Search engine optimization article generation method and device, electronic equipment and storage medium

Abstract

The invention discloses a search engine optimization article generation method and device, electronic equipment and a storage medium, and relates to the technical field of information processing. The method comprises the steps of obtaining a target keyword and at least one website address input by an operation interface; respectively accessing each website address, crawling article content containing the target keyword in a webpage of the website address, and retrieving a historical document associated with the target keyword in a pre-constructed knowledge base; and inputting the article content and the historical document into a pre-trained large language model to obtain a search engine optimization article with the same architecture as the historical document. By the adoption of the method, the newest expression mode can be quickly known, current event hotspots can be closely followed, the exposure degree can be increased, the uniqueness can be kept, manual writing is not needed, the response speed is higher, and the processing efficiency is greatly improved.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to a method, device, electronic device and storage medium for generating search engine optimization articles. Background Art

[0002] With the rapid development of the Internet, online articles such as news reports, entertainment news and product promotions have grown exponentially, and the content is diverse, so search engines can quickly find the required results. However, search engines will sort the search results, and manually written online articles have a fixed style and single wording, which will affect ranking and exposure, and the creation process is time-consuming and labor-intensive, and has limitations. Summary of the invention

[0003] In view of the above-mentioned defects or deficiencies in the related art, it is desired to provide a search engine optimization article generation method, device, electronic device and storage medium, which can automatically generate search engine optimization articles and improve processing efficiency and exposure.

[0004] In a first aspect, the present application provides a method for generating a search engine optimization article, the method comprising:

[0005] Obtaining a target keyword and at least one website address inputted in the operation interface;

[0006] Access each of the website addresses respectively, crawl the article content containing the target keyword in the web page of the website address, and retrieve the historical documents associated with the target keyword in the pre-built knowledge base;

[0007] The article content and the historical document are input into a pre-trained large language model to obtain a search engine optimization article with the same architecture as the historical document.

[0008] Optionally, in some embodiments of the present application, the large language model includes a first large language sub-model and a second large language sub-model connected to each other, and the first large language sub-model can generate an intermediate document with the same architecture as the historical document according to the article content and the historical document,

[0009] The second largest language sub-model can score the intermediate document, and when the score is less than a preset threshold, feed back the score and modification information of the intermediate document to the first largest language sub-model, until the score corresponding to the intermediate document modified by the first largest language sub-model is greater than or equal to the preset threshold, and the modified intermediate document is used as the search engine optimization article.

[0010] Optionally, in some embodiments of the present application, when scoring the intermediate document, the second largest language sub-model may sort out topics, check the real-time ranking of the target keyword, and analyze search engine page parameters.

[0011] Optionally, the website address in some embodiments of the present application includes link and path keywords.

[0012] Optionally, in some embodiments of the present application, crawling the article content containing the target keyword in the web page of the website address includes: locating the article title in the web page of the website address according to the target keyword, if the article title is an empty value, taking the line break after the target keyword as a reference, and using the content before the line break as the article content.

[0013] Optionally, the method in some embodiments of the present application further includes: filtering unreadable parts of the article content.

[0014] In a second aspect, the present application provides a device for generating a search engine optimization article, the device comprising:

[0015] An acquisition module, used to acquire a target keyword and at least one website address inputted from an operation interface;

[0016] A processing module, used to visit each of the website addresses respectively, crawl the article content containing the target keyword in the web page of the website address, and retrieve the historical documents associated with the target keyword in the pre-built knowledge base;

[0017] A generation module is used to input the article content and the historical document into a pre-trained large language model to obtain a search engine optimization article with the same architecture as the historical document.

[0018] Optionally, in some embodiments of the present application, the large language model includes a first large language sub-model and a second large language sub-model connected to each other, and the first large language sub-model can generate an intermediate document with the same architecture as the historical document according to the article content and the historical document,

[0019] The second largest language sub-model can score the intermediate document, and when the score is less than a preset threshold, feed back the score and modification information of the intermediate document to the first largest language sub-model, until the score corresponding to the intermediate document modified by the first largest language sub-model is greater than or equal to the preset threshold, and the modified intermediate document is used as the search engine optimization article.

[0020] In a third aspect, the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the instruction, the program, the code set or the instruction set is loaded and executed by the processor to implement the steps of the search engine optimization article generation method described in any one of the first aspects.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the search engine optimization article generation method described in any one of the first aspects.

[0022] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0023] The embodiments of the present application provide a method, device, electronic device and storage medium for generating search engine optimization articles. The target keywords are used to crawl the article content containing the target keywords in the public web pages of the website addresses, so that the latest expressions can be quickly understood, the hot topics of current affairs can be followed, and the exposure can be increased. Then, the historical documents retrieved from the integrated knowledge base can be used to automatically generate search engine optimization articles with the same structure as the historical documents through a pre-trained large language model, so as to maintain uniqueness. At the same time, no manual writing is required, the response speed is faster, and the processing efficiency is greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 A schematic diagram of a flow chart of a method for generating a search engine optimization article provided in an embodiment of the present application;

[0026] Figure 2 A structural block diagram of a search engine optimization article generation device provided in an embodiment of the present application;

[0027] Figure 3 A structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0030] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. Figures 1 to 3 The search engine optimization article generation method, device, electronic device and storage medium provided in the embodiments of the present application are described in detail.

[0031] Please refer to Figure 1 , which is a flow chart of a method for generating a search engine optimization article provided in an embodiment of the present application, the method specifically comprises the following steps:

[0032] S101, obtaining a target keyword and at least one website address inputted in an operation interface.

[0033] Exemplarily, in actual use, the user can enter the target keywords and website addresses through the operation interface. For example, the target keywords include but are not limited to product names and product attributes, and the website address includes but is not limited to links and path keywords, where the link can be a competitor's website URL (Uniform Resource Locator), a blog URL, and a reference SEO (Search Engine Optimization) article URL, and the path keyword can be the common keyword obtained by the user by observing all blog URLs of the target website. The advantage of this setting is that it is easy to quickly and accurately crawl the required content. If the user does not enter the common keyword, the default keywords such as blog and article are used.

[0034] S102, visiting each website address respectively, crawling the article content containing the target keyword in the web page of the website address, and searching the historical documents associated with the target keyword in the pre-built knowledge base.

[0035] Exemplarily, for example, in the process of crawling the content of articles containing target keywords, the embodiment of the present application can locate the title of the article in the web page of the website address according to the target keyword. If the article title is null, the line break after the target keyword is used as the basis, and the content before the line break is used as the article content. That is to say, when there are multiple target keywords, the line break after the last target keyword can be used as the basis, and if the article title is not null, the content after the article title and before the line break is used as the article content, for example, the article content is obtained through the Coze built-in browser plug-in and stored in the dictionary. Furthermore, the embodiment of the present application can also filter the unreadable part of the article content, such as the unreadable part is the line break, thereby reducing the amount of data and facilitating the subsequent rapid processing of the article content. For another example, the pre-built knowledge base can be a company's own knowledge base containing product and operation documents, or it can be a Google and Bing search library, etc.

[0036] S103, inputting the article content and historical documents into a pre-trained large language model to obtain a search engine optimization article with the same architecture as the historical document.

[0037] Exemplarily, the large language model in the embodiment of the present application includes a first large language sub-model and a second large language sub-model that are interconnected. The first large language sub-model can generate an intermediate document with the same architecture as the historical document based on the article content and historical documents, which can be Chat GPT-4, and the second large language sub-model can score the intermediate document and, when the score is less than a preset threshold, feedback the score and modification information of the intermediate document to the first large language sub-model until the score corresponding to the intermediate document modified by the first large language sub-model is greater than or equal to the preset threshold, and the modified intermediate document is used as a search engine optimization article.

[0038] Furthermore, when scoring intermediate documents, the second largest language sub-model can sort out topics, view the real-time ranking of target keywords, and analyze search engine page parameters. For example, through SEMrush's Keyword Magic Tool or Organic Research report, topics can be sorted out and core keywords that can be written into search engine optimization articles can be found. For another example, the Organic Research function can be used to view the real-time ranking and ranking changes of target keywords, which helps to identify which keywords perform well and which need to be optimized. The Keyword Gap function can be used to analyze the keyword coverage gap between your content page and the competitor's page, find out the uncovered keywords, and optimize them into your own content. For example, the Keyword Overview function can be used to analyze the target keyword's weight on the search engine page, the referral domain name, and the traffic valuation information, thereby determining the planning value of the target keyword. The Domain Overview, Traffic Analytics, and Organic Research functions can be used to view the basic information of the search website, the natural search channel data, and the creation of a competitor comparison view. The Backlink Analytics function can be used to analyze and evaluate the quality of backlinks. In addition, by analyzing and improving the loading speed, mobile friendliness, and ease of use of the search engine page, the user experience can be enhanced and the exposure can be further improved. In short, the embodiment of the present application uses the second largest language sub-model to evaluate the quality of the intermediate document from the dimensions of readability, originality, article tone, and search engine optimization capabilities. For example, the score range is 1 to 10 points. When the score corresponding to the intermediate document modified by the first largest language sub-model is greater than 9 points, the search engine optimization article is output and stored in the database.

[0039] The search engine optimization article generation method provided in the embodiment of the present application utilizes the target keyword to crawl the article content containing the target keyword in the public web page of the website address, so as to quickly understand the latest expression methods, keep up with the current hot topics, increase exposure, and then integrate the historical documents retrieved from the knowledge base, and automatically generate the search engine optimization article with the same structure as the historical document through the pre-trained large language model, so as to maintain the uniqueness, and at the same time, no manual writing is required, the response speed is faster, and the processing efficiency is greatly improved.

[0040] Based on the above embodiments, the present application provides a search engine optimization article generation device. The search engine optimization article generation device 100 can be applied to Figure 1 In the search engine optimization article generation method of the corresponding embodiment. Please refer to Figure 2 , the search engine optimization article generating device 100 comprises:

[0041] An acquisition module 101 is used to acquire a target keyword and at least one website address inputted from an operation interface;

[0042] Processing module 102, for accessing each website address respectively, crawling the article content containing the target keyword in the web page of the website address, and searching the historical documents associated with the target keyword in the pre-built knowledge base;

[0043] The generation module 103 is used to input the article content and the historical document into a pre-trained large language model to obtain a search engine optimization article with the same architecture as the historical document.

[0044] Optionally, in some embodiments of the present application, the large language model includes a first large language sub-model and a second large language sub-model connected to each other, and the first large language sub-model can generate an intermediate document with the same architecture as the historical document according to the article content and the historical document.

[0045] The second largest language sub-model can score the intermediate document, and when the score is less than a preset threshold, feedback the score and modification information of the intermediate document to the first largest language sub-model, until the score corresponding to the intermediate document modified by the first largest language sub-model is greater than or equal to the preset threshold, and the modified intermediate document is used as a search engine optimization article.

[0046] Optionally, in some embodiments of the present application, when scoring intermediate documents, the second largest language sub-model may sort out topics, check the real-time ranking of target keywords, and analyze search engine page parameters.

[0047] Optionally, in some embodiments of the present application, the website address includes links and path keywords.

[0048] Optionally, in some embodiments of the present application, the processing module 102 is specifically used to locate the article title in the web page of the website address according to the target keyword. If the article title is empty, the line break after the target keyword is used as the basis, and the content before the line break is used as the article content.

[0049] Optionally, in some embodiments of the present application, the processing module 102 also filters the unreadable part of the article content.

[0050] It should be noted that, for the description of the same steps and the same contents in this embodiment as those in other embodiments, reference can be made to the description in other embodiments and will not be repeated here.

[0051] The SEO article generation device provided in the embodiment of the present application utilizes the target keyword to crawl the article content containing the target keyword in the public web page of the website address, so as to quickly understand the latest expression methods, keep up with the current hot topics, increase exposure, and then integrate the historical documents retrieved from the knowledge base, and automatically generate the SEO article with the same structure as the historical document through the pre-trained large language model, so as to maintain the uniqueness, and at the same time, it does not need manual writing, the response speed is faster, and the processing efficiency is greatly improved.

[0052] Based on the above embodiments, the present application provides an electronic device. Figure 3 The electronic device 200 may include a processor 201 and a memory 202. The memory 202 stores at least one instruction, at least one program, code set or instruction set, which is loaded and executed by the processor 201 to implement Figure 1 The steps of the search engine optimization article generation method in the corresponding embodiment.

[0053] As another aspect, the present application provides a computer-readable storage medium for storing program code, the program code for executing the aforementioned Figure 1 Any implementation of the search engine optimization article generation method in the corresponding embodiment.

[0054] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0055] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules 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 an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms. The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0056] In addition, each functional module in each embodiment of the present application may be integrated into a processing unit, or each module may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium.

[0057] Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the whole 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 a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the search engine optimization article generation method of each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0058] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0059] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for generating search engine optimization articles, characterized in that: The method comprises: Obtaining a target keyword and at least one website address inputted in the operation interface; Access each of the website addresses respectively, crawl the article content containing the target keyword in the web page of the website address, and retrieve the historical documents associated with the target keyword in the pre-built knowledge base; The article content and the historical document are input into a pre-trained large language model to obtain a search engine optimization article with the same architecture as the historical document.

2. The method according to claim 1, characterized in that The large language model includes a first large language sub-model and a second large language sub-model connected to each other, wherein the first large language sub-model can generate an intermediate document having the same architecture as the historical document according to the content of the article and the historical document, The second largest language sub-model can score the intermediate document, and when the score is less than a preset threshold, feed back the score and modification information of the intermediate document to the first largest language sub-model, until the score corresponding to the intermediate document modified by the first largest language sub-model is greater than or equal to the preset threshold, and the modified intermediate document is used as the search engine optimization article.

3. The method according to claim 2, characterized in that When scoring the intermediate document, the second largest language sub-model can sort out topics, check the real-time ranking of the target keyword, and analyze search engine page parameters.

4. The method according to any one of claims 1 to 3, characterized in that The website address includes links and path keywords.

5. The method according to claim 4, characterized in that The crawling of the article content containing the target keyword in the web page of the website address includes: locating the article title in the web page of the website address according to the target keyword, and if the article title is a null value, taking the line break after the target keyword as a reference, and taking the content before the line break as the article content.

6. The method according to claim 5, characterized in that The method further includes: filtering unreadable parts of the article content.

7. A device for generating articles for search engine optimization, characterized in that: The device comprises: An acquisition module, used to acquire a target keyword and at least one website address inputted from an operation interface; A processing module, used to visit each of the website addresses respectively, crawl the article content containing the target keyword in the web page of the website address, and retrieve the historical documents associated with the target keyword in the pre-built knowledge base; A generation module is used to input the article content and the historical document into a pre-trained large language model to obtain a search engine optimization article with the same architecture as the historical document.

8. The device according to claim 7, characterized in that The large language model includes a first large language sub-model and a second large language sub-model connected to each other, wherein the first large language sub-model can generate an intermediate document having the same architecture as the historical document according to the content of the article and the historical document, The second largest language sub-model can score the intermediate document, and when the score is less than a preset threshold, feed back the score and modification information of the intermediate document to the first largest language sub-model, until the score corresponding to the intermediate document modified by the first largest language sub-model is greater than or equal to the preset threshold, and the modified intermediate document is used as the search engine optimization article.

9. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set or instruction set, and the instruction, the program, the code set or the instruction set is loaded and executed by the processor to implement the steps of the search engine optimization article generation method described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the search engine optimization article generation method described in any one of claims 1 to 6.

Images