Intelligent website building content generation and optimization method based on artificial intelligence

Abstract

The invention discloses an intelligent website building content generation and optimization method based on artificial intelligence, and particularly relates to the technical field of artificial intelligence, and the method specifically comprises the following steps: automatically building website contents based on search engine optimized keywords according to an input theme by utilizing an artificial intelligence technology, and storing the website contents in a database; the method comprises the following steps of: evaluating word thickness information of a keyword by applying search engine optimization to obtain an optimized spiral coefficient, evaluating performance experience information of automatically constructed contents by applying a website performance evaluation method to obtain a loading interaction coefficient, establishing an optimized bias model by combining the optimized spiral coefficient and the loading interaction coefficient, obtaining an optimized bias index, and establishing an optimized bias model; according to the method, the preset optimization bias threshold value is compared with the optimization bias index, the content generation quality and efficiency are subjected to classification evaluation, the optimization direction used for artificial intelligence automatic generation is controlled according to the classification evaluation result, and the optimization logic control problem of site building optimization for the randomly generated content is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and more specifically, to an intelligent website content generation and optimization method based on artificial intelligence. Background Art

[0002] AI-based intelligent website content generation and optimization is a technical method that uses artificial intelligence technology to automatically create, manage and optimize website content. It is used to assist website owners or developers to efficiently generate content and optimize website performance and user experience. The correlation between existing automated content generation and optimization logic is weak. Content generation and optimization may be performed by two independent component modules. AI-based content generation has a certain degree of randomness. Under the same model parameters and keywords, the content generated each time is not exactly the same. Therefore, the optimization logic control for website optimization of randomly generated content has become an urgent problem to be solved.

[0003] In order to solve the above defects, a technical solution is now proposed. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent website content generation and optimization method based on artificial intelligence to solve the deficiencies in the background technology.

[0005] In order to achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent website content generation and optimization method based on artificial intelligence, which uses artificial intelligence technology to automatically construct the content of the website based on the input topic and keywords optimized by search engines;

[0006] Use search engine optimization to evaluate the word thickness information of keywords, and obtain the optimization spiral coefficient based on the word thickness information;

[0007] Use the website performance evaluation method to evaluate the performance experience information of the automatically constructed content, and obtain the loading interaction coefficient based on the performance experience information;

[0008] An optimization bias model is established by combining the optimization spiral coefficient and the loading interaction coefficient to obtain the optimization bias index. The preset optimization bias threshold is compared with the optimization bias index to classify and evaluate the quality and efficiency of content generation.

[0009] The optimization direction used for automatic generation of artificial intelligence is controlled based on the classification evaluation results.

[0010] Preferably, the method for obtaining word thickness information is:

[0011] Obtain the composite loading coefficient of the web page within the cycle time T, and integrate the composite loading coefficients of several web pages within the cycle time T into a data set, and mark the data set as Wth = {bdq}, where q = {1, 2, 3, ..., p}, and p is a positive integer, bd q It represents the composite loading coefficient of the web page in the qth cycle time T, and the calculation expression of the diffusion coefficient is Among them, C k represents the keyword coverage, and In the formula, K t is the keyword set in the generated content, K c is the keyword set, D k represents the keyword density, and Where, T w is the total number of words in the text, f(K i ) is the keyword K i The frequency of occurrence in the generated content, i is the keyword index, and n is the total number of keywords;

[0012] Calculate the standard deviation of the composite loading coefficient of web pages within several cycle times T. The calculation expression is: In the formula, dia is the average value of the composite loading coefficient of the web page within several cycles of time T, and the calculation expression is:

[0013] Preferably, the method for obtaining the optimized spiral coefficient according to the word thickness information is:

[0014] The number of paragraphs of the generated content is calibrated as N pa , the number of information points is I pn , the user stay time is U st , the number of clicks is C li , the number of impressions is I mp , the number of visits is V is , the number of bounces is B on , then the calculation expression of the optimized spiral coefficient is In the formula, α and β are respectively (C li / I mp )*lg(Wth) and The weight coefficient of , and α and β are both positive numbers.

[0015] Preferably, the method for obtaining performance experience information is:

[0016] Obtain the composite loading coefficient of the web page within the cycle time T, and integrate the composite loading coefficients of several web pages within the cycle time T into a data set, and mark the data set as Wpa = {cl c}, where c = {1, 2, 3, ..., v}, and v is a positive integer, cl c It represents the composite loading coefficient of the web page in the cth cycle time T. The calculation expression of the composite loading coefficient is Among them, L t is the time required for the page to be fully loaded, T fb T is the time required for the server to start responding to the request and send the first byte. ti The time the user interacts with the page;

[0017] Calculate the standard deviation of the composite loading coefficient of web pages within several cycle times T. The calculation expression is: Where avl is the average value of the composite loading coefficient of the web page within several cycles T, and the calculation expression is:

[0018] Preferably, the method for obtaining the loading interaction coefficient according to the performance experience information is:

[0019] The page size is calibrated as P s , the number of requests is R eq , then the calculation expression of the loading interaction coefficient is The page size includes text and image resources, and the number of requests is the number of HTTP requests required to load the page.

[0020] Preferably, the method for establishing an optimized bias model and obtaining an optimized bias index is:

[0021] The calibration optimization bias index is 0 pb , the optimized bias model is O pb =γ1*O sc +γ2*L ic , where γ1 and γ2 are the optimized spiral coefficients O sc , loading interaction coefficient L ic The proportional coefficient, and γ1 and γ2 are both positive numbers.

[0022] Preferably, the logic for classifying and evaluating the quality and efficiency of content generation is:

[0023] Preset optimization bias threshold O th , the calculated optimization bias index O pb With the optimized bias threshold O th Compare, when optimizing the bias index O pb Less than or equal to the optimization bias threshold O th , then there is room for optimization in the tag-generated content;

[0024] When the optimization bias index O pb Greater than the optimization bias threshold O th , there is no room for optimization of the tag-generated content.

[0025] Preferably, the logic for controlling the optimization direction automatically generated by artificial intelligence according to the classification evaluation results is:

[0026] When the generated content is marked as having optimization space, the spiral threshold O1 and the interaction threshold L1 are preset to optimize the spiral coefficient O sc Compare with the spiral threshold O1 and load the interaction coefficient L ic Compared with the interaction threshold L1, when the spiral coefficient O is optimized sc Less than or equal to the spiral threshold O1, load interaction coefficient L ic When it is greater than the interaction threshold L1, the keyword density and content quality of the AI-generated content are optimized and adjusted;

[0027] When the optimal spiral coefficient O sc Greater than the spiral threshold O1, load interaction coefficient L ic When it is less than or equal to the interaction threshold L1, the page loading time and content structure of the AI-generated website are optimized and adjusted;

[0028] When the optimal spiral coefficient O sc Less than or equal to the spiral threshold O1, load interaction coefficient L ic When it is less than or equal to the interaction threshold L1, the keyword density, content quality of the AI-generated content and the page loading time and content structure of the AI-generated website are optimized and adjusted.

[0029] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0030] This application conducts a comprehensive evaluation of the generation quality and generation efficiency of intelligent website construction using artificial intelligence technology, obtains comprehensive evaluation indicators for automatic content generation, defines and controls the feedback adjustment logic of generated content according to the comprehensive evaluation indicators, optimizes the quality of automatically generated content and the utilization efficiency of the website, reduces the workload of manual control and improves the optimization efficiency of artificial intelligence automatically generated content, effectively improves the linear transition capability from content generation to control optimization, and avoids imbalance between the content generation direction and the optimization angle level. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] 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 recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0032] Figure 1 The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] Example 1: Please refer to Figure 1 As shown, the present invention is an intelligent website content generation and optimization method based on artificial intelligence, and the specific steps include:

[0035] Use artificial intelligence technology to automatically build the content of the website based on the input topic and keywords based on search engine optimization;

[0036] Use search engine optimization to evaluate the word thickness information of keywords, and obtain the optimization spiral coefficient based on the word thickness information;

[0037] Use the website performance evaluation method to evaluate the performance experience information of the automatically constructed content, and obtain the loading interaction coefficient based on the performance experience information;

[0038] An optimization bias model is established by combining the optimization spiral coefficient and the loading interaction coefficient to obtain the optimization bias index. The preset optimization bias threshold is compared with the optimization bias index to classify and evaluate the quality and efficiency of content generation.

[0039] The optimization direction used for automatic generation of artificial intelligence is controlled based on the classification evaluation results.

[0040] Automatic website building and automatic content generation based on artificial intelligence technology improves website building efficiency and content quality, while meeting the ever-changing user needs and search engine rules in the modern network environment. It has significant advantages for enterprises, individuals and developers, and can bring higher productivity and business value;

[0041] The traditional website building process may take weeks or even months, including design, development, content creation, etc., while the automatic website building system based on artificial intelligence can generate a complete website in a few hours or even minutes, which greatly saves time. The automated website building tool reduces the dependence on manual design, programming and content creation, reduces the website development cost and subsequent maintenance costs, and effectively creates high-quality websites with a lower budget for small and medium-sized enterprises and individual users;

[0042] Artificial intelligence automatically generates content that meets search engine optimization standards based on preset topics and keywords, reducing the workload of manual writing. Through natural language generation technology, artificial intelligence generates natural and fluent text to ensure that the content is both attractive to users and in line with search engine rules. Artificial intelligence analyzes user behavior, preferences and historical data to generate personalized content for different user groups, ensuring that each visitor can see the information that best matches their needs, improving user experience;

[0043] Artificial intelligence analyzes changes in search engine algorithms in real time, optimizes website structure, content keywords, metadata, internal links, etc., and improves the website's ranking in search engine results pages. Manual search engine optimization is complex and time-consuming, while artificial intelligence automatically adjusts content strategies through large amounts of data and algorithms to continuously optimize results. Search engine algorithms and rules change frequently, and artificial intelligence automatically tracks changes and instantly adjusts website content and structure to ensure that the website always remains in a suitable search engine optimization state;

[0044] Artificial intelligence automatically adjusts the website layout according to the user's device type to achieve responsive design and ensure the best user experience on all devices. At the same time, artificial intelligence continuously optimizes the user interface and interactive design by analyzing user behavior data, including clicks, dwell time, bounce rate, etc., effectively improving user satisfaction;

[0045] Artificial intelligence not only automatically generates content, but also continuously monitors the performance of the website and the results of search engine optimization, analyzes user feedback and traffic data, automatically adjusts content, optimizes loading speeds, and enhances user interaction experience, so that the website can always remain competitive in the ever-changing market and technological environment. Artificial intelligence automatically runs A / B tests on multiple versions of content, quickly identifies which versions of content or layout are popular with users, and automatically selects the best version to apply to the website, reducing the time cost of manual testing and optimization.

[0046] Use artificial intelligence technology to automatically build the content of the website based on the input topic and keywords based on search engine optimization;

[0047] Parse the input topic content based on natural language processing technology and determine the core, intent and domain of the topic. Process the input text through vocabulary, syntax and semantic analysis to extract core topics, keywords and contextual intent. Automatically identify key topics in the text through topic modeling algorithms and associate related subtopics.

[0048] Access a database containing high-frequency keywords and long-tail keywords to obtain matching high-frequency keywords and long-tail keywords. Based on the matching high-frequency keywords and long-tail keywords, use natural language generation technology to generate the core text content of the website and ensure that the generated content is readable, coherent, and naturally incorporates matching keywords.

[0049] The keyword data in the database is obtained through search engine trend analysis tools or a large number of crawled web pages and search engine data sets. The user's input topic is matched with the vocabulary in the keyword database through a matching algorithm, and the matching high-frequency keywords and long-tail keywords are extracted for text generation;

[0050] It should be noted that commonly used topic modeling algorithms include LDA, BERT, etc. High-frequency keywords are widely used and highly competitive words with large search volumes, while long-tail keywords are more specific with lower search volumes and competitiveness. Commonly used matching algorithms include cosine similarity, word embedding vector similarity, etc.

[0051] Use search engine optimization to evaluate the word thickness information of keywords, and obtain the optimization spiral coefficient based on the word thickness information;

[0052] The method for obtaining word thickness information is:

[0053] Obtain the composite loading coefficient of the web page within the cycle time T, and integrate the composite loading coefficients of several web pages within the cycle time T into a data set, and mark the data set as Wth = {bd q}, where q = {1, 2, 3, ..., p}, and p is a positive integer, bd q It represents the composite loading coefficient of the web page in the qth cycle time T, and the calculation expression of the diffusion coefficient is Among them, C k represents the keyword coverage, and In the formula, K t is the keyword set in the generated content, K c is the keyword set, D k represents the keyword density, and Where, T w is the total number of words in the text, f(K i ) is the keyword K i The frequency of occurrence in the generated content, i is the keyword index, and n is the total number of keywords;

[0054] Calculate the standard deviation of the composite loading coefficient of web pages within several cycle times T. The calculation expression is: In the formula, dia is the average value of the composite loading coefficient of the web page within several cycles of time T, and the calculation expression is:

[0055] The method for obtaining the optimized spiral coefficient based on word thickness information is:

[0056] The number of paragraphs of the generated content is calibrated as N pa , the number of information points is I pn , the user stay time is U st , the number of clicks is C li , the number of impressions is I mp , the number of visits is V is , the number of bounces is B on , then the calculation expression of the optimized spiral coefficient is In the formula, α and β are respectively (C li / I mp )*lg(Wth) and The weight coefficient of , and α and β are both positive numbers.

[0057] If the automatically generated content meets the high-quality SEO standards, the website will get better search engine rankings, thereby increasing traffic. One of the core of SEO is the reasonable distribution of keywords. By evaluating the quality of the content, we can ensure that the keyword density is moderate and avoid keyword stacking that leads to search engine penalties. High-quality content has a clear structure and logic, and is easy to be indexed and understood by search engines. Content evaluation ensures that the generated content is deeply related to the topic and provides valuable information rather than superficial descriptions.

[0058] In addition to search engine optimization, the attractiveness of content is directly related to the user experience and conversion rate. Attractive content attracts the user's interest, prompting them to stay longer, browse more pages, and interact. If the content is of low quality or does not meet the needs of users, users will quickly leave the page, resulting in a high bounce rate, which affects the overall performance of the website. By evaluating the attractiveness and optimizing the content, we can ensure that the content can meet the needs of users, thereby reducing the bounce rate. Attractive content can better drive users to take targeted actions. Evaluating the attractiveness helps to fine-tune the content and maximize the conversion rate.

[0059] Search engine algorithms are frequently updated and focus on content relevance, user behavior indicators, and user satisfaction. By analyzing user behavior data, content is optimized to adapt to the latest search engine algorithms, and the weight and ranking of pages are improved. Through regular evaluation and adjustment, search engine trends can be tracked and content optimized in real time to ensure that the generated content remains competitive in the long term.

[0060] Interactions include clicking links, filling out forms, etc., target actions include purchasing products, subscribing to services, downloading materials, etc. User behavior indicators include click-through rate and dwell time, and user behavior data include click-through rate, bounce rate, etc.

[0061] Use the website performance evaluation method to evaluate the performance experience information of the automatically constructed content, and obtain the loading interaction coefficient based on the performance experience information;

[0062] The method for obtaining performance experience information is as follows:

[0063] Obtain the composite loading coefficient of the web page within the cycle time T, and integrate the composite loading coefficients of several web pages within the cycle time T into a data set, and mark the data set as Wpa = {cl c}, where c = {1, 2, 3, ..., v}, and v is a positive integer, cl c It represents the composite loading coefficient of the web page in the cth cycle time T. The calculation expression of the composite loading coefficient is Among them, L t is the time required for the page to be fully loaded, T fb T is the time required for the server to start responding to the request and send the first byte. ti The time the user interacts with the page;

[0064] Calculate the standard deviation of the composite loading coefficient of web pages within several cycle times T. The calculation expression is: Where avl is the average value of the composite loading coefficient of the web page within several cycles T, and the calculation expression is:

[0065] The method for obtaining the loading interaction coefficient based on performance experience information is:

[0066] The page size is calibrated as P s , the number of requests is R eq , then the calculation expression of the loading interaction coefficient is The page size includes text and image resources, and the number of requests is the number of HTTP requests required to load the page.

[0067] Evaluate website performance and user experience to help identify problems users encounter during use, such as slow page loading or untimely response, which directly affect user satisfaction. By optimizing indicators, improve user experience and make users willing to stay and use the website, thereby enhancing user loyalty;

[0068] Improvements in performance indicators such as page load time and interactive time effectively reduced user bounce rates. Performance indicators were evaluated and optimized to maintain user engagement on the website.

[0069] Good performance and user experience are directly related to the improvement of conversion rate. Users are more likely to complete purchases, registrations or other target behaviors on a fast and smooth website. By evaluating and optimizing the experience, sales or other key business indicators can be effectively increased.

[0070] Regularly evaluate website performance to help identify performance bottlenecks and potential problems. By analyzing the data, you can clearly understand the areas that need improvement and effectively perform targeted optimization.

[0071] An optimization bias model is established by combining the optimization spiral coefficient and the loading interaction coefficient to obtain the optimization bias index. The preset optimization bias threshold is compared with the optimization bias index to classify and evaluate the quality and efficiency of content generation.

[0072] The method to establish the optimization bias model and obtain the optimization bias index is:

[0073] The calibration optimization bias index is 0 pb , the optimized bias model is O pb =γ1*O sc +γ2*L ic , where γ1 and γ2 are the optimized spiral coefficients O sc , loading interaction coefficient L ic The proportionality coefficient of , and γ1 and γ2 are both positive numbers;

[0074] The logic for classifying and evaluating the quality and efficiency of content generation is:

[0075] Preset optimization bias threshold O th , the calculated optimization bias index O pb With the optimized bias threshold O th Compare, when optimizing the bias index O pb Less than or equal to the optimization bias threshold O th , then there is room for optimization in the tag-generated content;

[0076] When the optimization bias index O pb Greater than the optimization bias threshold O th , there is no room for optimization of the tag-generated content.

[0077] The optimization direction used for automatic generation of artificial intelligence is controlled based on the classification evaluation results.

[0078] When the generated content is marked as having optimization space, the spiral threshold O1 and the interaction threshold L1 are preset to optimize the spiral coefficient O sc Compare with the spiral threshold O1 and load the interaction coefficient L ic Compared with the interaction threshold L1, when the spiral coefficient O is optimized sc Less than or equal to the spiral threshold O1, load interaction coefficient L ic When it is greater than the interaction threshold L1, the keyword density and content quality of the AI-generated content are optimized and adjusted;

[0079] When the optimal spiral coefficient O scGreater than the spiral threshold O1, load interaction coefficient L ic When it is less than or equal to the interaction threshold L1, the page loading time and content structure of the AI-generated website are optimized and adjusted;

[0080] When the optimal spiral coefficient O sc Less than or equal to the spiral threshold O1, load interaction coefficient L ic When it is less than or equal to the interaction threshold L1, the keyword density, content quality of the AI-generated content and the page loading time and content structure of the AI-generated website are optimized and adjusted.

[0081] This application conducts a comprehensive evaluation of the generation quality and generation efficiency of intelligent website construction using artificial intelligence technology, obtains comprehensive evaluation indicators for automatic content generation, defines and controls the feedback adjustment logic of generated content according to the comprehensive evaluation indicators, optimizes the quality of automatically generated content and the utilization efficiency of the website, reduces the workload of manual control and improves the optimization efficiency of artificial intelligence automatically generated content, effectively improves the linear transition capability from content generation to control optimization, and avoids imbalance between the content generation direction and the optimization angle level.

[0082] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0083] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of computer program goods. The computer program goods include one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0084] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0085] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0086] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0087] If the functions are implemented in the form of software functional units and sold or used as independent goods, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the prior art or the part of the technical solution can be embodied in the form of software goods, and the computer software goods are stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in 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, and other media that can store program codes.

[0088] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent website content generation and optimization method based on artificial intelligence, characterized in that: Use artificial intelligence technology to automatically build the content of the website based on the input topic and keywords based on search engine optimization; Use search engine optimization to evaluate the word thickness information of keywords, and obtain the optimization spiral coefficient based on the word thickness information; Use the website performance evaluation method to evaluate the performance experience information of the automatically constructed content, and obtain the loading interaction coefficient based on the performance experience information; An optimization bias model is established by combining the optimization spiral coefficient and the loading interaction coefficient to obtain the optimization bias index. The preset optimization bias threshold is compared with the optimization bias index to classify and evaluate the quality and efficiency of content generation. The optimization direction used for automatic generation of artificial intelligence is controlled based on the classification evaluation results.

2. The method for generating and optimizing website content based on artificial intelligence according to claim 1 is characterized in that: The method for obtaining word thickness information is: Obtain the composite loading coefficient of the web page within the cycle time T, and integrate the composite loading coefficients of several web pages within the cycle time T into a data set, and mark the data set as Wth = {bd q }, where q = {1, 2, 3, ..., p}, and p is a positive integer, bd q It represents the composite loading coefficient of the web page in the qth cycle time T, and the calculation expression of the diffusion coefficient is Among them, C k represents the keyword coverage, and In the formula, K t is the keyword set in the generated content, K c is the keyword set, D k represents the keyword density, and Where, T w is the total number of words in the text, f(K i ) is the keyword K i The frequency of occurrence in the generated content, i is the keyword index, and n is the total number of keywords; Calculate the standard deviation of the composite loading coefficient of web pages within several cycle times T. The calculation expression is: In the formula, dia is the average value of the composite loading coefficient of the web page within several cycles of time T, and the calculation expression is:

3. The method for generating and optimizing intelligent website content based on artificial intelligence according to claim 2 is characterized in that: The method for obtaining the optimized spiral coefficient based on word thickness information is: The number of paragraphs of the generated content is calibrated as N pa , the number of information points is I pn , the user stay time is U st , the number of clicks is C li , the number of impressions is I mp , the number of visits is V is , the number of bounces is B on , then the calculation expression of the optimized spiral coefficient is In the formula, α and β are respectively (C li / I mp )*lg(Wth) and The weight coefficient of , and α and β are both positive numbers.

4. The method for generating and optimizing intelligent website content based on artificial intelligence according to claim 1 is characterized in that: The method for obtaining performance experience information is as follows: Obtain the composite loading coefficient of the web page within the cycle time T, and integrate the composite loading coefficients of several web pages within the cycle time T into a data set, and mark the data set as Wpa = {cl c }, where c = {1, 2, 3, ..., v}, and v is a positive integer, cl c It represents the composite loading coefficient of the web page in the cth cycle time T. The calculation expression of the composite loading coefficient is Among them, L t is the time required for the page to be fully loaded, T fb T is the time required for the server to start responding to the request and send the first byte. ti The time the user interacts with the page; Calculate the standard deviation of the composite loading coefficient of web pages within several cycle times T. The calculation expression is: Where avl is the average value of the composite loading coefficient of the web page within several cycles T, and the calculation expression is:

5. The method for generating and optimizing intelligent website content based on artificial intelligence according to claim 4 is characterized in that: The method for obtaining the loading interaction coefficient based on performance experience information is: The page size is calibrated as P s , the number of requests is R eq , then the calculation expression of the loading interaction coefficient is The page size includes text and image resources, and the number of requests is the number of HTTP requests required to load the page.

6. The method for generating and optimizing intelligent website content based on artificial intelligence according to claim 1, characterized in that: The method to establish the optimization bias model and obtain the optimization bias index is: The calibration optimization bias index is 0 pb , the optimized bias model is O pb =γ1*O sc +γ2*L ic , where γ1 and γ2 are the optimized spiral coefficients O sc , loading interaction coefficient L ic The proportional coefficient, and γ1 and γ2 are both positive numbers.

7. The method for generating and optimizing intelligent website content based on artificial intelligence according to claim 6 is characterized in that: The logic for classifying and evaluating the quality and efficiency of content generation is: Preset optimization bias threshold O th , the calculated optimization bias index O pb With the optimized bias threshold O th Compare, when optimizing the bias index O pb Less than or equal to the optimization bias threshold O th , then there is room for optimization in the tag-generated content; When the optimization bias index O pb Greater than the optimization bias threshold O th , there is no room for optimization of the tag-generated content.

8. The method for generating and optimizing intelligent website content based on artificial intelligence according to claim 7 is characterized in that: The logic for controlling the optimization direction automatically generated by artificial intelligence based on the classification evaluation results is: When the generated content is marked as having optimization space, the spiral threshold O1 and the interaction threshold L1 are preset to optimize the spiral coefficient O sc Compare with the spiral threshold O1 and load the interaction coefficient L ic Compared with the interaction threshold L1, when the spiral coefficient O is optimized sc Less than or equal to the spiral threshold O1, load interaction coefficient L ic When it is greater than the interaction threshold L1, the keyword density and content quality of the AI-generated content are optimized and adjusted; When the optimal spiral coefficient O sc Greater than the spiral threshold O1, load interaction coefficient L ic When it is less than or equal to the interaction threshold L1, the page loading time and content structure of the AI-generated website are optimized and adjusted; When the optimal spiral coefficient O sc Less than or equal to the spiral threshold O1, load interaction coefficient L ic When it is less than or equal to the interaction threshold L1, the keyword density, content quality of the AI-generated content and the page loading time and content structure of the AI-generated website are optimized and adjusted.

Images