A cross-platform operation optimization system and method based on artificial intelligence

Abstract

A cross-platform content operation optimization system and method based on artificial intelligence, including an information and data collection module, a data and information analysis module, a hot topic collection management module, a traffic diversion function management module, a content creation module, an optimization flow coverage module and an intelligent delivery module; the traffic diversion function management module is used to create and manage traffic diversion functions for traffic diversion content; the content creation module is used to create content of different types and formats, the types of content include brand type content, traffic diversion type content and positive hot topic type content, and the formats of content include video format, graphic format and web page format; the optimization flow coverage module is used to generate a new flow transmission path; the intelligent delivery module is used to deliver the created content to various social media platforms, and deliver traffic to the content of the social media platform according to the preset flow transmission path.

Description

Technical Field

[0001] This invention relates to the field of cross-platform content operation optimization technology, and in particular to a cross-platform content operation optimization system and method based on artificial intelligence. Background Art

[0002] Cross-platform content operation refers to the strategy of publishing and managing content across multiple different social media, online platforms, or mobile applications. The aim of this approach is to expand brand influence, increase user engagement, enhance brand recognition, and ultimately achieve marketing goals. Cross-platform content operation is a complex but high-reward endeavor, requiring operators to possess strategic thinking, creativity, and analytical skills. Through effective cross-platform content operation, brands can better communicate with their target audience and establish a strong online presence. Existing cross-platform content operation technologies face the following technical challenges:

[0003] 1. Traditional social media analytics tools often encounter data overload issues due to the massive amount of data. Therefore, a module is needed to help identify and filter key information more quickly to compensate for the shortcomings and deficiencies of existing technologies.

[0004] 2. Some existing cross-platform operation systems are unable to fully promote the spread of positive content and effectively filter negative topics when managing trending topics on social media;

[0005] 3. When operating content across platforms, it is challenging to convert users from one platform to another because users on different platforms have different habits and usage patterns. Therefore, an effective strategy is needed to attract and guide users to achieve cross-platform attention and interaction, so as to better serve cross-platform content operation.

[0006] 4. The choice of network traffic transmission path significantly impacts content loading speed. An inappropriate path selection can cause traffic to traverse unnecessary intermediate routes, increasing transmission distance and loading time. In many cases, when traffic experiences low coverage along the transmission path, social media platforms experience slower content loading, negatively affecting user experience. Therefore, an effective detection mechanism is needed to compensate for the shortcomings of existing technologies. Summary of the Invention

[0007] To achieve the objectives of this invention, an artificial intelligence-based cross-platform content operation optimization system is provided, comprising an information and data collection module, a data and information analysis module, a hot topic collection and management module, a traffic generation function management module, a content creation module, a traffic coverage optimization module, and an intelligent delivery module. The input of the data and information analysis module is connected to the output of the information and data collection module; the input of the traffic generation function management module is connected to the output of the data and information analysis module; the input of the content creation module is connected to the outputs of the data and information analysis module, the hot topic collection and management module, and the traffic generation function management module; the input of the traffic coverage optimization module is connected to the output of the data and information analysis module; and the input of the intelligent delivery module is connected to the output of the content creation module.

[0008] The information and data collection module is used to collect enterprise information, content performance data, and conversion rate data;

[0009] The data and information analysis module is used to analyze the collected information and data to obtain analysis results;

[0010] The hot topic collection and management module is used to identify hot topics on social media platforms and manage the collected hot topics.

[0011] The traffic acquisition function management module is used to create and manage traffic acquisition functions for traffic acquisition content.

[0012] The content creation module is used to create content of different types and formats. The content types include brand-type content, traffic-driving content, and positive trending topic content. The content formats include video format, image and text format, and web page format.

[0013] The optimized traffic coverage module is used to generate new traffic transmission paths;

[0014] The intelligent delivery module is used to deliver the created content to various social media platforms. It delivers traffic to the content on the respective social media platform according to the preset traffic transmission path. Cross-platform promotion can help reach a wider audience and increase the exposure of the content. The traffic transmission path has a great impact on the content loading speed. The traffic transmission path includes unidirectional paths and relational paths. The relational path represents the sum of two or more connected unidirectional paths.

[0015] Furthermore, the information and data collection module includes an enterprise information collection submodule, a content performance data collection submodule, and a conversion rate data collection submodule;

[0016] The enterprise information collection submodule is used to connect to the enterprise information storage system, obtain enterprise information from the enterprise information storage system, and collect enterprise information, including brand information and product information.

[0017] The content performance data collection submodule is used to collect content performance data from social media platforms;

[0018] The conversion rate data collection submodule is used to collect conversion rate data, including fan conversion rate data, content engagement rate data, and purchase ratio data.

[0019] Furthermore, the content performance data collection submodule includes a user behavior data collection unit and a traffic data collection unit;

[0020] The user behavior data collection unit is used to collect users' browsing paths, purchase records, the number of new users browsing content, the number of new fans, the number of users participating in content brand activities and interactions, the number of users making purchases, and the number of users browsing content.

[0021] The traffic data collection unit is used to collect the relationship paths of traffic within a set time period and the coverage on the relationship paths. The relationship paths of traffic within a set time period usually refer to the user's behavioral trajectory on the network platform or application within a specific time period, which includes the pages visited by the user, the links clicked, the videos watched, the interactions participated in, etc.

[0022] Furthermore, the data and information analysis module includes a brand information analysis submodule, a product information analysis submodule, a user behavior data analysis submodule, and a traffic analysis submodule;

[0023] The brand information analysis submodule is used to analyze brand information and obtain brand information analysis results, which include the brand's personality characteristics, brand language style, emotional tone, brand image, and brand story.

[0024] The product information analysis submodule is used to analyze product information and obtain product information analysis results. The product information analysis results include the product's functions, characteristics, user benefits, and usage scenarios, and identify the differences and innovations between the product and competing products.

[0025] The user behavior data analysis submodule is used to analyze user behavior data and obtain analysis results, including information on media and platforms where users are active and susceptible, purchase peaks and repeat purchase behaviors during specific time periods.

[0026] The traffic analysis submodule calculates the coverage of traffic on relational paths within a set time period, which can more accurately monitor network traffic patterns and trends. By marking relational paths with calculated traffic coverage less than a preset threshold as low traffic coverage relational paths, targeted optimization of these paths can improve the efficiency of network resource utilization. If the calculated traffic coverage of a relational path is greater than or equal to the preset threshold, the relational path is marked as a high traffic coverage relational path.

[0027] Furthermore, the user behavior data analysis submodule includes a user browsing path analysis unit, a purchase record analysis unit, a fan conversion rate analysis unit, a content participation rate analysis unit, and a user purchase rate analysis unit;

[0028] The user's browsing path analysis unit is used to generate a visualized user journey image by analyzing the user's browsing path, identify hotspots in the image, and identify information about media and platforms that the user is active in and susceptible to.

[0029] The purchase record analysis unit is used to analyze purchase records and, by identifying patterns in the purchase records, to obtain analysis results on purchase peaks and repeat purchase behaviors in a specific time period.

[0030] The fan conversion rate analysis unit is used to calculate the proportion of new users who browse content and become fans of the brand's social media account, obtain fan conversion rate data, compare the fan conversion rates of different types of content, and draw the analysis results of the content that is most efficient at attracting users to become fans of the platform account.

[0031] The content participation rate analysis unit is used to calculate the content participation rate, obtain content participation rate data, compare the participation rates of different types of content, and obtain the content analysis results that attract users to participate in content brand activities and interactions to the greatest extent.

[0032] The user purchase rate analysis unit is used to calculate the ratio of the number of users who make purchases to the number of users who browse content, obtain purchase ratio data, compare the proportion of different types of content that guide users to complete purchases, and obtain the analysis results of the content that guides users to complete purchase behavior the highest.

[0033] Furthermore, the hot topic collection and management module includes a hot topic identification submodule, a hot topic collection submodule, and a negative hot topic filtering submodule;

[0034] The hot topic identification submodule is used to identify the usage of topic tags on social media platforms, analyze their popularity and user engagement, and thus determine whether the topic has become a hot topic.

[0035] The hot topic collection submodule is used to collect identified but unlabeled hot topics and classify them, including positive hot topics and negative hot topics.

[0036] The negative hot topic filtering submodule is used to set labels for negative hot topics according to a preset negative topic list, and then filter them in batches. The labeled negative hot topics will no longer be collected by the hot topic collection submodule as a basis for generating related content. It can effectively filter negative topics and will not cause data overload problems due to the huge amount of data.

[0037] Furthermore, the traffic acquisition function management module includes a target platform selection submodule, a cross-platform link generation submodule, a jump path generation submodule, a jump and loading monitoring submodule, and a traffic acquisition content recycling submodule;

[0038] The target platform selection submodule is used to recommend target platforms for users to jump to based on the results of user behavior data analysis.

[0039] The cross-platform link generation submodule is used to generate dedicated cross-platform links for each traffic-generating content. These links point to specific content on the target platform, ensuring link compatibility and security so that users can smoothly jump across platforms.

[0040] The redirect path generation submodule is used to obtain and parse the network address of the corresponding platform to be redirected to, and generate a redirect path based on the parsing result. The redirect path is the redirect path for the traffic-generating content.

[0041] The jump and loading monitoring submodule is used to monitor the jump process and the loading status of the target platform content after the user clicks on the cross-platform link;

[0042] The content recycling submodule is used to recycle the traffic-generating content back to the original social media platform according to the original redirect path after the content is loaded on the target platform. This avoids interfering with the user experience on the target platform. By converting users from one platform to another, it attracts and guides users to achieve cross-platform attention and interaction, and can better serve cross-platform content operation.

[0043] Furthermore, the content creation module includes a brand content creation submodule, a traffic-driving content creation submodule, and a positive trending topic content generation submodule;

[0044] The brand content creation submodule is used to create various types of brand content, and to create different types and formats of content about brand stories based on content performance data analysis results, brand information analysis results, conversion rate data analysis results, and product information analysis results.

[0045] The content creation submodule is used to create various types of content that drives traffic to the platform. It adds traffic-driving functions and elements to the existing brand content. These elements include trailers, highlight displays, exclusive offers, and limited-time events. The goal is to ensure that the content is attractive and valuable enough to encourage user clicks and engagement.

[0046] The positive trending topic content generation submodule is used to generate more content related to positive trending topics and to distribute more traffic to the search engines where the content related to positive trending topics is located. This can fully promote the spread of positive content and increase the exposure and participation of the content related to positive trending topics.

[0047] Furthermore, the optimized traffic coverage module includes a relational path planning submodule and a traffic transmission path switching submodule;

[0048] The relationship path planning submodule is used to input the low traffic coverage relationship path into the path planning model to plan a new relationship path. The path planning model can be trained to generate a new relationship path with higher traffic coverage than the input path.

[0049] The traffic transmission path switching submodule is used to change the traffic transmission path. By transmitting traffic on the new path, unnecessary transit paths and transmission distances can be reduced, which can significantly improve the loading speed of content and improve the user experience.

[0050] An AI-based cross-platform content operation optimization method includes the following optimization steps:

[0051] S01: Collect content performance data on social media platforms, including user browsing paths, purchase records, number of new users browsing content, number of new fans, number of users participating in content brand activities and interactions, number of purchasing users, and number of users browsing content.

[0052] S02: Analyze the user's browsing path, generate a visualized user journey image, identify hotspots in the image, and identify information about media and platforms that the user is active in and susceptible to.

[0053] S03: Identify patterns in purchase records to obtain analysis results on purchase peaks and repeat purchase behaviors in specific time periods;

[0054] S04: Calculate the percentage of new users who browse the content and convert them into followers of the brand's social media accounts. Obtain follower conversion rate data, compare the follower conversion rates of different types of content, and draw the analysis results of the content that is most effective in attracting users to become followers of the platform account.

[0055] S05: Calculate content engagement rates to obtain content engagement data. Compare engagement rates for different types of content to determine which types of content attract users to participate in content-branded activities and interactions to the highest degree.

[0056] S06: Calculate the ratio of purchasing users to browsing content users to obtain purchase ratio data; compare the proportion of different types of content that guide users to complete purchases to obtain the analysis results of which types of content guide users to complete purchase behavior with the highest proportion;

[0057] S07: Create different types and formats of content about the brand story based on content performance data analysis results, brand story, conversion rate data analysis results, and product information analysis results;

[0058] S08: Identify the usage of hashtags on social media platforms, analyze their popularity and user engagement, and thus determine whether the topic will become a trending topic;

[0059] S09: Collect identified but unlabeled trending topics and categorize them;

[0060] S10: Label negative hot topics according to the preset negative impact topic list, and then filter negative hot topics in batches;

[0061] S11: Generate more content related to positive trending topics, drive more traffic to search engines where such content is found, and increase the exposure and engagement of content related to positive trending topics; cross-platform promotion can help reach a wider audience and increase the exposure of topics.

[0062] S12: Based on the results of user behavior data analysis, recommend the target platform for users to jump to the content;

[0063] S13: Generate dedicated cross-platform links for each lead generation content, which point to specific content on the target platform;

[0064] S14: Obtain and parse the network address of the corresponding platform to be redirected, and generate a redirection path based on the parsing result;

[0065] S15: Monitor the redirection process and the loading status of the target platform content after a user clicks a cross-platform link;

[0066] S16: After the content on the target platform is loaded, the redirected content will be returned to the original social media platform according to the original redirect path to avoid interfering with the user's experience on the target platform;

[0067] S17: Create various traffic-driving content, adding traffic-driving functions and elements to the existing brand content. These elements include trailers, highlight displays, exclusive offers, and limited-time events, ensuring that the content is attractive and valuable enough to stimulate user clicks and participation.

[0068] S18: Collect the relationship paths of traffic within a set time period and the coverage on the relationship paths;

[0069] S19: Calculate the coverage rate of traffic on the relationship path within a set time period. If the calculated traffic coverage rate of the relationship path is less than a preset threshold, the relationship path is marked as a low traffic coverage relationship path. If the calculated traffic coverage rate of the relationship path is greater than or equal to the preset threshold, the relationship path is marked as a high traffic coverage relationship path. The high traffic coverage relationship path will not be input into the path planning model.

[0070] S20: Input the relationship path marked as having low traffic coverage into the path planning model, plan a new relationship path, the path planning model can be trained to obtain a new relationship path with higher traffic coverage than the input, change the traffic transmission path, and transmit traffic on the new relationship path;

[0071] S21: Repeat S01-S20.

[0072] The beneficial effects of the cross-platform content operation optimization system and method based on artificial intelligence of the present invention are as follows:

[0073] The trending topic identification submodule is used to identify the usage of topic tags on social media platforms, analyze their popularity and user engagement, and thus determine whether a topic has become a trending topic. This submodule can more quickly identify and filter key information indicating whether a topic has become a trending topic. The negative trending topic filtering submodule is used to label negative trending topics according to a preset negative topic list, and then filter them in batches. Labeled negative trending topics will no longer be collected by the trending topic collection submodule as a basis for generating related content, effectively filtering negative topics without causing data overload due to the large amount of data. The target platform selection submodule is used to recommend target platforms for users to redirect to based on user behavior data analysis results. The cross-platform link generation submodule is used to generate dedicated links for each type of content. Cross-platform links, pointing to specific content on the target platform, ensure link compatibility and security, allowing users to smoothly navigate between platforms. The redirection path generation submodule obtains and parses the network address of the target platform, generating a redirection path based on the parsing result. This redirection path is the redirection path for the referral content. The redirection and loading monitoring submodule monitors the redirection process and the loading status of the target platform content after the user clicks the cross-platform link. The referral content recycling submodule recycles the referral content back to the original social media platform along the original redirection path after the target platform content has finished loading, avoiding interference with the user experience on the target platform. Through these steps, users from one platform are converted to another, attracting and guiding users to engage and interact across platforms, thus better serving cross-platform content operation. The traffic analysis submodule calculates the coverage of traffic along a relationship path within a set time period, enabling more precise monitoring of network traffic patterns and trends. If the calculated traffic coverage of a relationship path is less than a preset threshold, the path is marked as a low-traffic-coverage path, allowing for targeted optimization and improved network resource utilization. Conversely, if the calculated traffic coverage is greater than or equal to the preset threshold, the path is marked as a high-traffic-coverage path. The relationship path planning submodule inputs the low-traffic-coverage path into a path planning model to plan a new path. This model can train a new path with higher traffic coverage than the initial input, reducing network resource requirements and potentially lowering network operation and maintenance costs. The traffic transmission path switching submodule changes the traffic transmission path. By transmitting traffic along the new path, unnecessary transit paths and distances are reduced, significantly improving content loading speed and enhancing user experience. Attached Figure Description

[0074] Figure 1This is a system architecture diagram of a cross-platform content operation optimization system based on artificial intelligence according to the present invention;

[0075] Figure 2 This is a system architecture diagram of the information and data collection module of an artificial intelligence-based cross-platform content operation optimization system of the present invention;

[0076] Figure 3 This is a system architecture diagram of the data and information analysis module of a cross-platform content operation optimization system based on artificial intelligence, according to the present invention.

[0077] Figure 4 This is a system architecture diagram of the hot topic collection and management module of a cross-platform content operation optimization system based on artificial intelligence according to the present invention;

[0078] Figure 5 This is a system architecture diagram of the traffic acquisition function management module of a cross-platform content operation optimization system based on artificial intelligence according to the present invention;

[0079] Figure 6 This is a system architecture diagram of the content creation module of a cross-platform content operation optimization system based on artificial intelligence according to the present invention;

[0080] Figure 7 This is a system architecture diagram of the optimized traffic coverage module of an artificial intelligence-based cross-platform content operation optimization system of the present invention;

[0081] Figure 8 This is a system architecture diagram of the content performance data collection submodule of an AI-based cross-platform content operation optimization system according to the present invention.

[0082] Figure 9 This is a system architecture diagram of the user behavior data analysis submodule of an AI-based cross-platform content operation optimization system according to the present invention.

[0083] 1-Information and Data Collection Module, 11-Enterprise Information Collection Sub-module, 12-Content Performance Data Collection Sub-module, 121-User Behavior Data Collection Unit, 122-Traffic Data Collection Unit, 13-Conversion Rate Data Collection Sub-module, 2-Data and Information Analysis Module, 21-Brand Information Analysis Sub-module, 22-Product Information Analysis Sub-module, 23-User Behavior Data Analysis Sub-module, 231-User Browsing Path Analysis Unit, 232-Purchase Record Analysis Unit, 233-Fan Conversion Rate Analysis Unit, 234-Content Engagement Rate Analysis Unit, 235-User Purchase Rate Analysis Unit, 24-Traffic Analysis Sub-module, 3-Hot Topic Collection The system comprises the following modules: 31-Hot Topic Identification Submodule, 32-Hot Topic Collection Submodule, 33-Negative Hot Topic Filtering Submodule, 4-Traffic Acquisition Function Management Submodule, 41-Target Platform Selection Submodule, 42-Cross-Platform Link Generation Submodule, 43-Jump Path Generation Submodule, 44-Jump and Loading Monitoring Submodule, 45-Traffic Acquisition Content Recycling Submodule, 5-Content Creation Module, 51-Branded Content Creation Submodule, 52-Traffic Acquisition Content Creation Submodule, 53-Positive Hot Topic Content Generation Submodule, 6-Optimized Traffic Coverage Module, 61-Relationship Path Planning Submodule, 62-Traffic Transmission Path Switching Submodule, and 7-Intelligent Targeting Module. DETAILED DESCRIPTION

[0084] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0085] like Figure 1-9 As shown, this invention discloses a cross-platform content operation optimization system based on artificial intelligence, comprising an information and data collection module 1, a data and information analysis module 2, a hot topic collection and management module 3, a traffic generation function management module 4, a content creation module 5, a traffic coverage optimization module 6, and an intelligent delivery module 7. The input of the data and information analysis module 2 is connected to the output of the information and data collection module 1; the input of the traffic generation function management module 4 is connected to the output of the data and information analysis module 2; the input of the content creation module 5 is connected to the outputs of the data and information analysis module 2, the hot topic collection and management module 3, and the traffic generation function management module 4; the input of the traffic coverage optimization module 6 is connected to the output of the data and information analysis module 2; and the input of the intelligent delivery module 7 is connected to the output of the content creation module 5.

[0086] The information and data collection module 1 is used to collect enterprise information, content performance data, and conversion rate data;

[0087] The data and information analysis module 2 is used to analyze the collected information and data to obtain analysis results;

[0088] The hot topic collection and management module 3 is used to identify hot topics on social media platforms and manage the collected hot topics.

[0089] The traffic acquisition function management module 4 is used to create and manage traffic acquisition functions for traffic acquisition content.

[0090] The content creation module 5 is used to create content of different types and formats. The content types include brand-type content, traffic-driving content, and positive trending topic-type content. The content formats include video format, image and text format, and web page format.

[0091] The optimized traffic coverage module 6 is used to generate new traffic transmission paths;

[0092] The intelligent delivery module 7 is used to deliver the created content to various social media platforms. It delivers traffic to the content on the social media platform according to the preset traffic transmission path. Cross-platform promotion can help reach a wider audience and increase the exposure of the content. The traffic transmission path has a great impact on the content loading speed. The traffic transmission path includes unidirectional paths and relational paths. The relational path represents the sum of two or more connected unidirectional paths.

[0093] The information and data collection module 1 includes an enterprise information collection submodule 11, a content performance data collection submodule 12, and a conversion rate data collection submodule 13;

[0094] The enterprise information collection submodule 11 is used to connect to the enterprise information storage system, obtain enterprise information from the enterprise information storage system, and collect enterprise information, including brand information and product information.

[0095] The content performance data collection submodule 12 is used to collect content performance data from social media platforms;

[0096] The conversion rate data collection submodule 13 is used to collect conversion rate data, including fan conversion rate data, content participation rate data, and purchase ratio data.

[0097] The content performance data collection submodule 12 includes a user behavior data collection unit 121 and a traffic data collection unit 122;

[0098] The user behavior data collection unit 121 is used to collect users' browsing paths, purchase records, the number of new users browsing content, the number of fan growth, the number of users participating in content brand activities and interactions, the number of purchasing users, and the number of users browsing content.

[0099] The traffic data collection unit 122 is used to collect the relationship path of traffic within a set time period and the coverage on the relationship path. The relationship path of traffic within the set time period usually refers to the user's behavior trajectory on the network platform or application within a specific time period, which includes the pages visited by the user, the links clicked, the videos watched, the interactions participated in, etc.

[0100] The data and information analysis module 2 includes a brand information analysis submodule 21, a product information analysis submodule 22, a user behavior data analysis submodule 23, and a traffic analysis submodule 24.

[0101] The brand information analysis submodule 21 is used to analyze brand information and obtain brand information analysis results, which include the brand's personality characteristics, brand language style, emotional tone, brand image and brand story.

[0102] The product information analysis submodule 22 is used to analyze product information and obtain product information analysis results. The product information analysis results include the product's functions, characteristics, user benefits, and usage scenarios, and identify the differences and innovations between the product and competing products.

[0103] The user behavior data analysis submodule 23 is used to analyze user behavior data and obtain analysis results, including information on user activity and susceptible media and platforms, purchase peaks and repeat purchase behaviors during specific time periods.

[0104] By calculating the coverage of traffic on the relationship path within a set time period through the traffic analysis submodule 24, the patterns and trends of network traffic can be monitored more accurately. By marking the relationship path with a calculated traffic coverage rate less than a preset threshold as a low traffic coverage relationship path, these paths can be optimized in a targeted manner to improve the efficiency of network resource utilization. If the calculated traffic coverage rate of the relationship path is greater than or equal to the preset threshold, the relationship path is marked as a high traffic coverage relationship path.

[0105] The user behavior data analysis submodule 23 includes a user browsing path analysis unit 231, a purchase record analysis unit 232, a fan conversion rate analysis unit 233, a content participation rate analysis unit 234, and a user purchase rate analysis unit 235.

[0106] The user's browsing path analysis unit 231 is used to generate a visualized user journey image by analyzing the user's browsing path, identify hotspots in the image, and identify information about media and platforms that the user is active in and susceptible to.

[0107] The purchase record analysis unit 232 is used to analyze purchase records and, by identifying patterns in the purchase records, to obtain analysis results of purchase peaks and repeat purchase behaviors in a specific time period.

[0108] The fan conversion rate analysis unit 233 is used to calculate the proportion of new users who browse content and convert them into fans of the brand's social media account, obtain fan conversion rate data, compare the fan conversion rates of different types of content, and obtain the content analysis results that are most efficient at attracting users to convert into fans of the platform account.

[0109] The content participation rate analysis unit 234 is used to calculate the content participation rate, obtain content participation rate data, compare the participation rates of different types of content, and obtain the content analysis results that attract users to participate in content brand activities and interactions to the greatest extent.

[0110] The user purchase rate analysis unit 235 is used to calculate the ratio of the number of users who make purchases to the number of users who browse content, obtain purchase ratio data, compare the proportion of different types of content that guide users to complete purchases, and obtain the analysis result of the content that guides users to complete purchase behavior the highest.

[0111] The hot topic collection and management module 3 includes a hot topic identification submodule 31, a hot topic collection submodule 32, and a negative hot topic filtering submodule 33;

[0112] The hot topic identification submodule 31 is used to identify the usage of topic tags on social media platforms, analyze their popularity and user participation, and thus determine whether the topic has become a hot topic.

[0113] The hot topic collection submodule 32 is used to collect identified but unlabeled hot topics and classify them, including positive hot topics and negative hot topics.

[0114] The negative hot topic filtering submodule 33 is used to set labels for negative hot topics according to a preset negative topic list, and then filter them in batches. The labeled negative hot topics will no longer be collected by the hot topic collection submodule 32 as a basis for generating related content. It can effectively filter negative topics and will not cause data overload due to the large amount of data.

[0115] The traffic acquisition function management module 4 includes a target platform selection submodule 41, a cross-platform link generation submodule 42, a jump path generation submodule 43, a jump and loading monitoring submodule 44, and a traffic acquisition content recycling submodule 45.

[0116] The target platform selection submodule 41 is used to recommend target platforms for users to jump to based on the results of user behavior data analysis.

[0117] The cross-platform link generation submodule 42 is used to generate dedicated cross-platform links for each traffic-generating content. These links point to specific content on the target platform, ensuring the compatibility and security of the links so that users can smoothly jump across platforms.

[0118] The redirection path generation submodule 43 is used to obtain and parse the network address of the corresponding platform to be redirected, and generate a redirection path based on the parsing result. The redirection path is the redirection path of the traffic-generating content.

[0119] The jump and loading monitoring submodule 44 is used to monitor the jump process and the loading status of the target platform content after the user clicks on the cross-platform link;

[0120] The content recycling submodule 45 is used to recycle the traffic-generating content back to the original social media platform according to the original redirect path after the content is loaded on the target platform, so as to avoid interfering with the user's experience on the target platform. By converting users from one platform to another, it attracts and guides users to achieve cross-platform attention and interaction, and can better serve cross-platform content operation.

[0121] The content creation module 5 includes a brand content creation submodule 51, a traffic-driving content creation submodule 52, and a positive trending topic content generation submodule 53;

[0122] The brand content creation submodule 51 is used to create various types of brand content, and to create different types and formats of content about brand stories based on content performance data analysis results, brand information analysis results, conversion rate data analysis results and product information analysis results.

[0123] The content creation submodule 52 is used to create various types of content that drives traffic, adding traffic-driving functions and elements to the existing brand content. These elements include trailers, highlight displays, exclusive offers, and limited-time events. The goal is to ensure that the content is attractive and valuable enough to encourage user clicks and engagement.

[0124] The positive trending topic content generation submodule 53 is used to generate more content related to positive trending topics and to distribute more traffic to the search engines where the content related to positive trending topics is located. This can fully promote the spread of positive content and increase the exposure and participation of the content related to positive trending topics.

[0125] The optimized traffic coverage module 6 includes a relational path planning submodule 61 and a traffic transmission path switching submodule 62;

[0126] The relationship path planning submodule 61 is used to input the low traffic coverage relationship path into the path planning model to plan a new relationship path. The path planning model can be trained to generate a new relationship path with higher traffic coverage than the input path, which can reduce the demand for network resources and thus potentially reduce the cost of network operation and maintenance.

[0127] The traffic transmission path switching submodule 62 is used to change the traffic transmission path. By transmitting traffic on the new path, unnecessary transit paths and transmission distances can be reduced, which can significantly improve the loading speed of content and improve the user experience.

[0128] An AI-based cross-platform content operation optimization method includes the following optimization steps:

[0129] S01: Collect content performance data on social media platforms, including user browsing paths, purchase records, number of new users browsing content, number of new fans, number of users participating in content brand activities and interactions, number of purchasing users, and number of users browsing content.

[0130] S02: Analyze the user's browsing path, generate a visualized user journey image, identify hotspots in the image, and identify information about media and platforms that the user is active in and susceptible to.

[0131] S03; Identify patterns in purchase records to obtain analysis results on purchase peaks and repeat purchase behaviors in specific time periods;

[0132] S04: Calculate the percentage of new users who browse the content and convert them into followers of the brand's social media accounts. Obtain follower conversion rate data, compare the follower conversion rates of different types of content, and draw the analysis results of the content that is most effective in attracting users to become followers of the platform account.

[0133] S05: Calculate content engagement rates to obtain content engagement data. Compare engagement rates for different types of content to determine which types of content attract users to participate in content-branded activities and interactions to the highest degree.

[0134] S06: Calculate the ratio of purchasing users to browsing content users to obtain purchase ratio data; compare the proportion of different types of content that guide users to complete purchases to obtain the analysis results of which types of content guide users to complete purchase behavior with the highest proportion;

[0135] S07: Create different types and formats of content about the brand story based on content performance data analysis results, brand story, conversion rate data analysis results, and product information analysis results;

[0136] S08: Identify the usage of hashtags on social media platforms, analyze their popularity and user engagement, and thus determine whether the topic will become a trending topic;

[0137] S09: Collect identified but unlabeled trending topics and categorize them;

[0138] S10: Label negative hot topics according to the preset negative impact topic list, and then filter negative hot topics in batches;

[0139] S11: Generate more content related to positive trending topics, drive more traffic to search engines where such content is found, and increase the exposure and engagement of content related to positive trending topics; cross-platform promotion can help reach a wider audience and increase the exposure of topics.

[0140] S12: Based on the results of user behavior data analysis, recommend the target platform for users to jump to the content;

[0141] S13: Generate dedicated cross-platform links for each lead generation content, which point to specific content on the target platform;

[0142] S14: Obtain and parse the network address of the corresponding platform to be redirected, and generate a redirection path based on the parsing result;

[0143] S15: Monitor the redirection process and the loading status of the target platform content after a user clicks a cross-platform link;

[0144] S16: After the content on the target platform is loaded, the redirected content will be returned to the original social media platform according to the original redirect path to avoid interfering with the user's experience on the target platform;

[0145] S17: Create various traffic-driving content, adding traffic-driving functions and elements to the existing brand content. These elements include trailers, highlight displays, exclusive offers, and limited-time events, ensuring that the content is attractive and valuable enough to stimulate user clicks and participation.

[0146] S18: Collect the relationship paths of traffic within a set time period and the coverage on the relationship paths;

[0147] S19: Calculate the coverage rate of traffic on the relationship path within a set time period. If the calculated traffic coverage rate of the relationship path is less than a preset threshold, the relationship path is marked as a low traffic coverage relationship path. If the calculated traffic coverage rate of the relationship path is greater than or equal to the preset threshold, the relationship path is marked as a high traffic coverage relationship path. The high traffic coverage relationship path will not be input into the path planning model.

[0148] S20: Input the relationship path marked as having low traffic coverage into the path planning model, plan a new relationship path, the path planning model can be trained to obtain a new relationship path with higher traffic coverage than the input, change the traffic transmission path, and transmit traffic on the new relationship path;

[0149] S21: Repeat S01-S20.

[0150] The beneficial effects of the cross-platform content operation optimization system and method based on artificial intelligence of the present invention are as follows:

[0151] The trending topic identification submodule is used to identify the usage of topic tags on social media platforms, analyze their popularity and user engagement, and thus determine whether a topic has become a trending topic. This submodule can more quickly identify and filter key information indicating whether a topic has become a trending topic. The negative trending topic filtering submodule is used to label negative trending topics according to a preset negative topic list, and then filter them in batches. Labeled negative trending topics will no longer be collected by the trending topic collection submodule as a basis for generating related content, effectively filtering negative topics without causing data overload due to the large amount of data. The target platform selection submodule is used to recommend target platforms for users to redirect to based on user behavior data analysis results. The cross-platform link generation submodule is used to generate dedicated links for each type of content. Cross-platform links, pointing to specific content on the target platform, ensure link compatibility and security, allowing users to smoothly navigate between platforms. The redirection path generation submodule obtains and parses the network address of the target platform, generating a redirection path based on the parsing result. This redirection path is the redirection path for the referral content. The redirection and loading monitoring submodule monitors the redirection process and the loading status of the target platform content after the user clicks the cross-platform link. The referral content recycling submodule recycles the referral content back to the original social media platform along the original redirection path after the target platform content has finished loading, avoiding interference with the user experience on the target platform. Through these steps, users from one platform are converted to another, attracting and guiding users to engage and interact across platforms, thus better serving cross-platform content operation. The traffic analysis submodule calculates the coverage of traffic along a relationship path within a set time period, enabling more precise monitoring of network traffic patterns and trends. If the calculated traffic coverage of a relationship path is less than a preset threshold, the path is marked as a low-traffic-coverage path, allowing for targeted optimization and improved network resource utilization. Conversely, if the calculated traffic coverage is greater than or equal to the preset threshold, the path is marked as a high-traffic-coverage path. The relationship path planning submodule inputs the low-traffic-coverage path into a path planning model to plan a new path. This model can train a new path with higher traffic coverage than the initial input, reducing network resource requirements and potentially lowering network operation and maintenance costs. The traffic transmission path switching submodule changes the traffic transmission path. By transmitting traffic along the new path, unnecessary transit paths and distances are reduced, significantly improving content loading speed and enhancing user experience.

[0152] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0153] The present invention and its embodiments have been described above. This description is not restrictive. The accompanying drawings are only one embodiment of the present invention. The actual content is not limited thereto. In short, if a person skilled in the art is inspired by this description and designs a similar structure and embodiment without departing from the spirit of the present invention, such design should fall within the protection scope of the present invention.

Claims

1. A cross-platform content operation optimization system based on artificial intelligence, characterized by: The system comprises an information and data collection module (1), a data and information analysis module (2), a hot topic collection management module (3), a traffic diversion function management module (4), a content creation module (5), a traffic coverage optimization module (6) and an intelligent delivery module (7); the input end of the data and information analysis module (2) is connected to the output end of the information and data collection module (1), the input end of the traffic diversion function management module (4) is connected to the output end of the data and information analysis module (2), the input end of the content creation module (5) is respectively connected to the output end of the data and information analysis module (2), the output end of the hot topic collection management module (3) and the output end of the traffic diversion function management module (4), the input end of the traffic coverage optimization module (6) is connected to the output end of the data and information analysis module (2), and the input end of the intelligent delivery module (7) is connected to the output end of the content creation module (5); The information and data collection module (1) is used to collect enterprise information, content performance data and conversion rate data; The data and information analysis module (2) is used to analyze the collected information and data to obtain analysis results; The hot topic collection and management module (3) is used to identify hot topics on the social media platform and manage the collected hot topics; The traffic diversion function management module (4) is used to create a traffic diversion function for the traffic diversion content and manage the traffic diversion function; The traffic diversion function management module (4) includes a target platform selection submodule (41), a cross-platform link generation submodule (42), a jump path generation submodule (43), a jump and load monitoring submodule (44) and a traffic diversion content recovery submodule (45); The target platform selection submodule (41) is used to recommend a target platform for redirecting content to the user based on the analysis results of the user behavior data; The cross-platform link generation submodule (42) is used to generate a dedicated cross-platform link for each diversion content, and these links point to the specific content of the target platform; The jump path generation submodule (43) is used to obtain and parse the network address of the corresponding platform to be jumped to, and generate a jump path according to the parsing result, wherein the jump path is the jump path of the diversion content; The jump and loading monitoring submodule (44) is used to monitor the jump process after the user clicks the cross-platform link and the loading status of the target platform content; The traffic diversion content recovery submodule (45) is used to recover the traffic diversion content to the original social media platform according to the original jump path after the content loading on the target platform is completed; The content creation module (5) is used to create content of different types and formats. The content types include brand type content, traffic diversion type content and active hot topic type content. The content formats include video format, graphic format and web page format. The optimized traffic coverage module (6) is used to generate a new traffic transmission path; The traffic coverage optimization module (6) comprises a relationship path planning submodule (61) and a traffic transmission path switching submodule (62); The relational path planning submodule (61) is used to input the low flow coverage relational path into the path planning model to plan a new relational path, and the path planning model can train a new relational path with a higher flow coverage than the input one; The traffic transmission path switching submodule (62) is used to change the traffic transmission path and transmit traffic on a new relationship path; The intelligent delivery module (7) is used to deliver the created content to various social media platforms, and deliver traffic to the content of the social media platform according to a preset traffic transmission path, wherein the traffic transmission path affects the content loading speed, and the traffic transmission path includes a unidirectional path and a relational path, wherein the relational path represents the sum of two or more connected unidirectional paths.

2. The cross-platform content operation optimization system based on artificial intelligence according to claim 1, characterized in that: The information and data collection module (1) comprises an enterprise information collection submodule (11), a content performance data collection submodule (12) and a conversion rate data collection submodule (13); The enterprise information collection submodule (11) is used to connect to the enterprise information storage system, obtain enterprise information from the enterprise information storage system, and collect enterprise information, wherein the enterprise information includes brand information and product information; The content performance data collection submodule (12) is used to collect content performance data of the social media platform; The conversion rate data collection submodule (13) is used to collect conversion rate data, including fan conversion rate data, content participation rate data and purchase ratio data.

3. The cross-platform content operation optimization system based on artificial intelligence according to claim 2, characterized in that: The content performance data collection submodule (12) includes a user behavior data collection unit (121) and a flow data collection unit (122); The user behavior data collection unit (121) is used to collect users' browsing paths, purchase records, the number of new users browsing content, the number of fans growing, the number of users participating in content brand activities and interactions, the number of purchasing users and the number of users browsing content; The flow data collection unit (122) is used to collect the relationship paths of the flow within a set time period and the coverage on the relationship paths.

4. The cross-platform content operation optimization system based on artificial intelligence according to claim 1, characterized in that: The data and information analysis module (2) comprises a brand information analysis submodule (21), a product information analysis submodule (22), a user behavior data analysis submodule (23) and a traffic analysis submodule (24); The brand information analysis submodule (21) is used to analyze brand information to obtain brand information analysis results, wherein the brand information analysis results include brand personality characteristics, brand language style, emotional tone, brand image and brand story; The product information analysis submodule (22) is used to analyze product information to obtain product information analysis results, wherein the product information analysis results include product functions, characteristics, user benefits and usage scenarios to identify differences and innovations between the product and competing products; The user behavior data analysis submodule (23) is used to analyze the user behavior data to obtain analysis results, which include information on the media and platforms where the user is active and susceptible, purchase peaks in a specific time period, and repeated purchase behavior; The traffic analysis submodule (24) is used to calculate the coverage rate of the traffic on the relationship path within a set time period. If the calculated traffic coverage rate of the relationship path is less than a preset threshold, the relationship path is marked as a low traffic coverage relationship path. If the calculated traffic coverage rate of the relationship path is greater than or equal to the preset threshold, the relationship path is marked as a high traffic coverage relationship path.

5. The cross-platform content operation optimization system based on artificial intelligence according to claim 4, characterized in that: The user behavior data analysis submodule (23) includes a user browsing path analysis unit (231), a purchase record analysis unit (232), a fan conversion rate analysis unit (233), a content participation rate analysis unit (234) and a user purchase rate analysis unit (235); The user browsing path analysis unit (231) is used to generate a visual user journey image by analyzing the user's browsing path, identify hot spots in the image, and identify information about the media and platforms where the user is active and susceptible to influence; The purchase record analysis unit (232) is used to analyze the purchase records, and obtain the analysis results of the purchase peak and repeated purchase behavior in a specific time period by identifying the patterns in the purchase records; The fan conversion rate analysis unit (233) is used to calculate the proportion of new users who browse the content and are converted into fans of the brand social media account, obtain fan conversion rate data, compare the fan conversion rates of different types of content, and obtain the content analysis result with the highest efficiency in attracting users to be converted into fans of the brand social media account; The content participation rate analysis unit (234) is used to calculate the content participation rate, obtain content participation rate data, compare the participation rates of different types of content, and obtain the content analysis results that attract users to participate in content brand activities and interactions to the highest degree; The user purchase rate analysis unit (235) is used to calculate the ratio of the number of purchasing users to the number of content browsing users, obtain purchase ratio data, compare the ratios of different types of content that guide users to complete purchases, and obtain the content analysis result with the highest ratio of guiding users to complete purchases.

6. The cross-platform content operation optimization system based on artificial intelligence according to claim 1, characterized in that: The hot topic collection and management module (3) comprises a hot topic identification submodule (31), a hot topic collection submodule (32) and a negative hot topic filtering submodule (33); The hot topic identification submodule (31) is used to identify the usage of topic tags on the social media platform, analyze their popularity and user participation, and thus determine whether the topic has become a hot topic; The hot topic collection submodule (32) is used to collect identified and unlabeled hot topics and classify the hot topics, wherein the hot topics include positive hot topics and negative hot topics; The negative hot topic filtering submodule (33) is used to set labels for negative hot topics according to a preset negative impact topic table, and then perform batch filtering. The labeled negative hot topics will no longer be collected by the hot topic collecting submodule (32) as a basis for generating related content.

7. The cross-platform content operation optimization system based on artificial intelligence according to claim 1, characterized in that: The content creation module (5) includes a brand content creation submodule (51), a traffic diversion content creation submodule (52) and a positive hot topic content generation submodule (53); The brand content creation submodule (51) is used to create various brand contents, and to create contents of different types and formats about brand stories based on the content performance data analysis results, the brand information analysis results, the conversion rate data analysis results and the product information analysis results; The traffic diversion content creation submodule (52) is used to create various traffic diversion contents, adding traffic diversion functions and traffic diversion elements on the basis of the original brand content, wherein the traffic diversion elements include trailers, highlight displays, exclusive offers and limited-time activities; The active hot topic content generation submodule (53) is used to generate more content related to active hot topics and deliver more traffic to the search engine where the content related to active hot topics is located.

8. A cross-platform content operation optimization method based on artificial intelligence, using a cross-platform content operation optimization system based on artificial intelligence as described in any one of claims 1 to 7, characterized in that: The optimization steps include: S01: Collect content performance data on social media platforms, including users’ browsing paths, purchase records, the number of new users browsing content, the number of fans added, the number of users participating in content brand activities and interactions, the number of purchasing users, and the number of users browsing content; S02: Analyze the user's browsing path, generate a visual user journey image, identify hot spots in the image, and identify information about the media and platforms where users are active and susceptible; S03: Identify patterns in purchase records and obtain analysis results of purchase peaks and repeated purchase behaviors in specific time periods; S04: Calculate the proportion of new users who browse the content and are converted into fans of the brand's social media account, obtain fan conversion rate data, compare the fan conversion rates of different types of content, and obtain the most efficient content analysis results for attracting users to convert into fans of the brand's social media account; S05: Calculate the content participation rate, obtain content participation rate data, compare the participation rates of different types of content, and obtain the analysis results of which types of content attract users to participate in content brand activities and interact with the highest degree; S06: Calculate the ratio of the number of users who purchased the content to the number of users who browsed the content, obtain purchase ratio data, compare the ratio of different types of content that guide users to complete purchases, and obtain the analysis results of which type of content has the highest ratio of users who complete purchases; S07: Create different types and formats of content about brand stories based on the content performance data analysis results, brand information analysis results, conversion rate data analysis results and product information analysis results; S08: Identify the usage of topic tags on social media platforms and analyze their popularity and user engagement to determine whether the topic has become a hot topic; S09: Collect the identified and unlabeled hot topics and classify them; S10: setting labels for negative hot topics according to a preset negative impact topic table, and then filtering the negative hot topics in batches; S11: Generate more content related to positive hot topics and deliver more traffic to search engines where content related to positive hot topics is located; S12: Based on the analysis results of user behavior data, recommend to users the target platform for redirecting content; S13: Generate dedicated cross-platform links for each diversion content, where these links point to specific content on the target platform; S14: Obtain and parse the network address of the corresponding platform to be jumped to, and generate a jump path according to the parsing result; S15: monitoring the jump process after the user clicks the cross-platform link and the loading status of the target platform content; S16: After the content of the target platform is loaded, the diversion content is recycled to the original social media platform according to the original jump path; S17: Create various traffic-generating contents, and add traffic-generating functions and elements based on the original brand content. The traffic-generating elements include trailers, highlight displays, exclusive offers, and limited-time events; S18: Collect the relationship paths of traffic within a set time period and the coverage on the relationship paths; S19: Calculate the coverage of the traffic on the relationship path within a set time period. If the calculated traffic coverage of the relationship path is less than a preset threshold, mark the relationship path as a low traffic coverage relationship path; If the calculated flow coverage of the relationship path is greater than or equal to a preset threshold, the relationship path is marked as a relationship path with excellent flow coverage, and the relationship path with excellent flow coverage will not be input into the path planning model; S20: inputting the relational path marked as having low traffic coverage into a path planning model to plan a new relational path, wherein the path planning model can train a new relational path having a higher traffic coverage than the input one, changing the traffic transmission path, and transmitting traffic on the new relational path; S21: Repeat S01-S20.

Images