Program propagation brand value evaluation method and system

Abstract

The invention provides a program propagation brand value evaluation method and system. The method comprises the following steps: acquiring network propagation data and hot search data about a program propagation brand from each network platform; preprocessing the network propagation data and the hot search data; evaluating a propagation value based on the preprocessed network propagation data and the hot search data; and processing the propagation value according to a media overflow value model constructed by a machine learning algorithm to obtain the media overflow value of the program propagation brand. According to the method, the propagation effect of the brand on the social media and the hot search platform is accurately evaluated and converted into the specific amount, so that the brand is helped to more scientifically evaluate and optimize the return on investment of program delivery, the propagation strategy is optimized, and the brand value is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital media and brand communication, and in particular to a method and system for evaluating the brand value of program communication. Background Art

[0002] Before the digital media era, the evaluation of brand communication effectiveness mainly relied on traditional media channels such as television, radio, newspapers, etc. These evaluation methods are usually based on quantitative indicators such as ratings, listening rates, and circulation, but it is difficult to accurately measure the brand's communication effect on new media channels such as social media. In addition, traditional methods often ignore key elements in the brand communication process, such as emotional factors, user participation, and word-of-mouth communication.

[0003] With the popularization of digital media and social media, brand communication channels have undergone profound changes. Social media platforms such as Weibo, Douyin, Kuaishou, Xiaohongshu, etc., with their huge user base and high interactivity, have become important positions for brand communication. These platforms not only provide rich user data, but also enable brands to interact directly with consumers, collect feedback and adjust communication strategies.

[0004] In the prior art, the EMV (Enhanced Media Value) model is an innovative method that has emerged in the field of media communication spillover value assessment in recent years. The calculation method of the existing EMV model usually includes the following steps: first, calculate the total number of times users see the content (UR), that is, the number of views of each work, such as an article, multiplied by the average viewing time; then calculate the cost (CPM) generated for every 1,000 impressions on each platform; finally, calculate the conversion rate (CR) of the number of impressions. The specific formula is: EMV = UR * CPM * CR / 1000. However, the EMV evaluation method of the prior art is only a simple calculation, ignoring factors such as content being liked, commented on, forwarded, and trending. The factors considered are relatively single, the evaluation is not comprehensive, and the accuracy needs to be improved. Summary of the invention

[0005] Based on the above content, the present invention provides a method and system for evaluating the brand value of program communication, which only solves the technical problems in the prior art that the accuracy of media spillover value evaluation needs to be improved.

[0006] A method for evaluating the brand value of program communication, comprising:

[0007] Step A1, collecting network communication data and hot search data about the program communication brand from various network platforms;

[0008] Step A2, pre-processing network propagation data and hot search data;

[0009] Step A3, evaluating the communication value based on the pre-processed network communication data and hot search data;

[0010] Step A4, processing the communication value according to the media spillover value model constructed by the machine learning algorithm to obtain the media spillover value of the program communication brand.

[0011] Furthermore, in step A1, the network communication data includes the number of reposts, likes, comments, exposure, and number of fans of the original work, and the original work contains both program-related words and brand-related words;

[0012] In step A3, the communication value includes the public opinion value;

[0013] In step A3, the network communication data is analyzed and processed based on the sentiment analysis algorithm, and the public opinion value of each original work is calculated according to the preset public opinion indicators. The preset public opinion indicators include the number of reposts, likes, comments, exposure and number of fans of the original work.

[0014] Furthermore, in step A1, the hot search data includes the popularity value and the duration of the hot words related to the program's brand promotion, and the hot words include both program-related words and brand-related words;

[0015] In step A3, the communication value also includes the hot search value;

[0016] In step A3, the hot search data is analyzed and processed, and the hot search value of each hot word is calculated using preset hot search indicators. The preset hot search indicators include the popularity value and dominance time of the hot word.

[0017] Furthermore, after step A4, the following steps are further included:

[0018] Step A5, calculating the brand's return on investment based on the media spillover value of the program's brand promotion and the cost of the brand's program placement.

[0019] Furthermore, after step A4, the following steps are further included:

[0020] Step A6: Based on the media spillover value of the program’s brand communication, use the intelligent recommendation algorithm to dynamically adjust the brand communication strategy.

[0021] A program dissemination brand value evaluation system is used to execute the aforementioned program dissemination brand value evaluation method, and is characterized by comprising:

[0022] Data collection module, used to collect network dissemination data and hot search data of program brands from various network platforms;

[0023] The preprocessing module is connected to the data collection module and is used to preprocess the network propagation data and hot search data;

[0024] The value assessment module is connected to the preprocessing module and is used to assess the communication value based on the preprocessed network communication data and hot search data;

[0025] The value conversion module is connected to the value assessment module and is used to process the communication value according to the media spillover value model constructed by the machine learning algorithm to obtain the media spillover value of the program placement brand.

[0026] Furthermore, the online communication data includes the number of reposts, likes, comments, exposure, and number of fans of the original works. The original works also contain program-related words and brand-related words.

[0027] Communication value includes public opinion value;

[0028] The value assessment module analyzes and processes network communication data based on the sentiment analysis algorithm, and calculates the public opinion value of each original work according to the preset public opinion indicators. The preset public opinion indicators include the number of reposts, likes, comments, exposure and the number of fans of the original work.

[0029] Furthermore, the hot search data includes the popularity value and dominance time of the hot words related to the program's brand promotion, and the hot words include both program-related words and brand-related words;

[0030] Communication value also includes hot search value;

[0031] The value assessment module analyzes and processes the hot search data and calculates the hot search value of each hot word using preset hot search indicators. The preset hot search indicators include the popularity value of the hot word and the duration of dominance on the list.

[0032] Furthermore, it also includes:

[0033] The return calculation module is connected to the value conversion module and is used to calculate the brand's return on investment based on the media spillover value of the program's brand dissemination and the cost of the brand's program placement.

[0034] Furthermore, it also includes:

[0035] The strategy adjustment module is connected to the value conversion module and is used to dynamically adjust the brand communication strategy based on the media spillover value of the program communication brand using an intelligent recommendation algorithm.

[0036] The beneficial technical effect of the present invention is that the present invention provides a comprehensive, accurate and quantitative method to solve the problem that it is difficult to accurately measure the degree of improvement in brand value caused by social media and trending search platforms in brand communication effect evaluation, and it is difficult to directly convert the communication volume into economic value. It can accurately evaluate the communication effect of the brand on social media and trending search platforms and convert it into a specific amount of money, thereby helping brands to more scientifically evaluate and optimize the return on investment (ROI) of program delivery, optimize communication strategies, evaluate the profitability of individual marketing activities and brands in a competitive environment, and enhance brand value. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A flowchart of the steps of a program communication brand value evaluation method of the present invention;

[0038] Figure 2 The module diagram of a program communication brand value evaluation method of the present invention is shown in FIG. DETAILED DESCRIPTION

[0039] 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.

[0040] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0041] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but they are not intended to limit the present invention.

[0042] See also Figure 1 The present invention provides a method for evaluating the brand value of a program, comprising:

[0043] Step A1, collecting network communication data and hot search data about the program communication brand from various network platforms;

[0044] Step A2, pre-processing network propagation data and hot search data;

[0045] Step A3, evaluating the communication value based on the pre-processed network communication data and hot search data;

[0046] Step A4, processing the communication value according to the media spillover value model constructed by the machine learning algorithm to obtain the media spillover value of the program communication brand.

[0047] Specifically, in step A1, data collection technology is used to collect raw data from social media platforms and hot search platforms across the entire network. These platforms include, but are not limited to, social media such as Weibo, Douyin, Kuaishou, Xiaohongshu, WeChat, and hot search platforms such as Douyin hot search and Weibo hot search. Data collection technology uses crawler technology and API interfaces to obtain data related to brand communication from these platforms, namely network communication data and hot search data, such as the number of reposts, likes, comments, and exposure of original articles, the number of fans of the publishing author, and the popularity value and dominance time of hot words. Comprehensive data collection on multiple platforms and types avoids the evaluation bias that may be caused by a single data source and improves the accuracy and reliability of the evaluation results.

[0048] Specifically, in step A2, data preprocessing technology is used to clean, remove duplicates, and normalize the collected raw data to improve data quality and analysis accuracy. During the data preprocessing process, duplicate, invalid, or abnormal data will be removed to ensure the accuracy and consistency of the data, which will facilitate the effectiveness of subsequent analysis. At the same time, the data is normalized to make data from different platforms and different indicators comparable, providing a basis for subsequent value assessment. Data preprocessing technology associates and fuses data from different sources to form a comprehensive data set.

[0049] The media spillover value model of the present invention converts the public opinion value and hot search value into specific amounts to quantitatively evaluate the economic effect of brand program placement. This technology combines big data analysis and algorithm models to calculate the conversion value of brands on social media and hot search platforms by deeply mining and analyzing the collected data.

[0050] Furthermore, in step A1, the network communication data includes the number of reposts, likes, comments, exposure, and number of fans of the original work, and the original work contains both program-related words and brand-related words;

[0051] In step A3, the communication value includes the public opinion value;

[0052] In step A3, the network communication data is analyzed and processed based on the sentiment analysis algorithm, and the public opinion value of each original work is calculated according to the preset public opinion indicators. The preset public opinion indicators include the number of reposts, likes, comments, exposure and number of fans of the original work.

[0053] The public opinion value assessment technology is based on the pre-processed network communication data, namely public opinion data, and uses natural language processing technology to calculate the public opinion value of the brand on social media. The public opinion value is mainly evaluated based on indicators such as the number of reposts, likes, comments, and exposure of original works such as original articles. These indicators reflect the brand's communication effect and user interaction on social media, and are an important basis for evaluating the brand's public opinion value.

[0054] Use natural language processing (NLP) technology and one of its applications, sentiment analysis algorithms, to judge the sentiment tendency of network communication data on social media. Sentiment analysis algorithms are particularly important for user interaction data such as likes, comments, and forwarding comments. Using sentiment analysis algorithms, we can analyze original works about the program’s brand communication, such as original articles that give positive feedback to the brand, and incorporate users’ sentiment tendencies and interactive behaviors into the evaluation system. In this way, the value of communication can be more accurately and comprehensively evaluated by combining various data. Introducing sentiment analysis algorithms and user engagement indicators (likes, forwarding, comments) can improve the accuracy and depth of evaluation, and can more accurately reflect the brand’s communication effect and user reputation on social media.

[0055] Reposts refer to the number of times a user shares an original work to their social network or personal page. Reposts not only expand the potential audience of the content, but also often reflect the value and appeal of the content itself.

[0056] Likes: Likes are a simple and direct way to show users’ recognition and support for a piece of content.

[0057] Number of comments: Comments represent the interactive communication between viewers and creators and are another important criterion for measuring content interactivity.

[0058] Impressions: Impressions refer to the number of times content is displayed to users, but it is important to note that this does not necessarily mean that all impressions will be converted into actual reading or viewing.

[0059] Number of followers of the publisher: The number of followers refers to the total number of people who follow a specific account and subscribe to its updates.

[0060] The public opinion value of each original work serves as input data for the media spillover value model.

[0061] Furthermore, in step A1, the hot search data includes the popularity value and the duration of the hot words related to the program's brand promotion, and the hot words include both program-related words and brand-related words;

[0062] In step A3, the communication value also includes the hot search value;

[0063] In step A3, the hot search data is analyzed and processed, and the hot search value of each hot word is calculated using preset hot search indicators. The preset hot search indicators include the popularity value and dominance time of the hot word.

[0064] The hot search value assessment technology is based on the pre-processed hot search data and uses algorithms to calculate the hot search value of the brand on the hot search platform. The hot search value is mainly assessed based on indicators such as the popularity value of the hot words and the duration of dominance on the list. These indicators reflect the influence and attention of the brand on the hot search platform and are an important basis for assessing the hot search value of the brand.

[0065] The hot search value of each hot word serves as the input data of the media spillover value model.

[0066] The media spillover value model takes the public opinion value of each original work and the hot search value of each hot word as input, and outputs the media spillover value after processing.

[0067] Furthermore, after step A4, the following steps are further included:

[0068] Step A5, calculating the brand's return on investment based on the media spillover value of the program's brand promotion and the cost of the brand's program placement.

[0069] ROI (Return On Investment) calculation technology is based on the amount calculated by EMV and the cost of brand placement programs to calculate the return on investment of brand placement programs. ROI is one of the important indicators to measure the effect of brand placement programs. It reflects the economic benefits and input-output ratio of brand placement programs.

[0070] The present invention provides a comprehensive, accurate and quantitative method to solve the problems that it is difficult to accurately measure the degree to which social media and hot search platforms enhance brand value in existing technical brand communication effect evaluations, and it is difficult to directly convert communication volume into economic value.

[0071] Furthermore, after step A4, the following steps are further included:

[0072] Step A6: Based on the media spillover value of the program’s brand communication, use the intelligent recommendation algorithm to dynamically adjust the brand communication strategy.

[0073] Establish personalized brand communication strategies based on user portraits and brand needs. For example, understand the age group and gender ratio of the brand's applicable population based on user portraits, and provide the brand with recommendations on programs and delivery methods.

[0074] After the brand is officially placed on the program, the brand communication strategy is dynamically adjusted based on the calculated media spillover value for the brand to refer to and make decisions, such as whether it needs to continue to be placed on the program, and if so, in what way, such as what type of advertising placement. The intelligent recommendation algorithm will comprehensively consider and give brand communication strategy recommendations based on the calculated media spillover value, as well as the collection and analysis of the program's brand network communication data, hot search data, and program playback data, such as the number of platform plays of the program, the popularity of the play, etc. For example, if the number of users watching the program is not high and the discussion is not hot enough, it means that the program is not attractive enough and the program is not popular enough, which will also indirectly affect the popularity of brand communication.

[0075] Specifically, after step A5, the method further includes:

[0076] Step A7: Generate a visualization report based on the media spillover value and the return on investment. The visualization report displays the changing trend of the media spillover value. By directly displaying the changing trend of the media spillover value and the return on investment, etc., it provides intuitive decision support for the brand.

[0077] Specifically, the changing trend of the media spillover value refers to calculating the daily media spillover value on a daily basis and then forming a trend chart in chronological order.

[0078] For the daily media spillover value, the public opinion value of the network communication data is calculated in an incremental form. The new original works added on that day are counted, and the public opinion value of each new original work is calculated based on the new original works. The current media spillover value is calculated based on the hot search data of the day.

[0079] See also Figure 2 The present invention provides a program communication brand value evaluation system, which is used to execute the aforementioned program communication brand value evaluation method, and is characterized by comprising:

[0080] A data collection module (1) is used to collect network dissemination data and hot search data of program brands from various network platforms;

[0081] A preprocessing module (2), connected to the data collection module (1), is used to preprocess the network propagation data and hot search data;

[0082] A value evaluation module (3), connected to the preprocessing module (2), is used to evaluate the communication value based on the preprocessed network communication data and hot search data;

[0083] The value conversion module (4) is connected to the value assessment module (3) and is used to process the communication value according to the media spillover value model constructed by the machine learning algorithm to obtain the media spillover value of the program placement brand.

[0084] Specifically, data collection technology is used to collect raw data from social media platforms and hot search platforms across the entire network. These platforms include, but are not limited to, social media such as Weibo, Douyin, Kuaishou, Xiaohongshu, WeChat, and hot search platforms such as Douyin hot search and Weibo hot search. Data collection technology uses crawler technology and API interfaces to obtain data related to brand communication from these platforms, namely network communication data and hot search data, such as the number of reposts, likes, comments, and exposure of original articles, the number of fans of the publishing author, and the popularity value and dominance time of hot words. Comprehensive data collection on multiple platforms and types avoids the evaluation bias that may be caused by a single data source and improves the accuracy and reliability of the evaluation results.

[0085] Specifically, data preprocessing technology is used to clean, remove duplicates, and normalize the collected raw data to improve data quality and analysis accuracy. During the data preprocessing process, duplicate, invalid, or abnormal data will be removed to ensure the accuracy and consistency of the data, which will facilitate the effectiveness of subsequent analysis. At the same time, the data is normalized to make data from different platforms and different indicators comparable, providing a basis for subsequent value assessment. Data preprocessing technology associates and fuses data from different sources to form a comprehensive data set.

[0086] The media spillover value model of the present invention converts the public opinion value and hot search value into specific amounts to quantitatively evaluate the economic effect of brand program placement. This technology combines big data analysis and algorithm models to calculate the conversion value of brands on social media and hot search platforms by deeply mining and analyzing the collected data.

[0087] Furthermore, the online communication data includes the number of reposts, likes, comments, exposure, and number of fans of the original works. The original works also contain program-related words and brand-related words.

[0088] Communication value includes public opinion value;

[0089] The value assessment module (3) analyzes and processes the network communication data based on the sentiment analysis algorithm, and calculates the public opinion value of each original work according to the preset public opinion indicators. The preset public opinion indicators include the number of reposts, likes, comments, exposure and number of fans of the original work.

[0090] The public opinion value assessment technology is based on the pre-processed network communication data, namely public opinion data, and uses natural language processing technology to calculate the public opinion value of the brand on social media. The public opinion value is mainly evaluated based on indicators such as the number of reposts, likes, comments, and exposure of original works such as original articles. These indicators reflect the brand's communication effect and user interaction on social media, and are an important basis for evaluating the brand's public opinion value.

[0091] Use natural language processing (NLP) technology and one of its applications, sentiment analysis algorithms, to judge the sentiment tendency of network communication data on social media. Sentiment analysis algorithms are particularly important for user interaction data such as likes, comments, and forwarding comments. Using sentiment analysis algorithms, we can analyze original works about the program’s brand communication, such as original articles that give positive feedback to the brand, and incorporate users’ sentiment tendencies and interactive behaviors into the evaluation system. In this way, the value of communication can be more accurately and comprehensively evaluated by combining various data. Introducing sentiment analysis algorithms and user engagement indicators (likes, forwarding, comments) can improve the accuracy and depth of evaluation, and can more accurately reflect the brand’s communication effect and user reputation on social media.

[0092] The public opinion value of each original work serves as input data for the media spillover value model.

[0093] Furthermore, the hot search data includes the popularity value and dominance time of the hot words related to the program's brand promotion, and the hot words include both program-related words and brand-related words;

[0094] Communication value also includes hot search value;

[0095] The value assessment module (3) analyzes and processes the hot search data and calculates the hot search value of each hot word using preset hot search indicators. The preset hot search indicators include the popularity value and the duration of dominance of the hot word.

[0096] The hot search value assessment technology is based on the pre-processed hot search data and uses algorithms to calculate the hot search value of the brand on the hot search platform. The hot search value is mainly assessed based on indicators such as the popularity value of the hot words and the duration of dominance on the list. These indicators reflect the influence and attention of the brand on the hot search platform and are an important basis for assessing the hot search value of the brand.

[0097] The hot search value of each hot word serves as the input data of the media spillover value model.

[0098] The media spillover value model takes the public opinion value of each original work and the hot search value of each hot word as input, and outputs the media spillover value after processing.

[0099] Furthermore, it also includes:

[0100] The return calculation module (5) is connected to the value conversion module (4) and is used to calculate the brand's return on investment based on the media spillover value of the program's brand dissemination and the cost of the brand's program placement.

[0101] ROI (Return On Investment) calculation technology is based on the amount calculated by EMV and the cost of brand placement programs to calculate the return on investment of brand placement programs. ROI is one of the important indicators to measure the effect of brand placement programs. It reflects the economic benefits and input-output ratio of brand placement programs.

[0102] The present invention provides a comprehensive, accurate and quantitative method to solve the problems that it is difficult to accurately measure the degree to which social media and hot search platforms enhance brand value in existing technical brand communication effect evaluations, and it is difficult to directly convert communication volume into economic value.

[0103] Furthermore, it also includes:

[0104] The strategy adjustment module (6) is connected to the value conversion module (4) and is used to dynamically adjust the brand communication strategy based on the media spillover value of the program communication brand using an intelligent recommendation algorithm.

[0105] Establish personalized brand communication strategies based on user portraits and brand needs. For example, understand the age group and gender ratio of the brand's applicable population based on user portraits, and provide the brand with recommendations on programs and delivery methods.

[0106] After the brand is officially placed on the program, the brand communication strategy is dynamically adjusted based on the calculated media spillover value for the brand to refer to and make decisions, such as whether it needs to continue to be placed on the program, and if so, in what way, such as what type of advertising placement. The intelligent recommendation algorithm will comprehensively consider and give brand communication strategy recommendations based on the calculated media spillover value, as well as the collection and analysis of the program's brand network communication data, hot search data, and program playback data, such as the number of platform plays of the program, the popularity of the play, etc. For example, if the number of users watching the program is not high and the discussion is not hot enough, it means that the program is not attractive enough and the program is not popular enough, which will also indirectly affect the popularity of brand communication.

[0107] Specifically, it also includes a display module (7), which is connected to the return calculation module (5) and the value conversion module (4) respectively, and is used to generate a visual report based on the media overflow value and the return on investment.

[0108] The visualization report displays the changing trend of media spillover value.

[0109] By directly displaying the changing trends of media spillover value and return on investment, etc., it provides intuitive decision-making support for brands.

[0110] The above are only preferred embodiments of the present invention, and are not intended to limit the implementation methods and protection scope of the present invention. Those skilled in the art should be aware that all solutions obtained by equivalent substitutions and obvious changes made using the description and illustrations of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for evaluating the brand value of a program, characterized in that: include: Step A1, collecting network communication data and hot search data about the program communication brand from various network platforms; Step A2, preprocessing the network propagation data and the hot search data; Step A3, evaluating the communication value based on the pre-processed network communication data and the hot search data; Step A4, processing the communication value according to the media spillover value model constructed by the machine learning algorithm to obtain the media spillover value of the program communication brand.

2. A program communication brand value evaluation method as claimed in claim 1, characterized in that: In step A1, the network communication data includes the forwarding volume, like volume, comment volume, exposure volume, and number of fans of the original work, and the original work contains both program-related words and brand-related words; In the step A3, the communication value includes public opinion value; In step A3, the network communication data is analyzed and processed based on a sentiment analysis algorithm, and the public opinion value of each original work is calculated according to preset public opinion indicators. The preset public opinion indicators include the number of reposts, likes, comments, exposure and number of fans of the original work.

3. A program communication brand value evaluation method as claimed in claim 1, characterized in that: In step A1, the hot search data includes the popularity value and the duration of the hot words related to the program's brand promotion, and the hot words include both program-related words and brand-related words; In the step A3, the communication value also includes the hot search value; In step A3, the hot search data is analyzed and processed, and the hot search value of each hot word is calculated using preset hot search indicators. The preset hot search indicators include the popularity value and dominance time of the hot word.

4. A program communication brand value evaluation method as claimed in claim 1, characterized in that: After step A4, the following steps are further included: Step A5, calculating the return on investment of the brand based on the media spillover value of the program's brand promotion and the cost of the brand's program placement.

5. A program communication brand value evaluation method as claimed in claim 1, characterized in that: After step A4, the following steps are also included: Step A6: Based on the media spillover value of the program's brand promotion, use an intelligent recommendation algorithm to dynamically adjust the brand promotion strategy.

6. A program dissemination brand value evaluation system, used to execute a program dissemination brand value evaluation method as claimed in any one of claims 1 to 5, characterized in that: include: Data collection module, used to collect network dissemination data and hot search data of program brands from various network platforms; A preprocessing module, connected to the data acquisition module, for preprocessing the network propagation data and the hot search data; A value evaluation module, connected to the preprocessing module, for evaluating the communication value based on the preprocessed network communication data and the hot search data; The value conversion module is connected to the value evaluation module and is used to process the communication value according to the media spillover value model constructed by the machine learning algorithm to obtain the media spillover value of the program placement brand.

7. A program broadcast brand value evaluation system as claimed in claim 6, characterized in that: The network communication data includes the number of reposts, likes, comments, exposure, and number of fans of the original works, and the original works contain both program-related words and brand-related words; The communication value includes public opinion value; The value assessment module analyzes and processes the network communication data based on the sentiment analysis algorithm, and calculates the public opinion value of each original work according to preset public opinion indicators. The preset public opinion indicators include the number of reposts, likes, comments, exposure and number of fans of the original work.

8. A program broadcast brand value evaluation system as claimed in claim 6, characterized in that: The hot search data includes the popularity value and the duration of dominance of the hot words related to the program's brand promotion, and the hot words include both program-related words and brand-related words; The communication value also includes the hot search value; The value evaluation module analyzes and processes the hot search data, and calculates the hot search value of each hot word using preset hot search indicators, wherein the preset hot search indicators include the popularity value and the dominance time of the hot word.

9. A program broadcast brand value evaluation system as claimed in claim 6, characterized in that: Also includes: The return calculation module is connected to the value conversion module and is used to calculate the return on investment of the brand based on the media spillover value of the program spreading the brand and the cost of the brand placing the program.

10. A program broadcast brand value evaluation system as claimed in claim 9, characterized in that: Also includes: The strategy adjustment modules are respectively connected to the value conversion modules and are used to dynamically adjust the brand communication strategy based on the media spillover value of the program communication brand using an intelligent recommendation algorithm.

Images