the second search information, and the third search information are aggregated to obtain the target index information.

[0011] In another implementation, in response to the user inputting an operation completion instruction on the second information configuration control of the terminal device, the preset abbreviations, preset full names, and the association between the preset abbreviations and the preset full names configured on the second information configuration control are updated to the preset; the second information configuration control is used to configure configuration information of the preset abbreviations, preset full names, and the association between the preset abbreviations and the preset full names.

[0012] According to a second aspect of an embodiment of the present invention, there is provided an information retrieval device, comprising: a conversion processing unit, configured to perform synonym conversion and merging processing on keywords of user input information based on a synonym library to obtain a target search term; the synonym library comprises preset abbreviations, preset full names and an association relationship between the preset abbreviations and the preset full names; a retrieval unit, configured to search in a preset data index library according to the target search term to obtain target index information for display to the user.

[0013] According to a third aspect of an embodiment of the present invention, a server is provided. The server is configured to execute the information retrieval method of the first aspect and any possible implementation manner thereof.

[0014] According to a fourth aspect of an embodiment of the present invention, there is provided a terminal device configured to perform the following operations: in response to an operation instruction on a user search page, obtain user input information from the search page, and send the user input information to a server, so that the server performs the following operations: based on a synonym library, perform synonym conversion and merging processing on the keywords of the user input information to obtain a target search term; the synonym library includes preset abbreviations, preset full names and an association relationship between the preset abbreviations and the preset full names; according to the target search term, search in a preset data index library to obtain target index information for display to the user.

[0015] In some implementations, it is also configured to perform: in response to an operation instruction on the user's retrieval page, display a first information configuration control on the retrieval page, and send the retrieval requirement information entered by the user on the first information configuration control to the server, so that the server responds to the confirmation instruction of the retrieval requirement information entered on the first information configuration control, and determines the target retrieval mode according to the input retrieval requirement information; the retrieval requirement information includes retrieval speed information and / or retrieval accuracy information and / or retrieval mode information.

[0016] In some implementations, it is also configured to execute: displaying a second information configuration control, and sending the synonym information configured and input by the user on the second information configuration control to a server, so that the server updates the preset abbreviations, preset full names, and the association between the preset abbreviations and the preset full names configured on the second information configuration control to the preset in response to the user inputting an operation completion instruction on the second information configuration control of the terminal device; the second information configuration control is used to configure configuration information of the preset abbreviations, the preset full names, and the association between the preset abbreviations and the preset full names; the synonym information includes the preset abbreviations, the preset full names, and the association between the preset abbreviations and the preset full names.

[0017] According to a fifth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which instructions are stored. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute an information retrieval method such as the first aspect and any possible implementation thereof.

[0018] According to a sixth aspect of an embodiment of the present disclosure, a computer program product is provided. The computer program product includes computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the information retrieval method of the first aspect and any possible implementation thereof.

[0019] The technical solution provided by the embodiment of the present invention brings at least the following beneficial effects: first, based on the preset relationship between the preset abbreviations and the preset full names in the synonym library, the keywords input by the user are converted into synonyms, so that the target search terms can include the full names or abbreviations of the keywords, so that the search terms are more comprehensive and the scope of the search terms is expanded. In this way, by including synonyms in the target search terms, the retrieval system can find documents that use different vocabulary to express the same concept, thereby improving the comprehensiveness of the retrieval results, and further avoiding missing synonymous index information due to ignoring synonyms such as full names or abbreviations during the retrieval process, thereby improving the retrieval scope and retrieval accuracy.

[0020] In addition, users do not need to manually enter multiple synonyms in order to obtain comprehensive results. The system will automatically process them, simplifying user operations, improving retrieval efficiency, and enhancing user experience.

[0021] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0023] Figure 1 is a schematic diagram of an information retrieval system according to an exemplary embodiment;

[0024] Figure 2 is a flow chart of an information retrieval method according to an exemplary embodiment;

[0025] Figure 3 is a block diagram of an information retrieval device according to an exemplary embodiment;

[0026] Figure 4 It is a schematic diagram showing an information retrieval device according to an exemplary embodiment. DETAILED DESCRIPTION

[0027] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0029] Before introducing the information retrieval method provided in the embodiment of the present application in detail, a brief introduction to the application scenarios and implementation architecture involved in the embodiment of the present application is first given.

[0030] First, a brief introduction to the application scenarios involved in this application is given.

[0031] As an independent Java Archive (JAR) package, the information intelligent retrieval tool can be easily integrated into any system with similar requirements to achieve simple, convenient and fast information retrieval functions. In the related retrieval method, the index information displayed to the user is usually determined by matching the string of user input information. The index information obtained by this retrieval method has low accuracy, low retrieval efficiency, and reduced user experience.

[0032] Research has found that database fuzzy search is a widely used search method that can provide real-time information query. Fuzzy search allows users to query based on partial information and keywords, which improves the flexibility of the query. Fuzzy query of related databases requires querying all data records. When the amount of data in the database is particularly large, the efficiency of fuzzy query will be significantly reduced, which may lead to excessive query time. Fuzzy search is based on fuzzy matching of strings and may return a large amount of irrelevant data. The system needs to spend extra time to screen and filter the results, which increases the difficulty of data processing and leads to a high cost burden.

[0033] Specifically, some database query methods often require users to enter precise information names or specific keywords in the names to retrieve information. However, when faced with massive and complex information data, users often find it difficult to quickly and accurately lock in the information they need. Especially in the field of financial products, due to the wide variety of products in various industries and the large amount of information, users often do not know the complete name of the product. For example, for "Agricultural Bank of China's 365-day peace of mind financial product", users may only know its abbreviation "Agricultural Bank of China Peace of Mind" or "Peace of Mind product". In this case, if the query system only supports exact matching, the user's search experience will be greatly reduced, because they may only know some keywords and cannot obtain complete product information.

[0034] In response to the above problems, the present application proposes an information retrieval method, which first performs synonym conversion processing on the keywords input by the user based on the preset relationship between the preset abbreviations and the preset full names in the synonym library, so that the target search terms can include the full names or abbreviations of the keywords, so that the search terms are more comprehensive and the scope of the search terms is expanded. In this way, by including synonyms in the target search terms, the retrieval system can find documents that use different vocabulary to express the same concept, thereby improving the comprehensiveness of the retrieval results, and further avoiding the omission of synonym-related index information due to ignoring synonyms such as full names or abbreviations during the retrieval process, thereby improving the retrieval scope and retrieval accuracy.

[0035] Secondly, the implementation architecture involved in this application is briefly introduced below.

[0036] Figure 1 Schematic diagram of an information retrieval system provided by the present disclosure. Figure 1 As shown, the information retrieval system includes a server 101 and at least one terminal device 102. The server 101 and the terminal device 102 can be connected via a wired network or a wireless network.

[0037] In some implementations, the terminal device 102 displays a search box for the user in response to an operation instruction on the user search page, and upon receiving an input confirmation instruction from the user on the search box, obtains the user input information from the search box on the search page, and sends the user input information to the server 101. The server 101 calls the synonym library, performs synonym conversion and merging processing on the keywords in the user input information, obtains the target search term, and searches the preset data index library according to the target search term to obtain the target index information for display to the user, and returns the target index information to the search page of the terminal device 102.

[0038] In some embodiments, the server 101 includes a database or is connected to a database, and can store synonym information in the synonym database and original index information in the preset data index database in the database. The terminal device 102 can access the associated information in the database through the server 101.

[0039] In some other embodiments, the server 101 may be a single server, or may be a server cluster composed of multiple servers. In some implementations, the server cluster may also be a distributed cluster. The present application does not limit the specific implementation of the server 101.

[0040] The terminal device 102 may be a mobile phone, tablet computer, desktop, laptop, handheld computer, notebook computer, ultra-mobile personal computer (UMPC), netbook, cellular phone, personal digital assistant (PDA), augmented reality (AR) and virtual reality (VR) devices, etc., which can install and use content community applications (such as Kuaishou). The present disclosure does not impose any special restrictions on the specific form of the terminal device 102. It can interact with the user through one or more methods such as keyboard, touchpad, touch screen, remote control, voice interaction or handwriting device.

[0041] The information retrieval method provided in the embodiment of the present application can be applied to the aforementioned Figure 1 The information retrieval system in the implementation architecture shown can also be applied to an information detection device or server.

[0042] For ease of understanding, the information retrieval method provided by the present application is specifically introduced below with reference to the accompanying drawings.

[0043] Figure 2 is a flowchart of an information retrieval method according to an exemplary embodiment. Figure 2 As shown, the information retrieval method includes the following steps.

[0044] S21, based on the synonym database, the keywords in the user input information are converted and merged into synonyms to obtain the target search terms.

[0045] The above-mentioned synonym library includes preset abbreviations, preset full names and the association between the preset abbreviations and the preset full names. The above-mentioned synonym library also includes multiple preset synonyms of multiple expressions and the mapping relationship between the multiple preset synonyms.

[0046] Optionally, the user input information may be input information returned by the terminal device to the server.

[0047] S22, searching in a preset data index library according to the target search term to obtain target index information for display to the user.

[0048] In this step, a match is searched in a preset data index library based on the target search term, and target index information associated with the target search term is matched from the preset data index library.

[0049] For example, for "Agricultural Bank of China's 365-day peace of mind wealth management product", users may only know its abbreviation "Agricultural Bank of China's peace of mind" or "peace of mind product". In this case, if the query system only supports exact matching, the user's search experience will be greatly reduced, because they may only know part of the keywords and cannot obtain complete product information. After the user enters "Agricultural Bank of China's peace of mind" or "peace of mind product", based on the synonym conversion and merging processing in the synonym library, the target search terms become "Agricultural Bank of China's peace of mind", "peace of mind product" and "Agricultural Bank of China's 365-day peace of mind wealth management product". The three dimensions of search information of "Agricultural Bank of China's peace of mind", "peace of mind product" and "Agricultural Bank of China's 365-day peace of mind wealth management product" can be fully retrieved in the preset data index library.

[0050] Through the above-mentioned search method, the keywords of the user input information are first converted into synonyms based on the preset relationship between the preset abbreviations and the preset full names in the synonym library, so that the target search terms can include the full names or abbreviations of the keywords, so that the search terms are more comprehensive and the scope of the search terms is expanded. In this way, by including synonyms in the target search terms, the search system can find information that uses different vocabulary to express the same concept, thereby improving the comprehensiveness of the search results, and further avoiding missing synonyms such as full names or abbreviations during the search process, thereby improving the search scope and search accuracy.

[0051] In addition, users do not need to manually enter multiple synonyms in order to obtain comprehensive results. The system will automatically perform synonym conversion and merging processing, simplifying user operations, improving retrieval efficiency, and enhancing user experience.

[0052] As a refinement and extension of the specific implementation method of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, the embodiment of the present application provides another information retrieval method.

[0053] The process of determining the target search term in the above step S21 is described below for two situations.

[0054] As an implementation method of the first case, in the case where the keyword includes a preset abbreviation or a preset full name in the synonym library, the user input information is segmented to obtain the keyword; the target keyword that is the same as the keyword is screened out from the preset abbreviation and preset full name in the synonym library; based on the association relationship, the associated words associated with the target keyword in the synonym library and the keyword are determined as the target search term.

[0055] The above-mentioned word segmentation processing includes converting the data format of user input information into data standard specifications that are consistent with the index information (i.e., original data) in the preset data index library, so as to support the conversion and normalization of the original data obtained from various channels according to the established unified data standards. On this basis, it is also possible to perform detailed word segmentation processing on the standardized data to ensure the accuracy and efficiency of subsequent information retrieval.

[0056] As an implementation method of the second case, for the case where the keyword does not include a preset abbreviation or a preset full name in the synonym library, when a target keyword identical to the keyword is not screened out from the preset abbreviation and the preset full name in the synonym library, the keyword is determined as the target search term.

[0057] As an implementation mode, before executing step S21, the following implementation steps may also be executed to enable the user to input the search requirement information through the first information configuration control, thereby realizing the user's differentiated requirements.

[0058] First, in response to an operation instruction of a user on a search page of a terminal device, an instruction to display a first information configuration control on the terminal device is sent to the terminal device.

[0059] The first information configuration control is used to input retrieval requirement information.

[0060] Secondly, in response to a confirmation instruction of the retrieval requirement information input on the first information configuration control, a target retrieval mode is determined according to the input retrieval requirement information.

[0061] The retrieval requirement information includes retrieval speed information and / or retrieval accuracy information and / or retrieval mode information.

[0062] Based on the above implementation, the specific process of obtaining the target index information in the above step S22 is as follows.

[0063] First, a target search mode is adopted to query and match the target index term with the preset index information in the preset data index library to obtain the target index information matching the target index term.

[0064] The above-mentioned target search mode includes one or more of the following: precise query search mode, information abbreviation query search mode and fuzzy query search mode.

[0065] The information matching degree of the precise query retrieval mode is higher than that of the information abbreviation query retrieval mode, and the matching degree of the information abbreviation query retrieval mode is higher than that of the fuzzy query retrieval mode.

[0066] The information matching degree is the matching degree between the preset index terms associated with the target index terms in the index information and the target index terms.

[0067] It should be noted that the above-mentioned target search mode can be a composite query search mode consisting of two or three of the precise query search mode, the information abbreviation query search mode and the fuzzy query search mode.

[0068] In some embodiments, in view of some database query methods, users are often required to enter precise information names or specific keywords in the names to retrieve information. However, when faced with massive and complex information data, it is often difficult for users to quickly and accurately lock in the information they need. Especially in the field of financial products, due to the wide variety of products in various industries and the large amount of information, users often do not know the complete names of products. Users can use compound query mode to query accurately.

[0069] In this implementation, when searching, the user may be very clear about some search contents or unclear about some search contents. Therefore, different search requirements will be set for the clear search terms and vague search terms input by the user, so that the search requirement information of each target search term can be input based on the first information configuration control, so as to configure different search modes for different search terms.

[0070] Specifically, when there are multiple target index words, in response to different search requirement information input by the user for different target index words, the target search mode corresponding to each target index word is determined according to the search requirement information corresponding to each target index word. In this way, in response to different search requirements for each target index word, searches are performed according to different target search modes to complete the composite search requirement.

[0071] As another retrieval method, the specific process of obtaining the target index information in the above step S22 is as follows.

[0072] First, according to the precise query retrieval mode, the information abbreviation query retrieval mode and the fuzzy query retrieval mode, the target index term is queried and matched with the preset index information in the preset data index library to obtain the first search information, the second search information and the third search information respectively.

[0073] Second, target index information is obtained according to the first search information, the second search information and the third search information.

[0074] Optionally, in order to improve the readability of the displayed target search information, the first search information, the second search information and the third search information in the target index information are displayed in order of priority.

[0075] The priorities of the first search result, the second search result and the third search result are reduced in sequence.

[0076] Optionally, obtaining the target index information according to the first retrieval information, the second retrieval information and the third retrieval information specifically includes: aggregating the first retrieval information, the second retrieval information and the third retrieval information according to their priorities to obtain the target index information.

[0077] For any target index word, extract the target preset index information with the highest priority among the preset index information associated with the target index word in the first search information, the second search information, and the third search information;

[0078] The target preset index information of each extracted target index word is integrated to obtain the target index information.

[0079] The priorities of the first search information, the second search information, and the third search information decrease in sequence.

[0080] Exemplarily, the target index word A is used to perform a search in three search modes to obtain the second search information b and the third search information c. Then, the second search information b is the target index information of the target index word A.

[0081] The target index word B is used to search in three search modes to obtain the first search information e, the second search information f and the third search information g. The first search information e is the target index information of the target index word B.

[0082] Optionally, the extracted target preset index information of each target index word is input into a machine language learning model to perform semantic learning to obtain the target index information.

[0083] The machine language learning model is a model obtained by training using sample index words extracted from preset index information in a preset data index library and sample index information in the preset index information corresponding to the sample index system as training samples.

[0084] Through the above implementation, with the keywords input by the user as the core, it is possible to intelligently identify and distinguish different scenarios to which the keywords belong, that is, scenarios of different search modes. Based on these scenarios, it provides comprehensive intelligent search functions, including precise query, directly hitting the target content; information abbreviation query, improving search speed; fuzzy query, broadening the search scope; and compound query, flexibly combining multiple keywords. These query methods complement each other, allowing users to easily respond to various query needs.

[0085] In this way, the intelligent association function is realized. When the user enters a keyword, it can be activated immediately, quickly analyzing and filtering out multiple pieces of information that are highly relevant to the keyword. This information is sorted and optimized precisely to ensure that the content that best meets the user's needs is presented first, providing users with both accurate and efficient recommendation services, greatly improving the user's query experience.

[0086] As an implementation mode, in response to a user inputting an operation completion instruction on a second information configuration control of a terminal device, the preset abbreviations, preset full names, and the association between the preset abbreviations and the preset full names configured on the second information configuration control are updated to the preset; the second information configuration control is used to configure configuration information of the preset abbreviations, preset full names, and the association between the preset abbreviations and the preset full names.

[0087] Specifically, for specific keywords, a detailed synonym library can be built. This design aims to further broaden the boundaries of search and capture more relevant information. With the assistance of the synonym library, the tool can achieve more accurate and comprehensive full-text search, improving the efficiency and accuracy of search.

[0088] In this implementation step, the second information configuration control is used to implement customized configuration and real-time updating of the synonym database to ensure the timeliness and accuracy of the information in the synonym database.

[0089] As a specific implementation method, the retrieval process is described as follows.

[0090] First, obtain the original data from each channel, convert and process the data according to the unified and rigorous data standard specifications, perform word segmentation on the processed standard data, and form an original data index library. The original data index library is the preset index library.

[0091] Secondly, a synonym library is pre-configured for the preset index information of the preset index library and verified; the synonym library contains a mapping relationship between the abbreviation and the full name.

[0092] For example, "compulsory traffic insurance" and "traffic accident liability insurance", "Agricultural Bank of China" and "Agricultural Bank of China".

[0093] The preset index information is also called original information.

[0094] Third, when searching for keywords, we first perform intelligent associative search on the keywords entered by the user, and then filter out multiple pieces of information that are highly relevant to the keywords based on the relevance scoring algorithm. We then sort and optimize the information and return it.

[0095] In some implementations, for any search mode retrieval information, the search information associated with the keyword is sorted according to the search frequency, and the search content under each search mode is displayed preferentially according to the search frequency.

[0096] Optionally, the search information whose search frequency is higher than a preset frequency or whose search frequency is before a preset order in each search mode is displayed.

[0097] For example, if you enter "Agricultural Bank of China", "Agricultural Bank of China xx Life Insurance" will be listed in front, and "Agricultural Bank of China xx Fixed Deposit" will be listed in the back.

[0098] Fourth, when searching by keywords, the keywords entered by the user are pre-segmented to obtain the entries corresponding to the keywords. The scene to which the keyword belongs is intelligently identified through the entry. According to the specific scene requirements and based on the conditions or matching degree entered by the user, the appropriate search method is selected: precise query that fully matches the data in the index library, information abbreviation query using abbreviation query, fuzzy query containing the keywords entered by the user, or compound query mixed with the first three, and information matching the keywords is returned.

[0099] For example, when a user enters "Agricultural Bank of China", it will intelligently associate "Agricultural Bank of China's 365-day financial management product" and other information. When searching for "Agricultural Bank of China", all information related to "Agricultural Bank of China" will be retrieved. After the synonym database is configured with the mapping relationship between "compulsory traffic insurance" and "traffic accident liability insurance", querying "compulsory traffic insurance" will retrieve all information related to "traffic accident liability insurance".

[0100] The above intelligent retrieval process takes user keywords as the core, intelligently identifies scenarios and provides precise, abbreviation, fuzzy and compound query functions to meet various user retrieval needs.

[0101] The above-mentioned intelligent association process supports intelligent association, quickly analyzes keywords and sorts and presents highly relevant information, provides accurate and efficient recommendations, and optimizes the user query experience.

[0102] The above synonym library configuration process builds a detailed synonym library for specific keywords, aiming to broaden the search scope, achieve more accurate and comprehensive full-text search, and improve efficiency and accuracy.

[0103] The above-mentioned pre-segmentation process supports data conversion normalization and detailed segmentation processing, ensuring the accuracy and efficiency of information retrieval.

[0104] Compared with the fuzzy search method of the database, the above information retrieval method is more streamlined and the efficiency is significantly improved. At the same time, it can intelligently identify the different scenarios to which the keywords belong, and provide a variety of query methods, including precise query, information abbreviation query, fuzzy query and compound query. These methods can complement each other and flexibly respond to various query needs. Furthermore, by optimizing the query mechanism of keywords and keyword combinations, the efficiency of complex information query has been significantly improved, thus achieving major breakthroughs and remarkable results in practical applications.

[0105] In order to realize the above functions, the information retrieval device includes hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0106] The present disclosure also provides a Figure 3 The information retrieval device shown is applied to an information retrieval system, and includes: a conversion processing unit 301, a retrieval unit 302 and a configuration unit 303.

[0107] The conversion processing unit 301 is configured to perform synonym conversion and merging processing on the keywords of the user input information based on the synonym library to obtain the target search term; the synonym library includes preset abbreviations, preset full names and the association relationship between the preset abbreviations and the preset full names.

[0108] The retrieval unit 302 is configured to search in a preset data index library according to a target search term to obtain target index information for display to the user.

[0109] In one embodiment, the conversion processing unit 301 is specifically configured to: perform word segmentation processing on the user input information to obtain keywords; filter out target keywords that are the same as the keywords from the preset abbreviations and preset full names in the synonym library; based on the association relationship, determine the associated words and keywords associated with the target keywords in the synonym library as target search terms.

[0110] In another embodiment, the conversion processing unit 301 is further specifically configured to: when a target keyword identical to the keyword is not screened out from the preset abbreviations and preset full names in the synonym library, determine the keyword as the target search term.

[0111] In another embodiment, before searching in a preset data index library according to the target search term to obtain the target index information for display to the user, the configuration unit 303 is configured to: in response to the user's operating instructions on the retrieval page of the terminal device, send an instruction to the terminal device to display a first information configuration control; the first information configuration control is used to input retrieval requirement information; in response to a confirmation instruction for the retrieval requirement information input on the first information configuration control, determine the target retrieval mode according to the input retrieval requirement information; the retrieval requirement information includes retrieval speed information and / or retrieval accuracy information and / or retrieval mode information.

[0112] In another embodiment, the retrieval unit 302 is specifically configured to: adopt a target retrieval mode to query and match the target index term with the preset index information in the preset data index library to obtain the target index information matching the target index term; the target retrieval mode includes one or more of the following: precise query retrieval mode, information abbreviation query retrieval mode and fuzzy query retrieval mode; the information matching degree of the precise query retrieval mode is higher than the information matching degree of the information abbreviation query retrieval mode, and the matching degree of the information abbreviation query retrieval mode is higher than the information matching degree of the fuzzy query retrieval mode; the information matching degree is the matching degree of the preset index term associated with the target index term in the index information and the target index term.

[0113] In another embodiment, the retrieval unit 302 is further specifically configured to: query and match the target index term with the preset index information in the preset data index library according to the precise query retrieval mode, the information abbreviation query retrieval mode and the fuzzy query retrieval mode, and obtain the first retrieval information, the second retrieval information and the third retrieval information respectively; obtain the target index information according to the first retrieval information, the second retrieval information and the third retrieval information.

[0114] In another embodiment, the priorities of the first search result, the second search result and the third search result decrease in sequence; the retrieval unit 302 is also specifically configured to: aggregate the first search information, the second search information and the third search information according to the priorities of the first search information, the second search information and the third search information to obtain the target index information.

[0115] In another embodiment, the configuration unit 303 is further specifically configured to: in response to the user inputting an operation completion instruction on the second information configuration control of the terminal device, update the preset abbreviations, preset full names, and the association between the preset abbreviations and the preset full names configured on the second information configuration control to the preset; the second information configuration control is used to configure configuration information of the preset abbreviations, preset full names, and the association between the preset abbreviations and the preset full names.

[0116] Regarding the device in the above embodiment, the specific manner in which each unit module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0117] Figure 4 is a schematic diagram of an information retrieval device provided by this application. Figure 4 The information retrieval device 50 may include at least one processor 501 and a memory 503 for storing processor executable instructions. The processor 501 is configured to execute instructions in the memory 503 to implement the information retrieval method in the following embodiments.

[0118] In addition, the information retrieval device 50 may further include a communication bus 502 , at least one communication interface 504 , an input device 506 , and an output device 505 .

[0119] The processor 501 may be a central processing unit (CPU), a microprocessing unit, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0120] Communication bus 502 may include a pathway for transmitting information between the above-mentioned components.

[0121] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0122] The input device 506 is used to receive input signals and the output device 505 is used to output signals.

[0123] The memory 503 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory may be independent and connected to the processing unit via a bus. The memory may also be integrated with the processing unit.

[0124] The memory 503 is used to store instructions for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the instructions stored in the memory 503, so as to realize the functions in the method of the present application.

[0125] In a specific implementation, as an embodiment, the processor 501 may include one or more CPUs, such as Figure 4 CPU0 and CPU1 in.

[0126] In a specific implementation, as an embodiment, the information retrieval device 50 may include multiple processors, such as Figure 4 501 and processor 507 in the embodiment of the present invention. Each of these processors may be a single-CPU processor or a multi-CPU processor. The processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0127] The above-mentioned information retrieval device can also be a server.

[0128] The information retrieval device is Figure 4 The system shown includes: a processor 501 and a memory 503 for storing executable instructions of the processor 501; wherein the processor 501 is configured to execute the executable instructions to implement the information retrieval method of any possible implementation method described above. And the same technical effect can be achieved, so it will not be repeated here to avoid repetition.

[0129] The embodiment of the present application also provides a computer-readable storage medium, when the instructions in the computer-readable storage medium are executed by the processor of the information retrieval device or the information retrieval equipment, the information retrieval device or the information retrieval equipment can execute the information retrieval method of any possible implementation method as described above. And the same technical effect can be achieved, so it will not be repeated here to avoid repetition.

[0130] An embodiment of the present application also provides a terminal device configured to perform the following operations: in response to an operation instruction on a user search page, obtain user input information from the search page, and send the user input information to a server, so that the server performs the following operations: based on a synonym library, perform synonym conversion and merging processing on the keywords of the user input information to obtain a target search term; the synonym library includes preset abbreviations, preset full names, and an association between the preset abbreviations and the preset full names; according to the target search term, search in a preset data index library to obtain target index information for display to the user.

[0131] In some embodiments, it is also configured to execute: in response to an operation instruction on the user's retrieval page, display a first information configuration control on the retrieval page, and send the retrieval requirement information entered by the user on the first information configuration control to the server, so that the server responds to the confirmation instruction of the retrieval requirement information entered on the first information configuration control, and determines the target retrieval mode according to the input retrieval requirement information; the retrieval requirement information includes retrieval speed information and / or retrieval accuracy information and / or retrieval mode information.

[0132] In some embodiments, it is also configured to execute: displaying a second information configuration control, and sending the synonym information configured and input by the user on the second information configuration control to the server, so that the server responds to the user inputting an operation completion instruction on the second information configuration control of the terminal device, and updates the preset abbreviation, preset full name, and the association relationship between the preset abbreviation and the preset full name configured on the second information configuration control to the preset; the second information configuration control is used to configure configuration information of the preset abbreviation, the preset full name, and the association relationship between the preset abbreviation and the preset full name; the synonym information includes the preset abbreviation, the preset full name, and the association relationship between the preset abbreviation and the preset full name.

[0133] The embodiment of the present application also provides a computer program product, including a computer program or instruction, which is executed by a processor as an information retrieval method in any of the above possible implementations. And it can achieve the same technical effect, so it will not be repeated here to avoid repetition.

[0134] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0135] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. An information retrieval method, characterized in that: The method comprises: Based on a synonym library, the keywords in the user input information are converted and merged into synonyms to obtain target search terms; the synonym library includes preset abbreviations, preset full names, and associations between the preset abbreviations and the preset full names; According to the target search term, a search is performed in a preset data index library to obtain target index information for display to the user.

2. The information retrieval method according to claim 1, characterized in that: Based on the synonym library, the keywords in the user input information are converted and merged into synonyms to obtain target search terms, including: Performing word segmentation processing on the user input information to obtain the keywords; Filtering out a target keyword identical to the keyword from the preset abbreviations and the preset full names in the synonym library; Based on the association relationship, the associated words associated with the target keyword in the synonym library and the keyword are determined as the target search term.

3. The information retrieval method according to claim 2, characterized in that: The method further comprises: When the target keyword identical to the keyword is not screened out from the preset abbreviations and the preset full names in the synonym library, the keyword is determined as the target search term.

4. The information retrieval method according to claim 1, characterized in that: Before searching the preset data index library according to the target search term to obtain the target index information for displaying to the user, the method further includes: In response to an operation instruction of the user on a search page of a terminal device, sending an instruction to the terminal device for the terminal device to display a first information configuration control; the first information configuration control is used to input search requirement information; In response to a confirmation instruction of the retrieval requirement information input on the first information configuration control, a target retrieval mode is determined according to the input retrieval requirement information; the retrieval requirement information includes retrieval speed information and / or retrieval accuracy information and / or retrieval mode information.

5. The information retrieval method according to claim 4, characterized in that: The step of searching in a preset data index library according to the target search term to obtain target index information for display to the user includes: Adopting the target search mode, querying and matching the target index word with the preset index information in the preset data index library, and obtaining the target index information matching the target index word; The target retrieval mode includes one or more of the following: precise query retrieval mode, information abbreviation query retrieval mode and fuzzy query retrieval mode; the information matching degree of the precise query retrieval mode is higher than the information matching degree of the information abbreviation query retrieval mode, and the matching degree of the information abbreviation query retrieval mode is higher than the information matching degree of the fuzzy query retrieval mode; the information matching degree is the matching degree of the preset index term associated with the target index term in the index information and the target index term.

6. The information retrieval method according to claim 1, characterized in that: The step of searching in a preset data index library according to the target search term to obtain target index information for display to the user includes: According to the precise query retrieval mode, the information abbreviation query retrieval mode and the fuzzy query retrieval mode, the target index word is queried and matched with the preset index information in the preset data index library to obtain the first search information, the second search information and the third search information respectively; The target index information is obtained according to the first search information, the second search information and the third search information.

7. The information retrieval method according to claim 6, characterized in that: The priorities of the first search result, the second search result and the third search result are successively lowered; obtaining the target index information according to the first search information, the second search information and the third search information includes: The first search information, the second search information and the third search information are aggregated according to their priorities to obtain the target index information.

8. The information retrieval method according to any one of claims 1 to 7, characterized in that: The method further comprises: In response to the user inputting an operation completion instruction on the second information configuration control of the terminal device, the preset abbreviations, preset full names, and the association between the preset abbreviations and the preset full names configured on the second information configuration control are updated to the preset; the second information configuration control is used to configure configuration information of the preset abbreviations, preset full names, and the association between the preset abbreviations and the preset full names.

9. An information retrieval device, characterized in that: The device comprises: A conversion processing unit is configured to perform synonym conversion and merging processing on the keywords of the user input information based on a synonym library to obtain a target search term; the synonym library includes preset abbreviations, preset full names, and an association relationship between the preset abbreviations and the preset full names; The retrieval unit is configured to search in a preset data index library according to the target search term to obtain target index information for display to the user.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the information retrieval method according to any one of claims 1 to 8.

Images