Page parameter generation method and page parameter generation device for webpage

Abstract

The invention provides a page parameter generation method and device for a webpage, and the method comprises the steps: obtaining a target page, and determining a prompt word template corresponding to the target page from a preset template library; obtaining page content information corresponding to the target page, and generating a cue word of the target page based on the page content information and the cue word template; and inputting the cue word into a pre-trained large language model, and generating a page parameter corresponding to the target page. By means of the method and device, the generated page parameters are more accurate and normative, manual participation is reduced, and the efficiency and accuracy of page parameter generation are greatly improved.

Description

Technical Field

[0001] This application relates to network data processing technology, and in particular, to a method and device for generating page parameters of a web page. Background Art

[0002] With the rapid development of Internet technology, search engines have become one of the main ways for users to obtain information. SEO (Search Engine Optimization), as a technical means to improve the natural ranking of a website in search engines, is crucial for enhancing the visibility and traffic of the website. To ensure that search engines can quickly and accurately crawl and index web page content, website administrators usually need to configure corresponding SEO information for each page, including titles, descriptions, and keywords, etc. These information not only help search engines understand the page content but also directly affect the ranking of the page in search results.

[0003] However, currently, the generation of these SEO information mainly relies on manual operations, that is, professionals summarize and refine according to the page content. This method not only has a large workload and low efficiency but also results in uneven quality of the generated SEO information due to differences in the refining capabilities and experiences of different personnel. In addition, with the rapid update and iteration of Internet information, the manual generation of SEO information is difficult to meet the requirements of real-time and consistency, thus affecting the overall optimization effect and user experience of the website. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method and device for generating page parameters of a web page. By combining a large language model and a prompt template, it realizes the automatic generation of page parameters of a web page. The generated page parameters are more accurate and standardized, reducing manual participation and greatly improving the efficiency and accuracy of page parameter generation.

[0005] In a first aspect, an embodiment of this application provides a method for generating page parameters of a web page. The page parameter generation method includes: Obtain a target page and determine the prompt template corresponding to the target page from a preset template library; Obtain the page content information corresponding to the target page, and generate a prompt for the target page based on the page content information and the prompt template; Input the prompt into a pre-trained large language model to generate the page parameters corresponding to the target page.

[0006] Further, the obtaining of the page content information corresponding to the target page includes: When the target page is a picture - type page, input the first picture in the target page into a picture recognition model, and determine the first picture content information output by the picture recognition model as the page content information corresponding to the target page; and / or, When the target page is a video - type page, input the video in the target page into a video recognition model, and determine the video content information output by the video recognition model as the page content information corresponding to the target page, or obtain at least one second picture in the video, input each second picture into the picture recognition model, and determine the second picture content information output by the picture recognition model as the page content information corresponding to the target page; and / or, When the target page is a description - type page or a Q&A - type page, identify the page elements in the target page to obtain the page content information corresponding to the target page, or obtain the parameter value corresponding to the target page through the server, and obtain the page content information corresponding to the target page based on the parameter value.

[0007] Further, generating the prompt word for the target page based on the page content information and the prompt word template includes: Determine at least one hot - word information from the page content information; Obtain at least one hot - spot information, match at least one hot - word information with at least one hot - spot information, and determine at least one target hot - word information; Generate the prompt word based on the prompt word template, the page content information, and at least one target hot - word information.

[0008] Further, determining at least one hot - word information from the page content information includes: Perform word segmentation on the page content information to obtain at least one phrase, and / or, for a preset number of characters, obtain at least one phrase corresponding to the preset number of characters from the page content information, and determine the occurrence times of each phrase; Sort at least one phrase based on the occurrence times, and determine a preset number of phrases from the sorting result as the hot - word information; Or, For each phrase, when the occurrence times of the phrase is greater than or equal to a preset threshold, then determine the phrase as the hot - word information.

[0009] Further, obtain the hot - spot information through the following steps: Determine the hot - spot information according to the search hot - spots of the target search engine in the historical time period; and / or, Obtain the search hotspots of the target search engine within a historical time period; Determine the hotspot information based on the changing trend of the search popularity of the search hotspots within the historical time period.

[0010] Further, before obtaining the target page, the page parameter generation method further includes: Obtain the page generation requirements, and determine the corresponding target page template from a plurality of preset page generation templates based on the page generation requirements; Determine the corresponding content generation model based on the content requirements in the page generation requirements, and use the content generation model to generate the target content information corresponding to the page generation requirements; Generate a first page based on the target page template and the target content information, and determine the first page as the target page.

[0011] Further, determining the prompt word template corresponding to the target page from the preset template library includes: Obtain the page information of the target page; wherein, the page information is at least one of the page type information, search engine information, and style preference information of the target page; Determine the prompt word template corresponding to the page information from the preset templates in the preset template library based on the page information.

[0012] Further, determining the prompt word template corresponding to the target page from the preset template library includes: Obtain the search optimization results of at least one preset template in the preset template library for historical pages; Determine the preset template with the best search optimization effect for historical pages as the prompt word template.

[0013] Further, the preset template library is constructed through the following steps: Generate at least one reference prompt word based on the page parameters of at least one first target reference page; Generate preset templates based on the reference prompt words to form the preset template library; and / or, Generate reference page parameters for a second target reference page based on at least one reference prompt word; Determine at least one target reference prompt word based on the search optimization results of the reference page parameters of the second target reference page; Generate preset templates based on the target reference prompt words to form the preset template library.

[0014] In a second aspect, an embodiment of the present application further provides a page parameter generation device for a web page, and the page parameter generation device includes: A template determination module, configured to obtain a target page and determine a prompt template corresponding to the target page from a preset template library; A prompt generation module, configured to obtain page content information corresponding to the target page and generate a prompt for the target page based on the page content information and the prompt template; A page parameter generation module, configured to input the prompt into a pre-trained large language model to generate page parameters corresponding to the target page.

[0015] A method and a device for generating page parameters of a web page provided by an embodiment of the present application. First, obtain a target page and determine a prompt template corresponding to the target page from a preset template library; then, obtain page content information corresponding to the target page and generate a prompt for the target page based on the page content information and the prompt template; finally, input the prompt into a pre-trained large language model to generate page parameters corresponding to the target page.

[0016] By combining a large language model and a prompt template, the present application realizes the automatic generation of page parameters of a web page. Generate a prompt for the target page according to the prompt template, and utilize the strong generalization ability and language understanding ability of the large language model to generate corresponding page parameters based on the prompt. In this way, the generated page parameters are more accurate and standardized, reducing manual participation and greatly improving the efficiency and accuracy of page parameter generation.

[0017] To make the above objects, features, and advantages of the present application more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, makes a detailed description as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] To more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 A flowchart of a method for generating page parameters of a web page provided by an embodiment of the present application; Figure 2 A schematic structural diagram of a device for generating page parameters of a web page provided by an embodiment of the present application; Figure 3 A schematic structural diagram of a device for generating page parameters of a web page provided by an embodiment of the present application; Figure 4A schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are only a part rather than all of the embodiments of the present application. Components of the embodiments of the present application usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application to be protected, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, every other embodiment obtained by those skilled in the art without creative efforts falls within the scope of protection of the present application.

[0021] First, the applicable application scenarios of the present application are introduced. The present application can be applied to network data processing technologies.

[0022] With the rapid development of Internet technologies, search engines have become one of the main ways for users to obtain information. As a technical means to improve the natural ranking of a website in a search engine, SEO (Search Engine Optimization) is crucial for enhancing the visibility and traffic of the website. To ensure that search engines can quickly and accurately crawl and index web page content, website administrators usually need to configure corresponding SEO information for each page, including titles, descriptions, and keywords, etc. These information not only helps search engines understand the page content but also directly affects the ranking of the page in search results.

[0023] It has been found through research that currently, the generation of this SEO information mainly relies on manual operations, that is, professionals summarize and refine it according to the page content. This method not only has a large workload and low efficiency but also results in uneven quality of the generated SEO information due to differences in the refining capabilities and experiences of different personnel. In addition, with the rapid update and iteration of Internet information, the method of manually generating SEO information is difficult to meet the requirements of real-time and consistency, thus affecting the overall optimization effect and user experience of the website.

[0024] Based on this, the embodiments of the present application provide a method for generating page parameters of a web page. By combining a large language model and a prompt template, it realizes the automatic generation of page parameters of the web page. The generated page parameters are more accurate and standardized, reducing manual participation and greatly improving the efficiency and accuracy of page parameter generation.

[0025] Please refer to Figure 1 , Figure 1The flowchart of a method for generating page parameters of a web page provided by an embodiment of this application. As Figure 1 shown in the figure, the page parameter generation method provided by the embodiment of this application includes: S101, obtain a target page, and determine a prompt word template corresponding to the target page from a preset template library.

[0026] Here, the preset template library stores multiple preset templates that are set in advance. The preset template library can include preset templates corresponding to each page type, each search engine, and each style preference, so that the large language model can generate page parameters corresponding to the target page according to the prompt words. The prompt word template also includes requirements for the generated page parameters.

[0027] For the above step S101, in specific implementation, obtain a target page. Here, the target web page can be generated by a target website, and determine a prompt word template corresponding to the target page from multiple preset templates stored in the preset template library.

[0028] According to the page parameter generation method provided by this application, the preset template library is constructed in the following two ways: Method 1: Generate at least one reference prompt word based on the page parameters of at least one first target reference page; generate preset templates based on the reference prompt words to form the preset template library.

[0029] For the above two steps, in specific implementation, first generate at least one reference prompt word based on the page parameters of the first target reference page. Here, a language model can be used to input the page parameters of the first target reference page into the language model, and the reference prompt words can be reversely summarized by the language model. For example, what kind of prompt words are needed to generate the page parameters of the first target reference page; the reference prompt words can also be generated by manual summarization. Then, use the reference prompt words to generate preset templates, and use the preset templates to construct the preset template library.

[0030] Method 2: Generate reference page parameters for a second target reference page based on at least one reference prompt word; determine at least one target reference prompt word based on the search optimization results of the reference page parameters of the second target reference page; generate preset templates based on the target reference prompt words to form the preset template library.

[0031] For the above two steps, in specific implementation, for the same second target reference page, generate multiple reference page parameters for the second target reference page according to at least one reference prompt word. Based on the search optimization results of different reference page parameters, determine at least one target reference prompt word, and then refine the prompt word template based on the target reference prompt words, and use the preset templates to construct the preset template library.

[0032] As an alternative embodiment, for the above step S101, determining the prompt word template corresponding to the target page from the preset template library includes: A: Obtain the page information of the target page.

[0033] For the above step A, in specific implementation, obtain the page information of the target page. Here, as an alternative embodiment, all externally callable page information of the target page can be obtained from the server side, or the page information of the target pages whose evaluation parameters such as page call volume and browsing time are in a certain proportion at the end can be obtained, or the page information of all externally callable target pages without page parameters set can be obtained. This application does not make specific limitations on this.

[0034] According to the embodiment provided by the present application, the page information is at least one of the page type information, search engine information, and style preference information of the target page.

[0035] Here, the page type information can be information such as video pages, picture pages, description pages, and Q&A pages used to describe the type of the target page. The search engine information refers to the information of the search engine targeted by search optimization. For different search engines, there are different preset templates to generate corresponding prompt words. For example, some search engines require the title to be no more than 10 characters, the description to be no more than 50 characters, and the keywords to be no more than 20 characters; some other search engines require the title to be no more than 20 characters, the description to be no more than 100 characters, and no keywords; and there are some other search engines that have other requirements for structured data in addition to the above requirements for titles, descriptions, and keywords. The style preference information can be to summarize the above information, or to focus on summarizing information related to time, or to focus on summarizing information related to emotions, etc. Since the content style preferences that different search engines, different page types, and different user groups want to obtain may be different, setting different preset templates is beneficial to generating page information that better meets the needs of users.

[0036] B: Based on the page information, determine the prompt word template corresponding to the page information from the preset templates in the preset template library.

[0037] For the above step B, in specific implementation, after determining the page information of the target page, based on this page information, determine the preset template corresponding to this page information from multiple preset templates in the preset template library as the prompt word template corresponding to the target page. Here, the corresponding prompt word template can be obtained from the preset template library based on the page type information; the preset template library can also include preset templates for different search engines and different style preferences, so the corresponding prompt word template can also be obtained based on the search engine information and style preference information.

[0038] As an alternative embodiment, for the above step S101, determining the prompt template corresponding to the target page from the preset template library includes: a: Obtain the search optimization results of at least one preset template in the preset template library for historical pages.

[0039] b: Determine the preset template with the optimal search optimization effect for historical pages as the prompt template.

[0040] For the above steps a - b, in specific implementation, first obtain the search optimization results of each preset template in the preset template library for historical pages. Specifically, for each preset template, obtain the historical prompts generated using this preset template, and obtain the historical page parameters generated based on this historical prompt. Use the search optimization effect of the historical page parameters for the historical page as the search optimization result of this preset template for the historical page. Then determine the preset template with the optimal search optimization effect for historical pages among multiple preset templates as the prompt template. In this way, the prompt template with the optimal optimization effect can be determined according to the search optimization effects of different preset templates for historical page parameters.

[0041] S102, Obtain the page content information corresponding to the target page, and generate the prompt for the target page based on the page content information and the prompt template.

[0042] Here, the page content information of a page refers to the specific content carried on the web page and its related attributes, which may include parameters such as text visible to users, multimedia resources, and structured data.

[0043] For the above step S102, in specific implementation, obtain the page content information corresponding to the target page, and generate the prompt for the target page based on the obtained page content information corresponding to the target page and the prompt template corresponding to the target page obtained in step S101.

[0044] Here, as an example, when the target page is a Q&A page, the corresponding prompt template may be "XXX Question: "XXXXX". XXX Reply: "XXXXXXXXXXXXXXXXXX". Requirements: Generate a title within 10 characters based on the above Q&A content; Generate a descriptor within 50 characters to describe the Q&A content; Extract keywords within 20 characters from the Q&A content". Among them, "XXX" is a placeholder. After obtaining the page content information corresponding to the target page, the placeholders in the above prompt template will be replaced according to the page content information, thereby generating the prompt. The "requirements" in the above example of the prompt template are the requirements for the generated page parameters.

[0045] Here, for different types of target pages, there are different methods to obtain the corresponding page content information. According to the embodiments provided in this application, the target page can be a video page, a picture page, a description page, or a Q&A page. Specifically, for the above step S102, the obtaining of the page content information corresponding to the target page includes: (1) When the target page is a picture page, input the first picture in the target page into a picture recognition model, and determine the first picture content information output by the picture recognition model as the page content information corresponding to the target page.

[0046] For the above step (1), in specific implementation, when the target page is a picture page, obtain the first picture included in the target page, and input the first picture into a pre-trained picture recognition model. The picture recognition model can recognize the first picture to extract the first picture content information corresponding to the first picture. Determine the first picture content information corresponding to the first picture in the target page as the page content information corresponding to the target page.

[0047] (2): When the target page is a video page, input the video in the target page into a video recognition model, and determine the video content information output by the video recognition model as the page content information corresponding to the target page. Or, obtain at least one second picture in the video, input each second picture into the picture recognition model, and determine the second picture content information output by the picture recognition model as the page content information corresponding to the target page.

[0048] For the above step (2), in specific implementation, when the target page is a video page, obtain the video included in the target page, and input the video into a pre-trained video recognition model. The video recognition model can recognize the video to extract the video content information corresponding to the video. Determine the video content information corresponding to the video in the target page as the page content information corresponding to the target page. Or, when the target page is a video page, extract at least one second picture from the video included in the target page, and input the second picture into a pre-trained picture recognition model. The picture recognition model can recognize the second picture to extract the second picture content information corresponding to the second picture. Determine the second picture content information corresponding to the second picture as the page content information corresponding to the target page.

[0049] (3): When the target page is a description page or a Q&A page, recognize the page elements in the target page to obtain the page content information corresponding to the target page. Or, obtain the parameter value corresponding to the target page through the server, and obtain the page content information corresponding to the target page based on the parameter value.

[0050] For the above step (3), in specific implementation, when the target page is a description page or a Q&A page, identify the page elements in the target page to obtain the page content information corresponding to the target page. Here, in a description page or a Q&A web page, identifying page elements and extracting content information is a process of separating the target content (such as text, Q&A pairs, etc.) from the complex page by analyzing the page elements, code structure, semantic features, and interaction patterns of the page. Specifically, for a description page, structured information such as titles, paragraphs, tables, etc. can be extracted as the page content information. For a Q&A page, content such as question titles, best answers, answerer information, etc. can be extracted as the page content information. Alternatively, when the target page is a description page or a Q&A page, obtain the parameter values corresponding to the target page through the server, and obtain the page content information corresponding to the target page based on the parameter values of the target page.

[0051] As an optional embodiment, for the above step S102, generating the prompt word for the target page based on the page content information and the prompt word template includes: Step 1021, determine at least one hot word information from the page content information.

[0052] Here, the hot word information refers to the phrases that appear with a relatively high frequency in the page content information.

[0053] For the above step 1021, in specific implementation, extract at least one hot word information from the page content information of the target page.

[0054] According to the embodiment provided by the present application, for the above step 1021, determine at least one hot word information from the page content information through the following two methods: Method 1: Segment the page content information to obtain at least one phrase, and / or, for a preset character number, obtain at least one phrase corresponding to the preset character number from the page content information, and determine the occurrence times of each phrase; sort at least one phrase based on the occurrence times, and determine a preset number of phrases from the sorting result as the hot word information.

[0055] For the above two steps, in the specific implementation, first obtain at least one phrase from the page content information. Specifically, at least one phrase can be obtained by segmenting the page content information; or at least one phrase corresponding to the preset number of characters can be obtained from the page content information for a preset number of characters. For example, when the preset number of characters is 2, a phrase consisting of two characters in the page content information is determined; and the number of occurrences of each phrase is determined. Then, at least one phrase is sorted based on the number of occurrences of the phrase, and a preset number of phrases are determined from the sorting results as hot word information. Here, specifically, at least one phrase is sorted from high to low based on the number of occurrences of the phrase, and the top-ranked phrases in the sorting results are used as hot word information. For example, when the preset number is 10, the top 10 phrases in the sorting results are used as hot word information.

[0056] Method 2: Segment the page content information to obtain at least one phrase, and / or, for a preset number of characters, obtain at least one phrase corresponding to the preset number of characters from the page content information, and determine the number of occurrences of each phrase; for each phrase, when the number of occurrences of the phrase is greater than or equal to a preset threshold, the phrase is determined as the hot word information.

[0057] For the above two steps, in the specific implementation, the method of determining at least one phrase from the page content information is the same as the method of determining the phrase in the above steps, which will not be repeated here. After determining at least one phrase, for each phrase, when the number of occurrences of the phrase is greater than or equal to a preset threshold, the phrase is determined as hot word information.

[0058] Step 1022, obtaining at least one hotspot information, and matching at least one hot word information with at least one hotspot information to determine at least one target hot word information.

[0059] In the specific implementation of step 1022, at least one hot word information is obtained, and the at least one hot word information is matched with at least one hot spot information to determine at least one target hot word information. Here, when matching, for each hot word information, when there is the same hot spot information as the hot word information, the hot word information is determined as the target hot word information.

[0060] According to the embodiment provided by the present application, for the above step 1022, multiple hotspot information is obtained by the following two methods: Method 1: Determine the hotspot information according to the search hotspots of the target search engine in a historical time period.

[0061] Here, the historical time period can be the past week or month, and this application does not make specific limitations thereon. Search hotspots refer to keywords or topics that have been searched by a large number of users during this historical time period.

[0062] For the above steps, in specific implementation, hotspot information is determined according to the search hotspots of the target search engine during the historical time period. Here, as an optional embodiment, the search terms searched through the target search engine during the historical time period can be obtained, and the number of times each search term is searched can be determined. When the number of times a searched term is searched is greater than or equal to a threshold, or the number of searches is among the top, then this searched term is used as a search hotspot to determine the hotspot information.

[0063] Method 2: Obtain the search hotspots of the target search engine during the historical time period; determine the hotspot information based on the changing trend of the search popularity of the search hotspots during the historical time period.

[0064] For the above two steps, in specific implementation, first, the search hotspots of the target search engine during the historical time period are obtained. Here, the method for obtaining search hotspots can refer to the description of the above steps and will not be elaborated here. Then, the hotspot information is determined based on the changing trend of the search popularity of the search hotspots during the historical time period. Here, as an optional embodiment, for each search hotspot, the changing trend of the search popularity of this search hotspot during the historical time period is statistically analyzed. If the changing trend of the search popularity is an upward trend, then this search hotspot is used as the hotspot information.

[0065] Step 1023, generate the prompt based on the prompt template, the page content information, and at least one target hot word information.

[0066] For the above step 1023, in specific implementation, after the target hot word information is determined, a prompt is generated based on the prompt template, the page content information, and at least one target hot word information. Here, there are multiple placeholders in the prompt template, and the placeholders are replaced with the page content information and the target hot word information to generate the prompt.

[0067] S103, input the prompt into a pre-trained large language model to generate the page parameters corresponding to the target page.

[0068] For the above-mentioned step S103, in specific implementation, the generated prompt is input into a pre-trained large language model, and the page parameters corresponding to the target page can be generated. Here, the page parameters may include the title, description, keywords, etc. of the target page, and may also include structured data, etc. The present application does not make specific limitations in this regard. According to the embodiments provided by the present application, the prompt template stores the requirements for the generated page parameters. Therefore, the large language model can utilize its language understanding ability and generalization ability to generate corresponding page parameters according to the requirements, reducing manual participation and greatly improving the efficiency and accuracy of page parameter generation. Moreover, by utilizing the strong generalization ability and understanding ability of the large language model, the generated page parameters are more accurate and standardized.

[0069] After generating the page parameters corresponding to the target page, the website information of the target website can be adjusted according to the page parameters, so as to improve the search result ranking and exposure of the target website in the search results.

[0070] According to the page parameter generation method provided by the embodiments of the present application, before obtaining the target page, the page parameter generation method further includes: I: Obtain a page generation requirement, and determine a corresponding target page template from a plurality of preset page generation templates based on the page generation requirement.

[0071] For the above-mentioned step I, in specific implementation, obtain a page generation requirement. Here, the page generation requirement may be for a certain target website, and determine a corresponding target page template from a plurality of preset page generation templates based on the page generation requirement. Here, for example, the page generation requirement may be "generate a picture page containing pictures of a certain element", "generate a video page containing videos of a certain element", or "generate a Q&A page answering XX questions", etc. The present application does not make specific limitations in this regard. As an example, when the page generation requirement is "generate a picture page containing pictures of a certain element", the target page template is the template of the picture page.

[0072] II: Determine a corresponding content generation model based on the content requirement in the page generation requirement, and use the content generation model to generate target content information corresponding to the page generation requirement.

[0073] For the above-mentioned step II, in specific implementation, a corresponding content generation model is determined based on the content requirements in the page generation requirements, and the target content information corresponding to the page generation requirements is generated using the content generation model. Here, as an example, when the page generation requirement is a Q&A page generation requirement and the content requirement is "generate a Q&A page with the question 'How to build a building?'", in this case, an agent more suitable for the construction field needs to be selected according to the content requirement to answer the above question, and different agents can be selected to answer multiple questions on a page. Another example is the picture class page generation requirement, and the content requirement is described as "pictures of a certain area, a certain housing type, and a certain decoration style". In this case, a picture generation model needs to be selected according to the content requirement to generate pictures that meet the content requirements. At the same time, a text expansion model or an agent suitable for decoration can be selected to first generate more detailed picture description information according to the requirement description, and then the picture generation model generates pictures that meet the content requirements; or, after the picture generation model generates pictures that meet the content requirements, a picture recognition model generates the description information of the corresponding pictures.

[0074] III: Generate a first page based on the target page template and the target content information, and determine the first page as the target page.

[0075] For the above-mentioned step III, in specific implementation, after the target content information is generated, the target content information is added to the corresponding position of the target page template, and then the first page can be generated, and the first page is determined as the target page. In this way, not only can the automatic generation of the page be realized according to the user's page generation requirements, but also the page parameters of the page can be automatically generated. After the page is generated, the page parameters corresponding to the page can also be generated through the above steps S101 - S103, realizing the fully automated generation and search optimization of the page and the page parameters.

[0076] The method for generating page parameters of a web page provided by the embodiments of this application is as follows: First, obtain a target page, and determine the prompt word template corresponding to the target page from a preset template library; then, obtain the page content information corresponding to the target page, and generate a prompt word for the target page based on the page content information and the prompt word template; finally, input the prompt word into a pre-trained large language model to generate the page parameters corresponding to the target page.

[0077] This application realizes the automatic generation of the page parameters of the web page by combining a large language model and a prompt word template. Generate a prompt word for the target page according to the prompt word template, and use the strong generalization ability and language understanding ability of the large language model to generate corresponding page parameters based on the prompt word. In this way, the generated page parameters are more accurate and standardized, reducing manual participation and greatly improving the efficiency and accuracy of page parameter generation.

[0078] Please refer to Figure 2 and Figure 3 , Figure 2 which is one of the structural schematic diagrams of a page parameter generation device provided by an embodiment of the present application, Figure 3 and is the second structural schematic diagram of a page parameter generation device provided by an embodiment of the present application. As Figure 2 shown in the page parameter generation device 200 includes: a template determination module 201, configured to obtain a target page and determine a prompt template corresponding to the target page from a preset template library; a prompt generation module 202, configured to obtain page content information corresponding to the target page and generate a prompt for the target page based on the page content information and the prompt template;

[0079] Further, when the prompt generation module 202 is used to obtain the page content information corresponding to the target page, the prompt generation module 202 is further configured to: when the target page is a picture type page, input the first picture in the target page into a picture recognition model, and determine the first picture content information output by the picture recognition model as the page content information corresponding to the target page; and / or, when the target page is a video type page, input the video in the target page into a video recognition model, and determine the video content information output by the video recognition model as the page content information corresponding to the target page, or obtain at least one second picture in the video, input each second picture into the picture recognition model, and determine the second picture content information output by the picture recognition model as the page content information corresponding to the target page; and / or, when the target page is a description type page or a Q&A type page, identify the page elements in the target page to obtain the page content information corresponding to the target page, or obtain the parameter value corresponding to the target page through the server, and obtain the page content information corresponding to the target page based on the parameter value.

[0080] Further, when the prompt generation module 202 is used to generate a prompt for the target page based on the page content information and the prompt template, the prompt generation module 202 is further configured to: determine at least one hot word information from the page content information; Obtain at least one piece of hot-spot information, match at least one hot-word information with at least one piece of hot-spot information, and determine at least one piece of target hot-word information; Generate the prompt word based on the prompt-word template, the page content information, and at least one piece of target hot-word information.

[0081] Further, when the prompt-word generation module 202 is used to determine at least one piece of hot-word information from the page content information, the prompt-word generation module 202 is further used to: Perform word segmentation on the page content information to obtain at least one phrase, and / or, for a preset number of characters, obtain at least one phrase corresponding to the preset number of characters from the page content information, and determine the occurrence times of each phrase; Sort at least one phrase based on the occurrence times, and determine a preset number of phrases from the sorting result as the hot-word information; Or, For each preset number of characters, obtain multiple phrases corresponding to the preset number of characters from the page content information, and determine the occurrence times of each phrase; For each phrase, when the occurrence times of the phrase are greater than or equal to a preset threshold, then determine the phrase as the hot-word information.

[0082] Further, the prompt-word generation module 202 is further used to obtain the hot-spot information through the following steps: Determine the hot-spot information according to the search hotspots of the target search engine in the historical time period; And / or, Obtain the search hotspots of the target search engine in the historical time period; Determine the hot-spot information based on the change trend of the search popularity of the search hotspots in the historical time period.

[0083] Please refer to Figure 3 , the page parameter generation device 200 further includes a page generation module 204. Before obtaining the target page of the target website, the page generation module 204 is used to: Obtain page generation requirements, and determine a corresponding target page template from a preset plurality of page generation templates based on the page generation requirements; Determine a corresponding content generation model based on the content requirements in the page generation requirements, and use the content generation model to generate target content information corresponding to the page generation requirements; Generate a first page based on the target page template and the target content information, and determine the first page as the target page.

[0084] Further, when the template determination module 201 is used to determine the prompt word template corresponding to the target page from multiple preset templates stored in a preset template library, the template determination module 201 is further configured to: Obtain the page information of the target page; wherein, the page information is at least one of the page type information, search engine information, and style preference information of the target page; Based on the page information, determine the prompt word template corresponding to the page information from the preset templates in the preset template library.

[0085] Further, when the template determination module 201 is used to determine the prompt word template corresponding to the target page from the preset template library, the template determination module 201 is further configured to: Obtain the search optimization results of at least one preset template in the preset template library for historical pages; Determine the preset template with the optimal search optimization effect for historical pages as the prompt word template.

[0086] Please refer to Figure 3 , the page parameter generation device 200 further includes a template library construction module 205, and the template library construction module 205 is configured to construct the preset template library through the following steps: Generate at least one reference prompt word based on the page parameters of at least one first target reference page; Generate preset templates based on the reference prompt words to form the preset template library; and / or, Generate reference page parameters for a second target reference page based on at least one reference prompt word; Determine at least one target reference prompt word based on the search optimization results of the reference page parameters of the second target reference page; Generate preset templates based on the target reference prompt words to form the preset template library.

[0087] Please refer to Figure 4 , Figure 4 is a schematic structural diagram of an electronic device provided in an embodiment of the present application. As Figure 4 shown in, the electronic device 400 includes a processor 410, a memory 420, and a bus 430.

[0088] The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 runs, the processor 410 communicates with the memory 420 through the bus 430. When the machine-readable instructions are executed by the processor 410, they can execute as described above Figure 1The steps of the method for generating page parameters of a web page in the illustrated method embodiment can be specifically implemented as can be seen in the method embodiment and will not be elaborated herein.

[0089] The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it can execute the steps of the method for generating page parameters of a web page in the method embodiment as illustrated above Figure 1 The steps of the method for generating page parameters of a web page in the illustrated method embodiment can be specifically implemented as can be seen in the method embodiment and will not be elaborated herein.

[0090] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described system, device, and unit can refer to the corresponding processes in the foregoing method embodiment and will not be elaborated herein.

[0091] In the several embodiments provided in the present application, it should be understood that the disclosed system, device, and method can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For another 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 displayed or discussed mutual coupling, direct coupling, or communication connection can be through some communication interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical, or other form.

[0092] The unit described as a separated component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0093] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0094] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0095] Finally, it should be noted that: the above-mentioned embodiments are only specific implementation manners of the present application, used to illustrate the technical solutions of the present application, rather than limiting them. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed by the present application can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes, or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for generating page parameters of a web page, characterized in that, The page parameter generation method includes: Obtain a target page and determine a prompt template corresponding to the target page from a preset template library; Obtain page content information corresponding to the target page, and generate a prompt for the target page based on the page content information and the prompt template; Input the prompt into a pre-trained large language model to generate page parameters corresponding to the target page.

2. The page parameter generation method according to claim 1, wherein The obtaining of the page content information corresponding to the target page includes: When the target page is a picture-type page, input the first picture in the target page into a picture recognition model, and determine the first picture content information output by the picture recognition model as the page content information corresponding to the target page; and / or, When the target page is a video-type page, input the video in the target page into a video recognition model, and determine the video content information output by the video recognition model as the page content information corresponding to the target page, or obtain at least one second picture in the video, input each second picture into the picture recognition model, and determine the second picture content information output by the picture recognition model as the page content information corresponding to the target page; and / or, When the target page is a description-type page or a Q&A-type page, identify page elements in the target page to obtain page content information corresponding to the target page, or obtain a parameter value corresponding to the target page through a server, and obtain the page content information corresponding to the target page based on the parameter value.

3. The page parameter generation method according to claim 1, wherein The generating of the prompt for the target page based on the page content information and the prompt template includes: Determine at least one hot word information from the page content information; Obtain at least one hot spot information, match at least one hot word information with at least one hot spot information, and determine at least one target hot word information; Generate the prompt based on the prompt template, the page content information, and at least one target hot word information.

4. The page parameter generation method according to claim 3, wherein The determining of at least one hot word information from the page content information includes: Perform word segmentation on the page content information to obtain at least one phrase, and / or, for a preset number of characters, obtain at least one phrase corresponding to the preset number of characters from the page content information and determine the occurrence times of each phrase; Sort at least one phrase based on the occurrence times, and determine a preset number of phrases from the sorting result as the hot word information; Or, For each phrase, when the occurrence times of the phrase are greater than or equal to a preset threshold, then determine the phrase as the hot word information.

5. The page parameter generation method according to claim 3, wherein The hot spot information is obtained through the following steps: Determine the hot spot information according to the search hot spots of a target search engine in a historical time period; and / or, Obtain the search hot spots of the target search engine in a historical time period; Determine the hot spot information based on the change trend of the search popularity of the search hot spots in the historical time period.

6. The page parameter generation method according to claim 1, wherein Before obtaining the target page, the page parameter generation method further includes: Obtain the page generation requirements, and determine the corresponding target page template from a plurality of preset page generation templates based on the page generation requirements; Determine the corresponding content generation model based on the content requirements in the page generation requirements, and use the content generation model to generate the target content information corresponding to the page generation requirements; Generate a first page based on the target page template and the target content information, and determine the first page as the target page.

7. The page parameter generation method according to claim 1, wherein The determining the prompt word template corresponding to the target page from the preset template library includes: Obtain the page information of the target page; wherein, the page information is at least one of the page type information, search engine information, and style preference information of the target page; Determine the prompt word template corresponding to the page information from the preset templates in the preset template library based on the page information.

8. The page parameter generation method according to claim 1, wherein The determining the prompt word template corresponding to the target page from the preset template library includes: Obtain the search optimization results of at least one preset template in the preset template library for historical pages; Determine the preset template with the best search optimization effect for historical pages as the prompt word template.

9. The page parameter generation method according to claim 1, wherein Construct the preset template library through the following steps: Generate at least one reference prompt word based on the page parameters of at least one first target reference page; Generate preset templates based on the reference prompt words to form the preset template library; And / or Generate reference page parameters for a second target reference page based on at least one reference prompt word; Determine at least one target reference prompt word based on the search optimization results of the reference page parameters of the second target reference page; Generate preset templates based on the target reference prompt words to form the preset template library.

10. A device for generating page parameters of a web page, characterized in that, The page parameter generation device includes: A template determination module, configured to obtain a target page and determine the prompt word template corresponding to the target page from a preset template library; A prompt word generation module, configured to obtain the page content information corresponding to the target page, and generate the prompt word of the target page based on the page content information and the prompt word template; A page parameter generation module, configured to input the prompt word into a pre-trained large language model to generate the page parameters corresponding to the target page.

Images