Information retrieval optimization method and device, electronic equipment and storage medium

Abstract

The invention discloses an information retrieval optimization method and device, electronic equipment and a storage medium. The method comprises the following steps: according to a knowledge graph corresponding to a website, labeling an attribute label for a target webpage of the website; wherein the knowledge graph comprises content keywords under each content category in the field to which the website belongs and relation attribute tags among the content keywords; updating an aggregation page of the website based on an attribute tag marked for the target webpage; and based on the attribute tag of the webpage, obtaining the aggregation page matched with the current retrieval text from the aggregation pages of the website. According to the embodiment of the invention, the technical problem that a search engine cannot accurately obtain the target information with relatively high matching degree with the retrieval theme input by the user in the related technology can be solved.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and specifically to an information retrieval optimization method, device, electronic device and storage medium. Background Art

[0002] How to better let search engines understand the content of the website is the core task of SEO (Search Engine Optimization) content construction. Efficient on-site search allows users to find target information quickly and accurately. Usually, when facing the search topic entered by the user, the search engine recalls the target information matching the search topic based on similar words or words with the same frequency of occurrence as the search topic. However, this method cannot accurately obtain the target information with a high degree of matching with the search topic entered by the user, and the accuracy of recalling the target information is low. Summary of the invention

[0003] In view of the above problems, the present application provides an information retrieval optimization method, device, electronic device and storage medium to at least solve the technical problem in the related art that the search engine cannot accurately obtain target information with a high degree of match with the search topic input by the user.

[0004] According to the first aspect of an embodiment of the present application, an information retrieval optimization method is provided, comprising: labeling a target web page of the above-mentioned website with attribute labels according to a knowledge graph corresponding to the website; wherein the above-mentioned knowledge graph includes content keywords under each content category in the field to which the above-mentioned website belongs and attribute labels for the relationship between content keywords; based on the attribute labels labeled for the above-mentioned target web page, updating the aggregation page of the above-mentioned website; based on the attribute labels of the web page, obtaining an aggregation page that matches the current search text from the aggregation page of the above-mentioned website.

[0005] According to the second aspect of an embodiment of the present application, an information retrieval optimization device is provided, and the information retrieval optimization device includes: a labeling unit, which is used to label attribute labels for the target web pages of the above-mentioned website according to the knowledge graph corresponding to the website; wherein the above-mentioned knowledge graph includes content keywords under each content category in the field to which the above-mentioned website belongs and attribute labels for the relationship between content keywords; an updating unit, which is used to update the aggregation page of the above-mentioned website based on the attribute labels annotated for the above-mentioned target web pages; a first acquisition unit, which is used to acquire an aggregation page matching the current search text from the aggregation pages of the above-mentioned website based on the attribute labels of the web pages.

[0006] According to a third aspect of an embodiment of the present application, a network device is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the information retrieval optimization method of the first aspect through the computer program.

[0007] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is further provided, in which a computer program is stored, wherein the computer program is configured to execute the information retrieval optimization method of the first aspect mentioned above when running.

[0008] In an embodiment of the present application, attribute labels are annotated for the target web pages of the above-mentioned website according to the knowledge graph corresponding to the website; wherein the above-mentioned knowledge graph includes attribute labels for content keywords and the relationship between content keywords under each content category in the field to which the above-mentioned website belongs; based on the attribute labels annotated for the above-mentioned target web pages, the aggregation page of the above-mentioned website is updated; based on the attribute labels of the web pages, the aggregation page matching the current search text is obtained from the aggregation page of the above-mentioned website; thus, the web pages in the website are annotated with attribute labels through the knowledge graph constructed by the category system class, and the aggregation page matching the current search text is obtained through the attribute labels; that is, compared with the prior art, the present application can not only make the content classification of the website more accurate, increase the search engine's understanding of the website content, but also improve the accuracy of the recalled information. Thereby, the technical problem in the related art that the search engine cannot accurately obtain the target information with a high degree of matching with the search topic input by the user can be solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Moreover, the same reference numerals are used throughout the drawings to represent the same components. In the drawings:

[0010] Figure 1 is a schematic diagram of an application environment of an optional information retrieval optimization method according to an embodiment of the present application;

[0011] Figure 2 is a schematic diagram of an application environment of an optional information retrieval optimization method according to an embodiment of the present application;

[0012] Figure 3 is a flowchart of an optional information retrieval optimization method according to an embodiment of the present application;

[0013] Figure 4 is a flowchart of another optional information retrieval optimization method according to an embodiment of the present application;

[0014] Figure 5 is a flowchart of another optional information retrieval optimization method according to an embodiment of the present application;

[0015] Figure 6is a flowchart of another optional information retrieval optimization method according to an embodiment of the present application;

[0016] Figure 7 This is an optional knowledge graph display schematic diagram according to an embodiment of the present application;

[0017] Figure 8 is a schematic diagram of a web page display of an optional information retrieval optimization method according to an embodiment of the present application;

[0018] Fig. 9 is a schematic diagram of a web page display of another optional information retrieval optimization method according to an embodiment of the present application;

[0019] Fig.10 is a web page display schematic diagram of another optional information retrieval optimization method according to an embodiment of the present application;

[0020] Fig.11 is a flow chart of an optional information retrieval optimization method according to an embodiment of the present application;

[0021] Fig.12 It is a structural schematic diagram of an information retrieval optimization device provided in an embodiment of the present application;

[0022] Fig.13 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only embodiments of a part of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention 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 invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] Optionally, according to one aspect of the embodiments of the present application, an information retrieval optimization method is provided. As an optional implementation, the information retrieval optimization method can be applied to, but is not limited to, Figure 1 In the application environment shown. The application environment may include, but is not limited to: a terminal device 102 for human-computer interaction with a user, a network 110, and a server 112. An information retrieval optimization application client is running in the terminal device 102. The terminal device 102 includes a display 108, a processor 106, and a memory 104. The display 108 is used to present the search text input by the user and the aggregated page of the website. The processor 106 is used to receive the search text sent by the user. The memory 104 is used to store the search text, the aggregated page of the website, the attribute tags of the web page, and the information retrieval optimization result. In addition, the server 112 includes a database 114 and a processing engine 116, and the database is used to store the search text, the aggregated page of the website, and the attribute tags of the web page. The processing engine 116 is used to annotate attribute labels for the target web pages of the above-mentioned website according to the knowledge graph corresponding to the website; wherein the above-mentioned knowledge graph includes content keywords under each content category in the field to which the above-mentioned website belongs and attribute labels for the relationship between content keywords; based on the attribute labels annotated for the above-mentioned target web pages, the aggregation page of the above-mentioned website is updated; based on the attribute labels of the web pages, the aggregation page that matches the current search text is obtained from the aggregation pages of the above-mentioned website.

[0026] The specific process is as follows: Assume that Figure 1 The terminal device 102 shown runs an information retrieval optimization client, and the server 112 executes steps S102-S104, and annotates attribute tags for the target webpage of the above website according to the knowledge graph corresponding to the website; wherein the above knowledge graph includes content keywords under each content category in the field to which the above website belongs and the relationship attribute tags between the content keywords; based on the attribute tags annotated for the above target webpage, the aggregation page of the above website is updated; the terminal device 102 executes step S106, and sends the search text input by the user to the server 112. The server 112 executes steps S108-S110, and based on the attribute tags of the webpage, obtains the aggregation page matching the current search text from the aggregation page of the above website; and sends the aggregation page matching the current search text to the terminal device 102. After receiving the aggregation page, the terminal device 102 displays the aggregation page matching the current search text.

[0027] In one or more embodiments, the above-mentioned dialogue processing method of the present application can be applied to Figure 2 In the application environment shown. Figure 2As shown, human-computer interaction can be performed between user 202 and user device 204. User device 204 includes memory 206 and processor 208. In this embodiment, user device 204 can refer to but not be limited to executing the operations performed by the above terminal device 102 to display the aggregated page matching the current search text.

[0028] Optionally, the terminal device 102 and the user device 204 include but are not limited to mobile phones, laptops, tablet computers, PDAs, MIDs (Mobile Internet Devices), desktop computers, smart TVs, etc. The information retrieval optimization client in the embodiment of the present application includes but is not limited to providing information retrieval optimization functions for video clients, instant messaging clients, browser clients, etc., using the information retrieval optimization method of the present application to interact with users, and receive user input information, etc. The above network may include but is not limited to: wired network, wireless network, wherein the wired network includes: local area network, metropolitan area network and wide area network, and the wireless network includes: Bluetooth, WIFI and other networks that realize wireless communication. The above server 112 includes a cloud server, which includes but is not limited to a private cloud server or a public cloud server. The above is only an example, and no limitation is made to this in the present embodiment.

[0029] The website content construction method in the related art is mainly carried out with the help of search engines, that is, by obtaining a large number of keywords and using the on-site search interface to batch generate aggregate pages, so as to achieve the purpose of attracting traffic. However, this crude content construction method often results in a large number of keywords with no relevant recall results due to the limited website content; moreover, the aggregate pages with random combinations of content will also reflect that the website as a whole has no clear theme structure, and the website's weight may also decrease accordingly.

[0030] In order to solve the above technical problems, as an optional implementation method, Figure 3 As shown, the embodiment of the present application provides an information retrieval optimization method, comprising the following steps:

[0031] S302, annotating attribute labels for target web pages of the above website according to the knowledge graph corresponding to the website; wherein the above knowledge graph includes content keywords under each content category in the field to which the above website belongs and relationship attribute labels between content keywords.

[0032] Specifically, in the embodiment of the present application, a knowledge base corresponding to the network is established through a knowledge graph, and concepts, entities, events and their relationships in the website content are described in the form of a graph. As shown in Table (1), the knowledge graph corresponding to the website is created through the content keywords under each content category in the field to which the website belongs and the relationship attribute labels between the content keywords.

[0033] Table (1)

[0034] Big Category First level category Secondary Category Third level category Product Elastic Computing Cloud Server ECS Elastic Computing Cloud Server Lightweight application server Elastic Computing Cloud Server …… Elastic Computing High Performance Computing Supercomputing clusters Elastic Computing High Performance Computing Batch Computing …… …… …… General Technology programming language rear end Java programming language rear end C++ programming language rear end … Software Development and Engineering operating system Linux Software Development and Engineering operating system Windows Software Development and Engineering operating system …… …… …… ……

[0035] As shown in Table (1), the content themes of the website are divided into two major categories: product category and general technology category. Each major category includes three levels of categories. This can establish a clear theme structure and category system for the website. This can not only improve the accuracy of search engines' understanding of website content, but also help the website obtain more accurate and high-quality traffic.

[0036] In the embodiment of the present application, the knowledge graph constructed by the above-mentioned category system is used to annotate attribute tags for web pages. For example, the target web page is a newly added web page in the website, and its content includes the solution to the Android exception when using the Kotlin library in the Java code. The attribute tags annotated for the target web page include "java", "kotlin library", "exception" and other tags. Or the attribute tags annotated include "programming language java", "kotlin library exception" and other tags.

[0037] S304: Based on the attribute tags marked for the target web page, update the aggregation page of the website.

[0038] Specifically, for example, there are 5 related articles before the aggregation page with tags such as "java", "kotlin library", and "exception", and the newly added web page is added to the aggregation page; when the user searches for "java's kotlin library exception", the recalled aggregation page includes 6 related articles including the newly added web page.

[0039] S306, based on the attribute tag of the web page, obtaining an aggregated page matching the current search text from the aggregated pages of the above website.

[0040] Specifically, in an embodiment of the present application, assuming that the current search text is "the solution to the android exception when using the kotlin library in the java code", after semantic recognition of the search text, the scope of this search is obtained as "java's kotlin library android exception", and web pages including attribute tags such as "java", "kotlin library", and "android exception" are combined into an aggregate page that matches the current search text. It should be noted that in this aggregate page, when the web page contains the above three attribute tags at the same time, it means that the web page has a higher weight and is displayed at the front of the aggregate page; when the web page contains two or one of the above attribute tags at the same time, it means that the web page has a relatively low weight and is displayed at the back of the aggregate page.

[0041] In an embodiment of the present application, attribute labels are annotated for the target web pages of the above-mentioned website according to the knowledge graph corresponding to the website; wherein the above-mentioned knowledge graph includes attribute labels for content keywords and the relationship between content keywords under each content category in the field to which the above-mentioned website belongs; based on the attribute labels annotated for the above-mentioned target web pages, the aggregation page of the above-mentioned website is updated; based on the attribute labels of the web pages, the aggregation page matching the current search text is obtained from the aggregation page of the above-mentioned website; thus, the web pages in the website are annotated with attribute labels through the knowledge graph constructed by the category system class, and the aggregation page matching the current search text is obtained through the attribute labels; that is, compared with the prior art, the present application can not only make the content classification of the website more accurate, increase the search engine's understanding of the website content, but also improve the accuracy of the recalled information. Thereby, the technical problem in the related art that the search engine cannot accurately obtain the target information with a high degree of matching with the search topic input by the user can be solved.

[0042] In one or more embodiments, Figure 4 As shown, the embodiment of the present application also provides an information retrieval optimization method, comprising the following steps:

[0043] S402, creating a corresponding category system according to the vocabulary of the field to which the website belongs, wherein the category system includes at least one primary content category;

[0044] S404, determining the content category to which the webpage content of the existing webpage on the website belongs according to the category system;

[0045] S406, identifying content keywords of the web page content under the content category to which it belongs, and identifying the relationship between the content keywords in the web page content, wherein the relationship between the content keywords is identified based on the grammar of the language used by the web page content;

[0046] S408: Create a knowledge graph corresponding to the website based on the identified content keywords and the relationship between the content keywords.

[0047] Specifically, in the embodiment of the present application, for example, if the current website is a website that provides medical services, a category system corresponding to the medical field is created based on the vocabulary of the medical concept field; if the current website is a website that provides cloud services, a category system corresponding to cloud technology is created based on the vocabulary of the cloud field; for example, if the current website is a website that provides cloud technology, as shown in Table (1), the category system includes three-level content categories. According to the category system, the content category to which the webpage content of the existing webpages on the website belongs is determined. For example, a webpage introducing Java content belongs to the third-level category, and its upper-level categories are backend, programming language, and general technology.

[0048] In one example, for example, a webpage with content including "Drug A can treat disease B" is identified based on the grammar recognition of the language used in the webpage content as "Drug A can treat disease B" with the subject "Drug A", the predicate "treatment", and the object "Disease B". The obtained keywords of the webpage content include "Disease A", "Drug B", "treatment", etc.

[0049] In another example, for example, a webpage containing content that Java is a programming language, based on the grammar recognition of the language used in the content of the webpage, it is recognized that the subject of "Java is a programming language" is "Java", the predicate is "is", and the object is "programming language". The content keywords of the webpage include "Java", "is", "programming language", etc. Similarly, the content keywords of other webpages of the website can be obtained. Based on the above content keywords of all webpages of the website and the relationship between the above content keywords, the following can be obtained: Figure 7 The knowledge graph corresponding to the website providing cloud services is shown.

[0050] S410, annotating attribute labels for target web pages of the website according to the knowledge graph corresponding to the website; wherein the knowledge graph includes content keywords under each content category in the field to which the website belongs and attribute labels for the relationship between the content keywords;

[0051] S412, updating the aggregation page of the website based on the attribute tag marked for the target web page;

[0052] S414, obtaining an aggregated page matching the current search text from the aggregated pages of the above website.

[0053] The above steps S410-S414 have been clearly explained in the previous text and will not be repeated here.

[0054] In one or more embodiments, Figure 5 As shown, the embodiment of the present application also provides an information retrieval optimization method, comprising the following steps:

[0055] S502, creating a corresponding category system according to the vocabulary of the field to which the website belongs, wherein the category system includes at least one first-level content category;

[0056] S504, determining the content category to which the webpage content of the existing webpage on the website belongs according to the category system;

[0057] S506, identifying content keywords of the web page content under the content category to which it belongs, and identifying the relationship between the content keywords in the web page content, wherein the relationship between the content keywords is identified based on the grammar of the language used by the web page content.

[0058] S508, identifying modifiers in the web page content based on the grammar of the language used by the web page content;

[0059] S510, creating a knowledge graph corresponding to the website based on the identified content keywords, the relationship between the content keywords and the modifiers.

[0060] Specifically, in the embodiments of the present application, the modifiers here include but are not limited to attributives, adverbials and complements in Chinese grammar. If the current website is a website that provides cloud services, a category system corresponding to cloud technology is created based on the cloud domain vocabulary. In one example, for example, a web page whose content includes "Keyword 1 Java is a programming language Keyword 2 Keyword 3", based on the grammatical recognition of the language used in the above web page content, it is recognized that the subject of "Keyword 1 Java is a programming language Keyword 2 Keyword 3" is "Java", the predicate is "is", and the object is "programming language". The attributive is "Keyword 1", the adverbial is "Keyword 2", and the complement is "Keyword 3", and the content keywords of the web page include the above-mentioned subject, predicate, object, attributive, adverbial, complement and other keywords. Similarly, the content keywords of other web pages of the website can be obtained. Based on the above-mentioned content keywords of all web pages of the website and the relationship between the above-mentioned content keywords, the following can be obtained: Figure 7 The knowledge graph corresponding to the website providing cloud services is shown.

[0061] S512, annotating attribute labels for target web pages of the above website according to the knowledge graph corresponding to the website; wherein the above knowledge graph includes content keywords under each content category in the field to which the above website belongs and relationship attribute labels between the content keywords;

[0062] S514, updating the aggregation page of the website based on the attribute tag marked for the target web page;

[0063] S516, based on the attribute tag of the web page, obtaining an aggregated page matching the current search text from the aggregated pages of the above website.

[0064] The above steps S502-S506, S512-S516 have been clearly explained in the previous text and will not be repeated here.

[0065] In one or more embodiments, Figure 6 As shown, the embodiment of the present application also provides an information retrieval optimization method, comprising the following steps:

[0066] S602, creating a corresponding category system according to the vocabulary of the field to which the website belongs, wherein the category system includes at least one first-level content category;

[0067] S604: Determine the content category to which the webpage content of the existing webpage on the website belongs according to the category system.

[0068] S606, training a label annotation model based on a preset data set, wherein the preset data set includes web page samples in the field to which the website belongs, and the web page samples are annotated with content keywords under the content category to which the web page samples belong and the relationship between the content keywords;

[0069] S608, using the trained labeling model to identify content keywords of the web page content under the content category to which it belongs, and to identify the relationship between the content keywords in the web page content;

[0070] S610: Create a knowledge graph corresponding to the website based on the identified content keywords and the relationship between the content keywords.

[0071] Specifically, in the embodiment of the present application, including but not limited to performing entity recognition and relationship extraction on a data set based on the trained label annotation model, the data set includes web page samples in the field to which the website belongs, and obtaining a plurality of triples consisting of entities and entity relationships; wherein each of the triples includes two entities and the relationship between the two entities;

[0072] The above-mentioned label annotation model is used to annotate the above-mentioned triples with labels, and the labels are adjusted according to the preset rules to obtain the entity table and entity relationship table of the field to which the above-mentioned website belongs; wherein the confidence of the labels in the above-mentioned entity table and entity relationship table are greater than or equal to the preset threshold, and the above-mentioned entity relationship table includes the above-mentioned relationship attribute labels; based on the above-mentioned entity table and entity relationship table, a knowledge graph corresponding to the field to which the above-mentioned website belongs is constructed. It should be noted that the above-mentioned trained label annotation model here includes but is not limited to a model obtained by a neural network related to NLP (Natural Language Processing).

[0073] S612, annotating attribute labels for target web pages of the above website according to the knowledge graph corresponding to the website; wherein the above knowledge graph includes content keywords under each content category in the field to which the above website belongs and relationship attribute labels between the content keywords;

[0074] S614, updating the aggregation page of the website based on the attribute tag marked for the target web page;

[0075] S616, based on the attribute tag of the web page, obtaining an aggregated page matching the current search text from the aggregated pages of the above website.

[0076] The above steps S602-S604, S612-S616 have been clearly explained in the previous text and will not be repeated here.

[0077] In one or more embodiments, updating the aggregation page of the website based on the attribute tag annotated for the target web page includes:

[0078] Determine whether the website has a tag that is the same as the attribute tag marked on the target webpage;

[0079] If it exists, determine the aggregation page corresponding to the attribute tag from the current aggregation page set of the website, and add the webpage information of the target webpage to the aggregation page;

[0080] If not, create an aggregate page including the web page information of the target web page.

[0081] Specifically, for example, the target web page includes attribute tags such as "java", "kotlin library", and "exception". When the above three attribute tags exist in the website, and there are 5 related articles before the aggregation page corresponding to these three attribute tags, the target web page is added to the aggregation page; when the user searches for "java's kotlin library exception", the recalled aggregation page includes the target web page and other 6 related articles. When at least one of the above three attribute tags does not exist in the website, an aggregation page including the web page information of the above target web page is created; for example, when the "kotlin library" attribute tag does not exist, before the above target web page is added, when the user searches for "kotlin library", no related articles can be recalled. After creating an aggregation page including the web page information of the above target web page, the aggregation page corresponding to the kotlin library can be recalled. It should be noted that the web page information here includes but is not limited to the link and subject name of the web page.

[0082] In one or more embodiments, the method of obtaining an aggregated page matching the current search text from the aggregated pages of the website based on the attribute tag of the web page includes:

[0083] Segmenting the current search text based on a preset segmentation model to obtain a segmentation result including at least one search term;

[0084] The above word segmentation results are matched with the attribute tags of the aggregation page of the website, and the aggregation page corresponding to the matched attribute tags is used as the aggregation page matching the above current search text.

[0085] For example, if the current search text entered by the user is "Can I run a virtual machine on an operating system 1V10 virtual machine?", the current search text is segmented based on the preset segmentation model, and a segmentation result including the search term "operating system 1V10 virtual machine" is obtained. After matching the above segmentation result with the attribute tag of the aggregation page of the website, the aggregation page corresponding to the matched attribute tag is used as the aggregation page that matches the above current search text. Figure 8 The aggregation page is shown. Click Figure 8 After linking the relevant content of the operating system 1 virtual machine running in Fig. 9 As shown in the figure, the aggregation page corresponding to the relevant content of the operating system 1 virtual machine is obtained. In the aggregation page, the first article has a high matching degree with the user's search text, indicating that the webpage has a high weight and is displayed at the front of the aggregation page; the following two articles have a relatively low matching degree with the user's search text, indicating that the webpage has a relatively low weight and is displayed at the back of the aggregation page. When the user clicks the link of the first article, he can go to the following page: Fig.10 The interface shown.

[0086] In one or more embodiments, the target webpage includes a plurality of attribute tags, and the information retrieval optimization method further includes:

[0087] Based on the current search text matching at least one of the multiple attribute tags, the target web page is recalled.

[0088] Specifically, in the embodiments of the present application, Fig.10 As shown, the lower part of the current web page is the attribute tag of the web page. There are multiple attribute tags. The web page can be recalled by any of the above tags. The above technical means can increase the accuracy of the target web page being recalled. By marking the attribute tags of the web page content and putting it on the relevant aggregation page, the content page can get multiple aggregation page tags, so that the search engine can understand the web page content more fully, and increase the chance of the web page content being exposed.

[0089] In one or more embodiments, the information retrieval optimization method further includes:

[0090] Obtain the historical search texts and historical browsing pages of users visiting the above websites;

[0091] According to the attribute labels corresponding to the historically browsed web pages and the historically searched texts, a user portrait of the visiting user is determined, and the user portrait is used to characterize characteristic attributes of the visiting user.

[0092] Specifically, in the embodiment of the present application, by obtaining the historical search text of the user who visited the website and the attribute tags corresponding to the historically browsed web pages, the user portrait of the visiting user can be obtained. By obtaining the user portrait, the user's search habits and interests can be obtained, based on which data reference can be provided for the user to search again, providing the user with more accurate target information.

[0093] Specifically, the above embodiment is used as an optional implementation method. Fig.11 As shown, the embodiment of the present application also provides an information retrieval optimization method, comprising the following steps:

[0094] 1. Receive new content published by users (new web pages);

[0095] 2. Tag (mark attribute tags) newly released content according to the knowledge graph of the technical field to which the current website belongs. The knowledge graph includes content keywords under each content category in the field to which the website belongs and the relationship attribute tags between content keywords;

[0096] 3. Determine whether the attribute tag marked with the newly released content already exists on the website. If it does, update the aggregation page (aggregation page corresponding to the attribute tag). If it does not exist, determine whether the marked attribute tag can be put online. If it can be put online, prepare to put the aggregation page online. If the attribute tag does not belong to the concept in the knowledge graph of the domain, it is determined that the attribute tag cannot be put online, and the current task is determined to be completed.

[0097] 4. Determine whether the recalled aggregation page has duplicate aggregations. If so, determine that the task is completed; if not, update the aggregation page.

[0098] Through the above technical solution of this application, it is possible to achieve multi-level content aggregation of the website, allowing search engines to obtain more comprehensive article label (classification) information, increasing the possibility of web page content being recalled. Compared with related technologies, this application also has the following technical effects: 1) Based on the knowledge graph, the label recognition rate of SEO content construction in sentence scenarios such as subjectless, elliptical sentences, and aliases is improved, and the accuracy of content annotation labels is improved; 2) The knowledge graph obtained by multi-level content division of the vocabulary in the field can obtain a clear entity relationship graph, making content classification more accurate, increasing the search engine's understanding of the content, and increasing the possibility of related web page content being recalled.

[0099] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0100] According to another aspect of the embodiment of the present application, an information retrieval optimization device for implementing the above-mentioned information retrieval optimization method is also provided. Fig.12 As shown, the device comprises:

[0101] The labeling unit 1202 is used to label the target web page of the above website with attribute labels according to the knowledge graph corresponding to the website; wherein the above knowledge graph includes content keywords under each content category in the field to which the above website belongs and the relationship attribute labels between the content keywords;

[0102] An updating unit 1204, configured to update the aggregation page of the website based on the attribute tag annotated for the target web page;

[0103] The first acquisition unit 1206 is used to acquire, based on the attribute tag of the web page, an aggregated page matching the current search text from the aggregated pages of the above website.

[0104] In an embodiment of the present application, attribute labels are annotated for the target web pages of the above-mentioned website according to the knowledge graph corresponding to the website; wherein the above-mentioned knowledge graph includes attribute labels for content keywords and the relationship between content keywords under each content category in the field to which the above-mentioned website belongs; based on the attribute labels annotated for the above-mentioned target web pages, the aggregation page of the above-mentioned website is updated; based on the attribute labels of the web pages, the aggregation page matching the current search text is obtained from the aggregation page of the above-mentioned website; thus, the web pages in the website are annotated with attribute labels through the knowledge graph constructed by the category system class, and the aggregation page matching the current search text is obtained through the attribute labels; that is, compared with the prior art, the present application can not only make the content classification of the website more accurate, increase the search engine's understanding of the website content, but also improve the accuracy of the recalled information. Thereby, the technical problem in the related art that the search engine cannot accurately obtain the target information with a high degree of matching with the search topic input by the user can be solved.

[0105] In one or more embodiments, the information retrieval optimization device further includes:

[0106] A creation unit, used to create a corresponding category system according to the vocabulary of the field to which the website belongs, wherein the category system includes at least one primary content category;

[0107] A first determining unit is used to determine the content category to which the webpage content of the existing webpage of the website belongs according to the category system;

[0108] A first recognition unit is used to recognize content keywords of the web page content under the content category to which it belongs, and to recognize the relationship between the content keywords in the web page content, wherein the relationship between the content keywords is recognized based on the grammar of the language used by the web page content;

[0109] The first creation unit is used to create a knowledge graph corresponding to the above-mentioned website based on the identified content keywords and the relationship between the above-mentioned content keywords.

[0110] In one or more embodiments, the information retrieval optimization device further includes:

[0111] A second recognition unit, configured to recognize modifiers in the web page content based on the grammar of the language used by the web page content;

[0112] The second creation unit is used to create a knowledge graph corresponding to the above-mentioned website based on the identified above-mentioned content keywords, the relationship between the above-mentioned content keywords and the above-mentioned modifiers.

[0113] In one or more embodiments, the information retrieval optimization device further includes:

[0114] A training unit, used for training a label annotation model based on a preset data set, wherein the preset data set includes web page samples in the field to which the website belongs, and the web page samples are annotated with content keywords under the content category to which the web page samples belong and the relationship between the content keywords;

[0115] The identification unit is used to identify the content keywords of the web page content under the content category to which it belongs by using the trained label annotation model, and to identify the relationship between the content keywords in the web page content.

[0116] In one or more embodiments, the updating unit 1204 includes:

[0117] A determination module, used to determine whether the website has a label identical to the attribute label marked on the target web page;

[0118] A determination module, used to determine the aggregation page corresponding to the attribute tag from the current aggregation page set of the website, and add the webpage information of the target webpage to the aggregation page;

[0119] The creation module is used to create an aggregate page including the web page information of the target web page.

[0120] In one or more embodiments, the acquisition unit 1206 includes:

[0121] A word segmentation module, used to segment the current search text based on a preset word segmentation model to obtain a word segmentation result including at least one search word;

[0122] The matching module is used to match the above word segmentation results with the attribute tags of the aggregation page of the website, and use the aggregation page corresponding to the matched attribute tag as the aggregation page matching the above current search text.

[0123] In one or more embodiments, the target webpage includes a plurality of attribute tags, and the information retrieval optimization device further includes:

[0124] The recall unit is used to recall the target web page based on the matching between the current search text and at least one tag among the multiple attribute tags.

[0125] In one or more embodiments, the information retrieval optimization device further includes:

[0126] A second acquisition unit is used to acquire the historical search texts and historical browsed web pages of the users visiting the above website;

[0127] The second determining unit is used to determine the user portrait of the visiting user according to the attribute tags corresponding to the historical search text and the historical browsed web pages, wherein the user portrait is used to characterize the characteristic attributes of the visiting user.

[0128] According to another aspect of the embodiment of the present application, an electronic device for implementing the above-mentioned information retrieval optimization method is also provided. The electronic device may be Figure 1 The terminal device or server shown in the figure includes, but is not limited to, a cloud server. This embodiment is described by taking the electronic device as a server as an example. Fig.13 As shown, the electronic device includes a memory 1302 and a processor 1304. The memory 1302 stores a computer program, and the processor 1304 is configured to execute the steps in any of the above method embodiments through the computer program.

[0129] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0130] S1, annotating attribute labels for target web pages of the above website according to the knowledge graph corresponding to the website; wherein the above knowledge graph includes content keywords under each content category in the field to which the above website belongs and attribute labels for the relationship between the content keywords;

[0131] S2, updating the aggregation page of the above website based on the attribute tags marked for the above target web page;

[0132] S3, based on the attribute tags of the web pages, obtains the aggregated pages matching the current search text from the aggregated pages of the above websites.

[0133] Among them, the memory 1302 can be used to store software programs and modules, such as the program instructions / modules corresponding to the information retrieval optimization method and device in the embodiment of the present application, and the processor 1304 executes various functional applications and data processing by running the software programs and modules stored in the memory 1302, that is, realizing the above-mentioned information retrieval optimization method. The memory 1302 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1302 may further include a memory remotely arranged relative to the processor 1304, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. Among them, the memory 1302 may be specifically used, but not limited to, for storing the aggregated pages of the website, and the attribute tags annotated by the web page.

[0134] As an example, Fig.13 As shown, the memory 1302 may include, but is not limited to, the labeling unit 1202, the updating unit 1204, and the first obtaining unit 1206 in the information retrieval optimization device. In addition, it may also include, but is not limited to, other module units in the information retrieval optimization device, which will not be described in detail in this example.

[0135] Optionally, the transmission device 1306 is used to receive or send data via a network. Specific examples of the network may include a wired network and a wireless network. In one example, the transmission device 1306 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 1306 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0136] In addition, the electronic device mentioned above further includes: a connection bus 1308, which is used to connect various module components in the electronic device mentioned above.

[0137] In other embodiments, the network device may be a node in a distributed system, wherein the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting the multiple nodes through network communication. Among them, the nodes may form a peer-to-peer (P2P) network, and any form of computing device, such as a server, terminal or other electronic device, may become a node in the blockchain system by joining the peer-to-peer network.

[0138] In one or more embodiments, the present application also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the above-mentioned information retrieval optimization method. Wherein, the computer program is configured to execute the steps of any of the above-mentioned method embodiments when running.

[0139] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0140] S1, annotating attribute labels for target web pages of the above website according to the knowledge graph corresponding to the website; wherein the above knowledge graph includes content keywords under each content category in the field to which the above website belongs and attribute labels for the relationship between the content keywords;

[0141] S2, updating the aggregation page of the above website based on the attribute tags marked for the above target web page;

[0142] S3, based on the attribute tags of the web pages, obtains the aggregated pages matching the current search text from the aggregated pages of the above websites.

[0143] Optionally, in this embodiment, a person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing hardware related to the terminal device through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0144] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0145] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on such understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which can be personal computers, servers or network devices, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention.

[0146] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0147] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0148] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0149] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0150] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

[0151] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

Claims

1. An information retrieval optimization method, characterized in that: The method comprises: According to the knowledge graph corresponding to the website, attribute labels are marked for the target web pages of the website; wherein the knowledge graph includes content keywords under each content category in the field to which the website belongs and attribute labels for the relationship between content keywords; Based on the attribute tags marked for the target web page, updating the aggregation page of the website; Based on the attribute tags of the web pages, an aggregated page matching the current search text is obtained from the aggregated pages of the website.

2. The method according to claim 1, characterized in that Before labeling the target webpage of the website with attribute labels according to the knowledge graph corresponding to the website, the method further includes: Creating a corresponding category system according to the vocabulary of the field to which the website belongs, wherein the category system includes at least one primary content category; Determining the content category to which the webpage content of the existing webpage of the website belongs according to the category system; Identifying content keywords of the webpage content under the content category to which it belongs, and identifying the relationship between the content keywords in the webpage content, wherein the relationship between the content keywords is identified based on the grammar of the language used by the webpage content; Based on the identified content keywords and the relationship between the content keywords, a knowledge graph corresponding to the website is created.

3. The method according to claim 2, characterized in that The method further comprises: Identifying modifiers in the webpage content based on the grammar of the language used by the webpage content; Based on the identified content keywords, the relationships between the content keywords, and the modifiers, a knowledge graph corresponding to the website is created.

4. The method according to claim 2 or 3, characterized in that: The method further comprises: Training a label annotation model based on a preset data set, wherein the preset data set includes web page samples in the field to which the website belongs, and the web page samples are annotated with content keywords under the content category to which the web page samples belong and the relationship between the content keywords; The trained labeling model is used to identify content keywords of the web page content under the content category to which it belongs, and to identify the relationship between content keywords in the web page content.

5. The method according to any one of claims 1 to 3, characterized in that: The updating of the aggregation page of the website based on the attribute tag marked for the target web page includes: Determine whether the website has a tag that is the same as the attribute tag marked on the target webpage; If it exists, determine the aggregation page corresponding to the attribute tag from the current aggregation page set of the website, and add the webpage information of the target webpage to the aggregation page; If not, an aggregate page including the web page information of the target web page is created.

6. The method according to any one of claims 1 to 3, characterized in that: Based on the attribute tags of the web pages, obtaining an aggregated page matching the current search text from the aggregated pages of the website includes: Segmenting the current search text based on a preset segmentation model to obtain a segmentation result including at least one search term; The word segmentation result is matched with the attribute tag of the aggregation page of the website, and the aggregation page corresponding to the matched attribute tag is used as the aggregation page matching the current search text.

7. The method according to any one of claims 1 to 3, characterized in that: The target webpage includes a plurality of attribute tags, and the method further includes: The target web page is recalled based on that the current search text matches at least one tag among the multiple attribute tags.

8. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Obtaining historical search texts and historical browsing web pages of users visiting the website; A user portrait of the visiting user is determined according to the attribute tags corresponding to the historically browsed web pages and the historically searched texts, and the user portrait is used to characterize characteristic attributes of the visiting user.

9. An information retrieval optimization device, characterized in that: The device comprises: A labeling unit, used to label the target web page of the website with attribute labels according to the knowledge graph corresponding to the website; wherein the knowledge graph includes content keywords under each content category in the field to which the website belongs and the relationship attribute labels between the content keywords; An updating unit, configured to update the aggregation page of the website based on the attribute tag annotated for the target web page; The first acquisition unit is used to acquire, based on the attribute tag of the web page, an aggregated page matching the current search text from the aggregated pages of the website.

10. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method according to any one of claims 1 to 8.

Images