Information retrieval method and equipment

Abstract

The invention relates to the technical field of computers, in particular to an information retrieval method and device, the method is applied to a server, and the method comprises the steps that in response to the received information retrieval request sent by a first user terminal, the information retrieval request is analyzed, and an analysis result is obtained; retrieving in a private network database and / or a public network database based on the analysis result to obtain at least one target retrieval result; the at least one target retrieval result is sent to the first user terminal; according to the method, the information retrieval efficiency and accuracy can be improved.

Description

Technical Field

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

[0002] With the maturity of Internet technology, private networks are increasingly being used by enterprises, schools or social organizations to protect data and information security.

[0003] Typically, after users enter a restricted network environment, their search objects are limited to information and data available on the private network. At this time, if they want to search on the public network, they need to switch browsers or even terminals and search again, resulting in a complex and inefficient data search process for users in restricted network environments, and the search results obtained are not comprehensive enough. Summary of the Invention

[0004] The embodiments of the present application provide an information retrieval method and device, which improve the efficiency and accuracy of information retrieval.

[0005] In a first aspect, an information retrieval method is provided, wherein the method is applied to a server and comprises:

[0006] In response to receiving the information retrieval request sent by the first user terminal, parsing the information retrieval request to obtain a parsing result;

[0007] Searching the private network database and / or the public network database based on the parsing result to obtain at least one target search result;

[0008] The at least one target retrieval result is sent to the first user terminal.

[0009] By adopting the above technical solution, based on a server capable of simultaneously searching for data in a private network database and a public network database, after receiving an information retrieval request sent by a user terminal, information retrieval is performed in at least one of the private network database and the public network database based on the parsing result of the information retrieval request, thereby achieving the goal of retrieving information for the user in the public network database and the private network database based on the same server, reducing the complexity of the user's information retrieval operation process, and improving the information retrieval efficiency and the completeness of the retrieval results.

[0010] Optionally, searching the private network database and / or the public network database based on the parsing result to obtain at least one target search result includes:

[0011] Searching the private network database and / or the public network database based on the analysis result to obtain multiple candidate search results and a recommendation index value for each candidate search result;

[0012] Based on the recommendation strategy and the recommendation index value of each candidate search result, at least one target search result is determined from the plurality of candidate search results.

[0013] By adopting the above technical solution, the candidate search results obtained by retrieval can be scored to obtain the recommendation index value of each candidate search result, and based on the recommendation strategy and the recommendation index value of the candidate search result, at least one target search result can be determined among the multiple candidate search results, so as to recommend the search results that are more in line with the search intention to the user and improve the accuracy of the determined search results.

[0014] Optionally, the parsing result includes a target keyword, and the searching in the private network database and / or the public network database based on the parsing result to obtain multiple candidate search results and a recommendation index value for each candidate search result includes:

[0015] Retrieving, from the private network database and / or the public network database, a plurality of candidate resources matching the target keyword, wherein the candidate resources include a preset number of characters in the target keyword, and / or the candidate resources include a preset number of characters in an approximate keyword, and the character difference between the approximate keyword and the target keyword satisfies a preset character difference condition;

[0016] Based on each candidate resource, candidate search results are determined respectively to obtain multiple candidate search results, and a recommendation index value of each candidate search result is determined based on a preset scoring strategy.

[0017] Optionally, the parsing result further includes a semantic parsing result. The determining of candidate search results based on each candidate resource includes:

[0018] For each candidate resource, if target information matching the semantic parsing result exists in the candidate resource, a candidate search result is generated based on the target information.

[0019] Optionally, the parsing result further includes resource screening conditions, and the method further includes:

[0020] Based on the resource screening condition, valid resources are screened from the multiple candidate resources to obtain multiple updated candidate resources.

[0021] By adopting the above technical solution, after retrieving multiple candidate resources that match the target keyword, multiple candidate resources that match the user's actual needs can be screened based on the resource screening conditions provided by the user, so as to improve the matching degree between the final target search results and the user's needs.

[0022] Optionally, searching the private network database and / or the public network database for multiple candidate resources matching the target keyword includes:

[0023] For the private network database, obtaining tag information of each pre-stored resource in the private network database;

[0024] If the tag information and the target keyword meet a preset tag matching condition, the pre-stored resource is determined as a valid resource;

[0025] Among the multiple valid resources, multiple candidate resources matching the target keyword are determined.

[0026] By adopting the above technical solution, the target keyword and label information can be compared when searching in the private network database. When the label information and the target keyword meet the preset label matching conditions, the pre-stored resource is determined as a valid resource. The server does not need to traverse each pre-stored resource in the private network database to retrieve the candidate resources that match the target keyword, thereby reducing the resource consumption of information retrieval and improving the retrieval efficiency.

[0027] Optionally, searching the private network database and / or the public network database for multiple candidate resources matching the target keyword includes:

[0028] Based on the target keyword and the database matching strategy, determining a target database that matches the target keyword;

[0029] If the target database is the private network database, multiple candidate resources matching the target keyword are retrieved from the private network database.

[0030] By adopting the above technical solution, before the search, the target database that needs to be searched can be determined in the private network database and the public network database based on the target keywords, so as to reduce the resource consumption of information retrieval and improve the search efficiency when the search information only exists in the private network database.

[0031] Optionally, searching the private network database and / or the public network database based on the parsing result to obtain at least one target search result includes:

[0032] A search engine related to multiple business scenarios is triggered, and searches are performed in a private network database and / or a public network database based on the parsing results to obtain at least one target search result related to each business scenario.

[0033] By adopting the above technical solution, the search pressure can be dispersed to multiple search engines for processing through the search engine associated with each business scenario, which not only improves the search efficiency, but also improves the search accuracy and reliability.

[0034] Optionally, when the target search result is determined based on the candidate search results, the method further includes:

[0035] Determining a matching index value between the analysis result and each business scenario based on a predetermined business matching strategy;

[0036] For each business scenario, based on the matching index value between the parsing result and the business scenario, the recommendation index value of each candidate retrieval result related to the business scenario is updated to obtain an updated recommendation index value of each candidate retrieval result related to the business scenario.

[0037] By adopting the above technical solution, when candidate search results are obtained based on search engine searches associated with multiple business scenarios, the recommendation index values ​​of the candidate search results obtained based on search engine searches associated with each business scenario can be updated according to the matching index values ​​between the parsing results and the business scenarios, so as to recommend to the user the search results that are more in line with the business scenario to which the user's search question belongs.

[0038] Optionally, searching the private network database and / or the public network database based on the parsing result to obtain at least one target search result includes:

[0039] Comparing the parsing results and the search matching conditions associated with each business scenario, and determining the business scenario whose parsing results meet the search matching conditions as the target business scenario;

[0040] A target search engine related to the target business scenario is triggered, and a search is performed in a private network database and / or a public network database based on the parsing result to obtain at least one target search result related to each business scenario.

[0041] By adopting the above technical solution, when search engines for multiple business scenarios are deployed in the server, the target search results can be determined through the search engine for the business scenario that matches the content to be searched by the user, thereby reducing resource consumption and improving search efficiency.

[0042] Optionally, the method further includes:

[0043] In response to receiving the resource storage instruction sent by the second user terminal, obtaining the resources to be stored;

[0044] The resources to be stored are stored in the private network database based on a resource structured format to obtain pre-stored resources, and the resources to be stored are analyzed based on a label processing model to obtain label information of the resources to be stored, and the label information is associated with the pre-stored resources.

[0045] In a second aspect, an information retrieval device is provided, wherein the device is a server and includes:

[0046] a parsing module configured to, in response to receiving an information retrieval request sent by the first user terminal, parse the information retrieval request to obtain a parsing result;

[0047] A retrieval module is configured to search the private network database and / or the public network database based on the parsing result to obtain at least one target retrieval result;

[0048] The sending module is configured to send the at least one target retrieval result to the first user terminal.

[0049] According to a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method according to the first aspect.

[0050] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first aspect is implemented.

[0051] In a fifth aspect, a computer program product is provided, comprising a computer program, which implements the method described in the first aspect when executed by a processor.

[0052] It is to be understood that both the foregoing general description and the following detailed description are exemplary, and are intended to provide further explanation of the technology as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The above and other purposes, features, and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0054] Figure 1 This is a schematic diagram of an implementation scenario of an information retrieval method in an embodiment of the present application.

[0055] Figure 2 This is a flowchart of an information retrieval method according to an embodiment of the present application.

[0056] Figure 3 This is a schematic diagram of an execution scenario of an information retrieval method according to an embodiment of the present application.

[0057] Figure 4It is a schematic diagram of the execution flow of an information retrieval method in an embodiment of the present application.

[0058] Figure 5 This is a block diagram of an information retrieval device according to an embodiment of the present application.

[0059] Figure 6 is a schematic diagram illustrating a computer program product according to an embodiment of the present application.

[0060] Figure 7 FIG. 1 is a hardware block diagram illustrating an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0061] The following describes embodiments of the present application in more detail with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are for illustrative purposes only and are not intended to limit the scope of protection of the present application.

[0062] It should be understood that the various steps described in the method embodiments of the present application can be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0063] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc. mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0064] It should be noted that the modifications of "one" and "multiple" mentioned in this application are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0065] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0066] In order to solve the above problems, the present invention provides an information retrieval method. Figure 1 Schematic diagram showing an implementation scenario of the information retrieval method of the exemplary embodiment of the present application; Figure 1 As shown, the implementation scenario 100 includes a server 101 and a user terminal 102, wherein the server 101 is a server for providing information retrieval services for user terminals used by users. The server can be deployed in the form of a server cluster to provide information retrieval services to users in high-concurrency scenarios; the user terminal 102 is a terminal device used by a user who needs to perform information retrieval, or a terminal device used by an administrator of a private network database. The user terminal can be an electronic device such as a computer, notebook, tablet computer, mobile phone or wearable device. Specifically, it can be determined based on actual needs and is not limited in this embodiment of the present application;

[0067] like Figure 1 As shown, a communication link is established between the server 101 and the user terminal 102 to facilitate the private network database administrator to upload resources within the private network domain, or the user to perform information retrieval based on the information retrieval method provided in the embodiment of the present application.

[0068] Figure 2 A flowchart of an information retrieval method according to an exemplary embodiment of the present application is shown. The method can be applied to a terminal device, such as Figure 2 As shown, the method of the embodiment of the present application may include:

[0069] Step S201: in response to receiving an information retrieval request sent by a first user terminal, parsing the information retrieval request to obtain a parsing result;

[0070] Step S202: Searching the private network database and / or the public network database based on the parsing result to obtain at least one target search result;

[0071] Step S203: sending at least one target search result to the first user terminal;

[0072] To summarize, the information retrieval method provided in the embodiment of the present application is based on a server that has the ability to perform data retrieval in both a private network database and a public network database. After receiving an information retrieval request sent by a user terminal, the server performs information retrieval in at least one of the private network database and the public network database based on the parsing result of the information retrieval request, thereby achieving the goal of retrieving information for the user in the public network database and the private network database based on the same server, reducing the complexity of the user's information retrieval operation process, and improving the information retrieval efficiency and the completeness of the retrieval results.

[0073] The following Figure 2 The specific implementation of each step in the embodiment shown is described in detail:

[0074] In step S201, in response to receiving an information retrieval request sent by a first user terminal, the server parses the information retrieval request to obtain a parsing result.

[0075] In an embodiment of the present application, the information retrieval request includes retrieval information, and the retrieval information is the information to be answered input by the user through the first user terminal, wherein the retrieval information can be of various different types, specifically, it can be determined based on the actual input of the user, and the embodiment of the present application does not limit this. For example, the retrieval information can be text information, picture information or audio information, etc.

[0076] It can be understood that in an embodiment of the present application, the first user terminal can display a retrieval information input page for the user to enter the retrieval information to be queried on the retrieval information input page, and after determining that the user has entered the retrieval information, generate an information retrieval request based on the retrieval information, and send the information retrieval request to the server; wherein, the retrieval information input page can be a page of different application products, wherein the application product can be a web page, a mini-program or an application, etc., and the embodiment of the present application does not limit this.

[0077] In an optional embodiment, the server parses the information retrieval request in response to receiving the information retrieval request sent by the first user terminal, and the process of obtaining the parsing result may include: in response to receiving the information retrieval request sent by the first user terminal, parsing the information retrieval request to obtain target retrieval information, and then calling the information parser corresponding to the type of the target retrieval information to process the target retrieval information to obtain the parsing result.

[0078] It should be noted that, in the embodiments of the present application, the information parsers corresponding to different types of retrieval information generally have different processes for processing retrieval information. For example, for text-based retrieval information, the process of the information parser for text-based retrieval information processing the retrieval information may include: performing word segmentation processing on the text to obtain target keywords. Furthermore, the server may also perform semantic analysis based on the target keywords and the retrieval information to obtain semantic parsing results; or, for image-based retrieval information, the process of the information parser for image-based retrieval information processing the retrieval information may include: performing text recognition on the image file to obtain the text information in the image file, and then performing word segmentation processing on the text information to obtain target keywords. Furthermore, the server may also perform semantic analysis based on the target keywords and the text information in the image to obtain semantic parsing results; or, for audio-based retrieval information, the process of the information parser for audio-based retrieval information processing the retrieval information may include: extracting text information from the audio file to obtain the text information in the audio file, and then performing word segmentation processing on the text information to obtain target keywords. Furthermore, the server may also perform semantic analysis based on the keywords and the text information in the image to obtain semantic parsing results.

[0079] It should be noted that in the embodiment of the present application, the target keyword consists of at least one character, and the target keyword is the smallest character unit that can be used for word segmentation in the text contained in the search information; for example, if the search information is: Please check today's weather, the target keywords are: today and weather two keywords; wherein, the server can determine the target keyword as the parsing result; optionally, the parsing result can also include the target search result and / or semantic parsing result.

[0080] In step S202, the server searches the private network database and / or the public network database based on the parsing result to obtain at least one target search result.

[0081] In an embodiment of the present application, the server can simultaneously search at least one of a private network database and a public network database based on the analysis results to obtain the target search results. The private network database can pre-store pre-stored resources, which may include terminology database data, announcement document data, knowledge base data, private domain community forum data, process document data and administrative document data, etc. The public network database can contain data accessible to nodes on the Internet, such as information, policy documents and open forum data of various industries, etc., where the data format can be HTML, Word, PDF, Excel, etc.

[0082] In an optional embodiment, the server may also allow a private network database administrator to store private network data in the private network database, wherein the server may: in response to receiving a resource storage instruction sent by a second user terminal, obtain the resources to be stored; then, store the resources to be stored in the private network database based on a resource structured format to obtain pre-stored resources; analyze the resources to be stored based on a label processing model to obtain label information for the resources to be stored; and associate the label information with the pre-stored resources, wherein the label information includes descriptive phrases or word groups that classify and summarize the content of the resources. On the one hand, the private network database administrator can store private network data in the database according to the resource structured format to facilitate data management within the private network domain; on the other hand, label information can be generated for pre-stored resources in the private network database to facilitate rapid matching of matching candidate resources when users perform information searches.

[0083] It should be noted that in the embodiment of the present application, the resource structured format is a pre-established resource storage format. The resource structured format may include field identifiers, field types, field lengths, whether the field can be null values, and field description information, etc. Specifically, it can be determined based on actual needs. The embodiment of the present application does not limit this. For example, as shown in Table 1, Table 1 shows a resource structured format provided by the embodiment of the present application. The resource structured format shown in Table 1 includes field identifiers, field types, whether the field can be null values, and field description information.

[0084] Table 1

[0085] Field Tags Field Type Is it non-empty? Field Description docKey String yes Unique key identifier docSubject String yes title docSummary String no Contents Summary docLink String no Document source link docModule String no Document source business identifier keyword String no Tags, keywords docType String yes Document type: Rich text / attachment fileName String no Attachment Name docContent Object yes Document Contents docCreator String no Document Author docCreateTime timestamp yes Creation time

[0086] Among them, the process of the server storing the resources to be stored in the private network database based on the resource structured format may include: synchronizing the resources to be stored to the intermediate table through data synchronization technology, and traversing each resource to be stored in the intermediate table, parsing the resources to be stored according to the content parsing engine corresponding to the data format of each resource to be stored, and obtaining the field values ​​associated with different fields in the resource structured format; further, based on the resource structured format and the field values ​​associated with different fields, storing the resources to be stored to obtain pre-stored resources, wherein the data synchronization technology can be Fast Data Integration (FDI), Application Programming Interface Gateway (API Gateway, APIG), or data lake, etc.

[0087] It should be noted that in the embodiment of the present application, the server can search at least one of the private network database and the public network database through a pre-set search strategy combined with the analysis results, wherein the search strategy can be determined based on actual needs, and the embodiment of the present application does not limit this.

[0088] For example, in an embodiment of the present application, the retrieval strategy may include a resource matching strategy, which is a strategy used to match resources in the database that match the user's retrieval information. For example, the resource matching strategy may include: a general matching algorithm, a proximity matching algorithm and / or a phrase search algorithm, etc.

[0089] Optionally, the search strategy may also include: resource screening conditions, search result scoring strategy, database matching strategy and / or search result filtering strategy, etc.

[0090] Among them, the resource screening conditions are restriction conditions used to screen resources that meet user needs from the retrieved candidate resources. The resource screening conditions can be pre-configured based on actual needs, or obtained after the server parses the information retrieval request; wherein, the resource screening conditions may include: resource time restriction conditions, resource category restriction conditions, resource status restriction conditions and resource search area restriction conditions, etc. For example, the resource screening conditions include: resource time conditions are: resources within 1 year before the current time, resource category restriction conditions are: administrative documents, forums and announcements, resource status restriction conditions are: valid resources, and resource search area restriction conditions are: the title or text of the retrieved document resource.

[0091] The scoring strategy for the retrieval results is a strategy for determining the recommendation value of the retrieval results. The scoring strategy for the retrieval results can be determined based on actual needs. The embodiments of the present application do not limit this. For example, the scoring strategy for the retrieval results may include an ES (Elasticsearch) scoring strategy or a BM25 (Best Matching 25) scoring strategy.

[0092] The database matching strategy is a strategy used to screen the target database in the private network database and the public network database, wherein the database matching strategy includes: database matching conditions associated with the private network database and / or the public network database, the database matching conditions may include that the target keyword and the matching keyword in the parsing result are the same, and / or that the target keyword and the approximate matching keyword in the parsing result are the same, wherein the matching keyword and / or the approximate matching keyword in the database matching condition can be determined based on actual needs, and the embodiments of the present application do not limit this.

[0093] The filtering strategy of the retrieval results is used to filter the retrieval results, wherein the filtering strategy of the retrieval results may include the filtering conditions of the retrieval results. Specifically, it can be determined based on actual needs. The embodiment of the present application does not limit this. For example, the filtering conditions of the retrieval results may include that the document type is type A document.

[0094] In an optional embodiment, the server searches the private network database and / or the public network database based on the parsing result to obtain at least one target retrieval result. The process may include: searching the private network database and / or the public network database based on the parsing result to obtain multiple candidate retrieval results and a recommendation index value for each candidate retrieval result; then, based on the recommendation strategy and the recommendation index value for each candidate retrieval result, determining at least one target retrieval result from the multiple candidate retrieval results. The retrieved candidate retrieval results may be scored to obtain a recommendation index value for each candidate retrieval result, and based on the recommendation strategy and the recommendation index value for the candidate retrieval results, determining at least one target retrieval result from the multiple candidate retrieval results, so as to recommend retrieval results that are more in line with the retrieval intent to the user and improve the accuracy of the determined retrieval results.

[0095] Among them, the recommendation strategy can be determined based on actual needs, and the embodiments of the present application do not limit this. For example, the recommendation strategy can be: determining the candidate retrieval result with the highest recommendation index value as the target retrieval result, or sorting multiple candidate retrieval results in descending order according to the recommendation index value to obtain a candidate retrieval result sequence, and then, starting from the candidate retrieval result with the largest recommendation index value in the candidate retrieval result sequence, selecting a preset number of candidate retrieval results and determining them as the target retrieval results, wherein the preset number can be determined based on actual needs. For example, the preset number can be 10, or, among multiple candidate retrieval results, the candidate retrieval result with a recommendation index value greater than the recommendation index value threshold is determined as the target retrieval result, wherein the recommendation index value threshold can be determined based on actual needs.

[0096] In an optional embodiment, the parsing result includes a target keyword, and the server searches a private network database and / or a public network database based on the parsing result to obtain multiple candidate search results, and the process of recommending an index value for each candidate search result may include: searching the private network database and / or the public network database for multiple candidate resources that match the target keyword; further, determining a candidate search result based on each candidate resource to obtain multiple candidate search results, and determining a recommendation index value for each candidate search result based on a preset scoring strategy, wherein the candidate resource includes a preset number of characters in the target keyword, and / or the candidate resource includes a preset number of characters in an approximate keyword, and the character difference between the approximate keyword and the target keyword meets a preset character difference condition. The character difference condition can be determined based on actual needs, and the embodiment of the present application is not limited to this. For example, the character difference condition includes the same meaning but different characters, or at least three adjacent characters are the same. When the target keyword is included in the parsing result, the candidate resource can be directly searched and determined based on the target keyword, and the search results and the recommendation index value of each search result can be determined, thereby improving the efficiency of determining the search result based on the parsing result.

[0097] It should be noted that in an embodiment of the present application, the server can use a large language model to retrieve multiple candidate resources that match the target keyword in the private network database and / or the public network database, wherein the type of the large language model can be determined based on actual needs, and the embodiment of the present application does not limit this. For example, the large language model can be a fourth-generation generative pre-trained transformer model (Generative Pre-trained Transformer 4, CTP4), a fifth-generation generative pre-trained transformer (Generative Pre-trained Transformer 5, GTP5All), or a large language model meta AI (Large Language Model Meta AI, LLaMa); wherein, the resource matching strategy used by the server in the search process of the private network database using the large language model can be determined based on the actual configuration, and the embodiment of the present application does not limit this.

[0098] Among them, when the target keyword is included in the parsing result, the server will determine the candidate search results based on each candidate resource respectively. The process of obtaining multiple candidate search results includes: determining each candidate resource as a candidate search result respectively, and obtaining multiple candidate search results.

[0099] It can be understood that in the embodiment of the present application, the scoring strategy used in the process of the server determining the recommendation index value of each candidate search result can be configured based on actual needs, and the embodiment of the present application does not limit this.

[0100] For example, if the scoring strategy is the ES scoring strategy, the ES scoring strategy is:

[0101] score(q, d)=queryNorm(q)·coord(q, d)·∑(tf(t in d)·idf(t)^2·t.getBoost()·norm(t, d));

[0102] Where score(q,d) is the relevance score of document d to query q; queryNorm(q) is the query normalization factor used to normalize the query; coord(q,d) is the coordination factor, which represents the ratio of the number of hit terms in the query to the total number of terms in the query; tf(tind) is the term frequency of term t in document d; idf(t) is the inverse document frequency of term t; t.getBoost() is the weight value used in the query; norm(t,d) is the field length normalization value.

[0103] It should be noted that in an embodiment of the present application, when the scoring strategy is the ES scoring strategy, the weight values ​​pre-configured in the server may include: resource weight values ​​configured for resources, which may be determined based on the field or business to which the resource belongs, weight values ​​configured for each field in the resource, which may include titles, attachment names, abstracts, text, and reference files, etc., and weight values ​​determined for the matching performance of target keywords in different fields of the resource, wherein the matching performance may include: the field contains a preset number of characters for each target keyword or each approximate keyword, or the beginning or end of the field contains a preset number of characters for each target keyword or each approximate keyword, the field contains part of the target keyword or a preset number of characters for each approximate keyword, etc.

[0104] Among them, for matching performance, the server can also set a weight value adjustment strategy. For example, the higher the frequency of the target keyword or approximate keyword appearing in the field, the server will increase the weight value associated with the matching performance according to the preset adjustment strategy. Specifically, the increase value can be determined based on actual needs. The embodiment of the present application does not limit this. For example, if the target keyword or approximate keyword appears three more times in the field, the weight value will be increased by 0.1.

[0105] In an optional embodiment, the parsing result also includes a semantic parsing result. The server may determine candidate search results based on each candidate resource, and the process may include: for each candidate resource, if target information matching the semantic parsing result exists in the candidate resource, generating a candidate search result based on the target information, wherein the target information is information used to answer the user's question. After determining, based on the target keyword, that candidate resources may contain target information that can be used to answer the user's question, and if it is determined that the candidate resources do contain target information that can answer the user's question, the target information may be extracted to obtain a candidate search result, so as to combine the semantic analysis results to improve the accuracy and reliability of the determined target search result.

[0106] In an optional embodiment, the parsing result also includes resource screening conditions. After retrieving multiple candidate resources matching the target keyword, the server may further: based on the resource screening conditions, screen valid resources from the multiple candidate resources to obtain updated multiple candidate resources. After retrieving multiple candidate resources matching the target keyword, the server may screen multiple candidate resources that match the user's actual needs based on the resource screening conditions provided by the user, thereby improving the matching degree between the final target search result and the user's needs.

[0107] In an optional embodiment, the process of the server retrieving multiple candidate resources matching the target keyword in the private network database and / or public network database may include: obtaining the tag information of each pre-stored resource in the private network database; then, if the tag information and the target keyword meet a preset tag matching condition, determining the pre-stored resource as a valid resource; further, determining multiple candidate resources matching the target keyword among multiple valid resources. When searching in the private network database, the target keyword and the tag information can be compared, and if the tag information and the target keyword meet the preset tag matching condition, the pre-stored resource can be determined as a valid resource. The server does not need to traverse each pre-stored resource in the private network database to retrieve the candidate resource matching the target keyword, thereby reducing resource consumption of information retrieval and improving retrieval efficiency.

[0108] Among them, the preset tag matching conditions can be determined based on actual needs, and the embodiments of the present application do not limit this. For example, the tag matching conditions may include: the target keyword exists in the business tag, or there are similar keywords of the target keyword in the tag information.

[0109] In an optional embodiment, the process of the server searching the private network database and / or public network database for multiple candidate resources matching the target keyword may include: determining a target database matching the target keyword based on the target keyword and a database matching strategy; then, if the target database is the private network database, searching the private network database for multiple candidate resources matching the target keyword. Prior to the search, the target databases to be searched may be determined based on the target keyword in the private network database and the public network database, thereby reducing resource consumption and improving search efficiency when the search information exists solely in one private network database.

[0110] Optionally, the process of the server determining the target database matching the target keyword based on the target keyword and the database matching strategy may include: comparing the target keyword, and the matching keyword and / or the approximate matching keyword in the database matching condition associated with the private network database; if the target keyword, and the matching keyword and / or the approximate matching keyword in the database matching condition associated with the private network database are the same, then determining that the target database is a private network database.

[0111] Alternatively, if the target keyword and each matching keyword and / or each approximate matching keyword in the database matching condition associated with the private network database are different, the target keyword and the matching keyword and / or the approximate matching keyword in the database matching condition associated with the public network database are compared. If the target keyword and the matching keyword and / or the approximate matching keyword in the database matching condition associated with the public network database are the same, the target database is determined to be a public network database; or, if the target keyword and each matching keyword and / or each approximate matching keyword in the database matching condition associated with the public network database are different, the target database is determined to be a private network database and a public network database.

[0112] In an optional embodiment, the process of the server searching in a private network database and / or a public network database based on the analysis result to obtain at least one target retrieval result may include: searching in a private network database and / or a public network database based on the analysis result to obtain multiple candidate retrieval results, and determining the multiple candidate retrieval results as target retrieval results when the number of the multiple candidate retrieval results is less than or equal to a quantity threshold, wherein the quantity threshold can be determined based on actual needs, and the embodiment of the present application does not limit this. For example, the quantity threshold can be greater than or equal to 2 and less than or equal to 5.

[0113] It should be noted that in the embodiment of the present application, in order to further improve the retrieval efficiency, multiple retrieval engines can be configured in the server, each retrieval engine can correspond to a business scenario, and the resources retrieved by each retrieval engine during the retrieval process are usually resources corresponding to the business scenario related to the business engine, so as to further improve the retrieval efficiency and accuracy. Among them, the business scenario can be configured based on actual needs, and the embodiment of the present application does not limit this. For example, the business scenarios may include: administrative management scenarios, project management scenarios, and logistics management scenarios, etc.

[0114] In an optional embodiment, the server searches a private network database and / or a public network database based on the parsed results to obtain at least one target search result, which may include triggering search engines associated with multiple business scenarios and searching the private network database and / or the public network database based on the parsed results to obtain at least one target search result associated with each business scenario. By using search engines associated with each business scenario, the search load can be distributed across multiple search engines for processing, thereby improving not only search efficiency but also search accuracy and reliability.

[0115] In an optional embodiment, when the target search result is determined based on the candidate search results, the server may further: determine a matching index value between the parsing result and each business scenario based on a predetermined business matching strategy; then, for each business scenario, update the recommendation index value of each candidate search result related to the business scenario based on the matching index value between the parsing result and the business scenario, thereby obtaining an updated recommendation index value for each candidate search result related to the business scenario. When candidate search results are obtained based on a search engine search associated with multiple business scenarios, the recommendation index value of the candidate search results obtained based on a search engine search associated with each business scenario may be updated based on the matching index value between the parsing result and the business scenario, so as to recommend to the user search results that are more in line with the business scenario to which the user's search question belongs.

[0116] Among them, the business matching strategy includes: when the target keyword in the parsing result is the same as the scenario feature keyword in the business scenario description information, the matching index value is determined as the first parameter value; and when the target keyword in the parsing result is different from the scenario feature keyword in the business scenario description information, the matching index value is determined as the second parameter value, wherein the scenario feature keyword can be pre-configured during the search engine deployment process of the business scenario.

[0117] Alternatively, the business matching strategy may also include: when a preset number of target keywords in the parsing results are the same as the scenario feature keywords in the business scenario description information, the matching index value is determined as the third parameter value, wherein the preset number, the first parameter value, the second parameter value and the third parameter value can be determined based on actual needs, and the embodiments of the present application do not limit this.

[0118] It can be understood that, when the target retrieval result is determined based on the candidate retrieval results, the process of the server determining at least one target retrieval result may include: determining at least one target retrieval result among the multiple candidate retrieval results based on the recommendation strategy and the updated recommendation index value of each candidate retrieval result.

[0119] In an optional embodiment, when search engines associated with multiple businesses are deployed in the server, the process of the server searching in a private network database and / or a public network database based on the parsing results to obtain at least one target retrieval result may include: comparing the parsing results and the search matching conditions associated with each business scenario, and determining the business scenario for which the parsing results meet the search matching conditions as the target business scenario; then, triggering the target search engine related to the target business scenario, searching in the private network database and / or the public network database based on the parsing results, and obtaining at least one target retrieval result related to each business scenario. When search engines for multiple business scenarios are deployed in the server, the target retrieval result can be determined by using the search engine for the business scenario that matches the content to be searched by the user, thereby reducing resource consumption and improving retrieval efficiency.

[0120] Among them, the search matching conditions associated with each business scenario include whether the target keywords in the parsing results are consistent with the scenario feature keywords of the business scenario. If they are consistent, it is determined that the parsing results meet the search matching conditions; otherwise, it is determined that the parsing results do not meet the search matching conditions.

[0121] It can be understood that the server triggers search engines related to multiple business scenarios, and searches in the private network database and / or the public network database based on the analysis results to obtain at least one target retrieval result related to each business scenario, or triggers a target search engine related to the target business scenario, and searches in the private network database and / or the public network database based on the analysis results to obtain at least one target retrieval result related to each business scenario. For this process, please refer to the above embodiment, in which the server searches in the private network database and / or the public network database based on the analysis results to obtain at least one target retrieval result. This embodiment of the present application will not elaborate on this.

[0122] In step S203, the server sends the at least one target search result to the first user terminal;

[0123] In the embodiment of the present application, the target search result is the question-answering content that matches the user's search information.

[0124] In an optional embodiment, before sending the at least one target search result to the first user terminal, the server may further filter the at least one target search result based on a search result filtering policy to obtain an updated target search result, and send the updated target search result to the first user terminal. The obtained target search result may be further filtered based on the search result filtering policy to improve the reliability and effectiveness of the search results pushed to the user.

[0125] It can be understood that after the first user terminal obtains the target retrieval result, it can query the target display template associated with the resource type identifier in the prefabricated template library based on the type identifier of the target retrieval result, wherein, when the target display template exists in the prefabricated template library, the target retrieval result is displayed based on the target display template, or, when the target display template does not exist in the prefabricated template library, the target retrieval result is displayed based on the conventional display template; wherein, the type of the target retrieval result can be text, picture or web page, etc.

[0126] In an optional embodiment, the server may further: read historical parsing results of past information retrieval requests, and based on the historical parsing results and the parsing results of the currently received information retrieval request, estimate relevant search intent, search the private network database and / or the public network database based on the relevant search intent to obtain at least one piece of recommended information, and send the at least one piece of recommended information to the first user terminal. Based on the user's current search information and historical search information, the server may predict recommended information that the user may be interested in, and send the recommended information to the first user terminal, thereby improving the user's information retrieval experience.

[0127] Among them, the process of the server estimating the relevant retrieval intention based on the historical analysis results and the analysis results of the currently received information retrieval request can be implemented based on the intention recognition technology, and the process of the server searching in the private network database and / or the public network database based on the relevant retrieval intention to obtain at least one recommended information can refer to the above embodiment, in which the server searches in the private network database and / or the public network database based on the analysis results to obtain at least one target retrieval result, which will not be elaborated in the embodiments of the present application.

[0128] For example, Figure 3 As shown, Figure 3A schematic diagram of an execution scenario of an information retrieval method provided in an embodiment of the present application is shown. The execution scenario of the information retrieval method is constructed based on a chat channel module 301, an information parsing module 302, and an integration center module 303. The chat channel module 301 is used to obtain retrieval information input by a user and provide the retrieval information to the information parsing module 302 through an information retrieval request. The information parsing module 302 determines the parsing result of the information retrieval request through word segmentation and semantic analysis, and determines a target database and provides the parsing result to the integration center module 303. The integration center module 303 searches the target database (public network database and / or private network database) based on the parsing result to obtain multiple candidate resources, and sends the multiple candidate resources to the information parsing module 302. The information parsing module 302 can screen the candidate resources based on the resource screening conditions, and determine the candidate retrieval results based on the screened candidate resources, and determine the recommended index value of each candidate retrieval result based on a preset scoring strategy. At the same time, the multiple candidate retrieval results can also be sorted based on the recommended index value to process the target retrieval result.

[0129] For example, Figure 4 As shown, Figure 4 A schematic diagram illustrating the execution flow of an information retrieval method provided in an embodiment of the present application is shown. In this diagram, a user inputs search information via a first user terminal, a server obtains the information retrieval request via a chat channel, performs word segmentation and semantic analysis on the retrieval request via an information parsing module to obtain a parsing result, and, based on the parsing result, searches a private network database and a public network database to obtain at least one target retrieval result. Finally, the at least one target retrieval result is sent to the first user terminal.

[0130] It is understandable that in the embodiments of the present application, Figure 3 and Figure 4 For the specific implementation process in the scenario shown in , please refer to the above embodiment, and this application will not go into details.

[0131] The exemplary embodiment of the present application provides an information retrieval device, Figure 5 A schematic block diagram of the functional modules of an information retrieval device according to an exemplary embodiment of the present application is shown. The device is a server, such as Figure 5 As shown, the information retrieval device 500 includes:

[0132] The parsing module 501 is configured to, in response to receiving an information retrieval request sent by the first user terminal, parse the information retrieval request to obtain a parsing result;

[0133] A search module 502 is configured to search the private network database and / or the public network database based on the parsing result to obtain at least one target search result;

[0134] The sending module 503 is configured to send the at least one target search result to the first user terminal.

[0135] Optionally, the retrieval module 502 is configured to:

[0136] Searching the private network database and / or the public network database based on the analysis result to obtain multiple candidate search results and a recommendation index value for each candidate search result;

[0137] Based on the recommendation strategy and the recommendation index value of each candidate search result, at least one target search result is determined from the plurality of candidate search results.

[0138] Optionally, the parsing result includes target keywords, and the retrieval module 502 is configured to:

[0139] Retrieving, from the private network database and / or the public network database, a plurality of candidate resources matching the target keyword, wherein the candidate resources include a preset number of characters in the target keyword, and / or the candidate resources include a preset number of characters in an approximate keyword, and the character difference between the approximate keyword and the target keyword satisfies a preset character difference condition;

[0140] Based on each candidate resource, candidate search results are determined respectively to obtain multiple candidate search results, and a recommendation index value of each candidate search result is determined based on a preset scoring strategy.

[0141] Optionally, the parsing result further includes a semantic parsing result, and the retrieval module 502 is configured to:

[0142] For each candidate resource, if target information matching the semantic parsing result exists in the candidate resource, a candidate search result is generated based on the target information.

[0143] Optionally, the parsing result further includes a resource screening condition, and the apparatus further includes a screening module 504 configured to:

[0144] Based on the resource screening condition, valid resources are screened from the multiple candidate resources to obtain multiple updated candidate resources.

[0145] Optionally, the retrieval module 502 is configured to:

[0146] For the private network database, obtaining tag information of each pre-stored resource in the private network database;

[0147] If the tag information and the target keyword meet a preset tag matching condition, the pre-stored resource is determined as a valid resource;

[0148] Among the multiple valid resources, multiple candidate resources matching the target keyword are determined.

[0149] Optionally, the retrieval module 502 is configured to:

[0150] Based on the target keyword and the database matching strategy, determining a target database that matches the target keyword;

[0151] If the target database is the private network database, multiple candidate resources matching the target keyword are retrieved from the private network database.

[0152] Optionally, the retrieval module 502 is configured to:

[0153] A search engine related to multiple business scenarios is triggered, and searches are performed in a private network database and / or a public network database based on the parsing results to obtain at least one target search result related to each business scenario.

[0154] Optionally, when the target search result is determined based on the candidate search result, the apparatus further includes an updating module 505 configured to:

[0155] Determining a matching index value between the analysis result and each business scenario based on a predetermined business matching strategy;

[0156] For each business scenario, based on the matching index value between the parsing result and the business scenario, the recommendation index value of each candidate retrieval result related to the business scenario is updated to obtain an updated recommendation index value of each candidate retrieval result related to the business scenario.

[0157] Optionally, the retrieval module 502 is configured to:

[0158] Comparing the parsing results and the search matching conditions associated with each business scenario, and determining the business scenario whose parsing results meet the search matching conditions as the target business scenario;

[0159] A target search engine related to the target business scenario is triggered, and a search is performed in a private network database and / or a public network database based on the parsing result to obtain at least one target search result related to each business scenario.

[0160] Optionally, the apparatus further includes a resource storage module 506 configured to:

[0161] In response to receiving the resource storage instruction sent by the second user terminal, obtaining the resources to be stored;

[0162] The resources to be stored are stored in the private network database based on a resource structured format to obtain pre-stored resources, and the resources to be stored are analyzed based on a label processing model to obtain label information of the resources to be stored, and the label information is associated with the pre-stored resources.

[0163] The exemplary embodiments of the present application further provide an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, wherein the computer program, when executed by the at least one processor, causes the electronic device to perform a method according to an embodiment of the present application.

[0164] An exemplary embodiment of the present application further provides a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to perform a method according to an embodiment of the present application.

[0165] like Figure 6 As shown, the exemplary embodiment of the present application further provides a computer program product 600, including a computer program 601, wherein when the computer program is executed by a processor of a computer, it is used to enable the computer to perform the method according to the embodiment of the present application.

[0166] refer to Figure 7 , a block diagram of an electronic device 700 that can serve as a server of the present application will now be described, which is an example of a hardware device that can be applied to various aspects of the present application. Electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0167] like Figure 7 As shown, the electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. Various programs and data required for the operation of the electronic device 700 can also be stored in the RAM 703. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0168] Multiple components within electronic device 700 are connected to I / O interface 705, including an input unit 706, an output unit 707, a storage unit 708, and a communication unit 709. Input unit 706 can be any type of device capable of inputting information into electronic device 700. Input unit 706 can receive input numeric or character information and generate key input signals related to user settings and / or function control of the electronic device. Output unit 707 can be any type of device capable of presenting information and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. Storage unit 708 may include, but is not limited to, a magnetic disk or an optical disk. Communication unit 709 allows electronic device 700 to exchange information / data with other devices via computer networks such as the Internet and / or various telecommunication networks and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0169] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units for running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above. For example, in some embodiments, the method of the exemplary embodiment of the present application may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via the ROM 702 and / or the communication unit 709. In some embodiments, the computing unit 701 may be configured to perform the method of the exemplary embodiment of the present application by any other appropriate means (e.g., by means of firmware).

[0170] The program code for implementing the methods of the present application can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow charts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0171] In the context of the present application, a machine-readable medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0172] As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., magnetic disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including machine-readable media that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0173] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0174] In the above embodiments, they can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, they can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is performed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a terminal, a user device or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program or instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, a hard disk, or a tape; it can also be an optical medium, such as a digital video disc (DVD); it can also be a semiconductor medium, such as a solid state drive (SSD).

[0175] Although the present application has been described with reference to specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely illustrative of the present application as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, the present application is intended to include such modifications and variations as fall within the scope of the claims of the present application and their equivalents.

Claims

1. An information retrieval method, characterized in that: The method is applied to a server and includes: In response to receiving the information retrieval request sent by the first user terminal, parsing the information retrieval request to obtain a parsing result; Searching the private network database and / or the public network database based on the parsing result to obtain at least one target search result; The at least one target retrieval result is sent to the first user terminal.

2. The information retrieval method according to claim 1, wherein: The searching in the private network database and / or the public network database based on the parsing result to obtain at least one target search result includes: Searching the private network database and / or the public network database based on the analysis result to obtain multiple candidate search results and a recommendation index value for each candidate search result; Based on the recommendation strategy and the recommendation index value of each candidate search result, at least one target search result is determined from the plurality of candidate search results.

3. The information retrieval method according to claim 2, wherein: The parsing result includes a target keyword. The search is performed in a private network database and / or a public network database based on the parsing result to obtain multiple candidate search results, and a recommendation index value for each candidate search result includes: Retrieving, from the private network database and / or the public network database, a plurality of candidate resources matching the target keyword, wherein the candidate resources include a preset number of characters in the target keyword, and / or the candidate resources include a preset number of characters in an approximate keyword, and the character difference between the approximate keyword and the target keyword satisfies a preset character difference condition; Based on each candidate resource, candidate search results are determined respectively to obtain multiple candidate search results, and a recommendation index value of each candidate search result is determined based on a preset scoring strategy.

4. The information retrieval method according to claim 3, wherein: The parsing result also includes a semantic parsing result. The candidate search results are determined based on each candidate resource, including: For each candidate resource, if target information matching the semantic parsing result exists in the candidate resource, a candidate search result is generated based on the target information.

5. The information retrieval method according to claim 3, wherein: Retrieving multiple candidate resources matching the target keyword in the private network database and / or the public network database includes: For the private network database, obtaining tag information of each pre-stored resource in the private network database; If the tag information and the target keyword meet a preset tag matching condition, the pre-stored resource is determined as a valid resource; Among the multiple valid resources, multiple candidate resources matching the target keyword are determined.

6. The information retrieval method according to claim 3, wherein: Retrieving multiple candidate resources matching the target keyword in the private network database and / or the public network database includes: Based on the target keyword and the database matching strategy, determining a target database that matches the target keyword; If the target database is the private network database, multiple candidate resources matching the target keyword are retrieved from the private network database.

7. The information retrieval method according to any one of claims 1 to 6, wherein: In the case where the target search result is determined based on the candidate search results, the method further includes: Determining a matching index value between the analysis result and each business scenario based on a predetermined business matching strategy; For each business scenario, based on the matching index value between the parsing result and the business scenario, the recommendation index value of each candidate retrieval result related to the business scenario is updated to obtain an updated recommendation index value of each candidate retrieval result related to the business scenario.

8. The information retrieval method according to any one of claims 1 to 6, characterized in that: The searching in the private network database and / or the public network database based on the parsing result to obtain at least one target search result includes: Comparing the parsing results and the search matching conditions associated with each business scenario, and determining the business scenario whose parsing results meet the search matching conditions as the target business scenario; A target search engine related to the target business scenario is triggered, and a search is performed in a private network database and / or a public network database based on the parsing result to obtain at least one target search result related to each business scenario.

9. The information retrieval method according to any one of claims 1 to 6, wherein: The method further comprises: In response to receiving the resource storage instruction sent by the second user terminal, obtaining the resources to be stored; The resources to be stored are stored in the private network database based on a resource structured format to obtain pre-stored resources, and the resources to be stored are analyzed based on a label processing model to obtain label information of the resources to be stored, and the label information is associated with the pre-stored resources.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the method according to any one of claims 1 to 9.

Images