Anhui culture display system based on data driving

Abstract

The invention discloses a data-driven badge culture display system, which relates to the field of culture promotion and comprises a data acquisition module, a data analysis module and a recommendation display module. The data acquisition module is used for acquiring user browsing information and interactive feedback information displayed by the Anhui culture; the data analysis module analyzes the information browsing behavior of the user to obtain a recommendation value of the user side, and sends the recommendation value to the recommendation display module; the recommendation display module analyzes and judges the browsing behavior and the feedback information of the user to execute a corresponding recommendation display strategy; through deep analysis of user behaviors and in combination with accurate calculation and feedback mechanisms, the accuracy of content recommendation and user experience can be remarkably improved, and it is ensured that recommended content always keeps correlation and attraction; through detailed analysis and multi-level classification of the feedback information, the acceptability of the user to the recommended content can be improved, and more accurate and personalized recommendation can be provided.

Description

Technical Field

[0001] The present invention relates to the technical field of cultural promotion, and in particular to a data-driven Anhui culture display system. Background Art

[0002] Local cultural displays play an important role in maintaining and developing local culture, showcasing local traditional crafts, arts and customs, and helping to protect and pass on the unique local cultural heritage. Hui culture is an important part of Chinese traditional culture. Through displays, local residents and tourists can understand and learn about local traditions, and enhance their sense of identity and pride in local culture. Unique local cultural displays can attract tourists, increase the visibility of local cultural products, develop related cultural industries, and promote the development of tourism, thereby driving the local economy. Displaying local cultural characteristics to the outside world promotes exchanges and understanding between different regions and cultures. While retaining traditions, it combines modern technology and design concepts for innovation to promote the modernization and development of local culture.

[0003] At present, the use of traditional display methods lacks innovation and interaction and cannot effectively attract the interest of modern audiences. The display content is often too scattered and lacks systematicity and coherence, and cannot fully display the overall appearance of local culture. While protecting traditional culture, cultural innovation and modernization are often neglected, resulting in the display content appearing outdated and unattractive. Summary of the invention

[0004] The purpose of the present invention is to solve the problems mentioned in the above background technology and to propose a data-driven Hui culture display system.

[0005] The purpose of the present invention can be achieved through the following technical solutions: a data-driven Hui culture display system, including a data acquisition module, a data analysis module and a recommendation display module; the specific steps are:

[0006] The data collection module collects user browsing information and interactive feedback information displayed by Huiwenhua; the user browsing information displayed by Huiwenhua includes the start time, end time and number of times the user directly closes the recommendation when clicking on the recommended browsing; the user interactive feedback information includes likes, collections, comments and forwarding;

[0007] The data analysis module obtains the recommendation value of the user end by analyzing the user's browsing behavior and sends it to the recommendation display module;

[0008] The recommendation display module analyzes and judges the user's browsing behavior and feedback information to execute the corresponding recommendation display strategy; the specific steps are:

[0009] Get the interactive feedback information of the forums in the past year, get the likes, favorites, comments and reposts of each forum every month, and record them as D ijk , S ijk , P ijk and Z ijk ; where j = 1, 2, 3 ... J, J is a positive integer, J represents the total number of months of the section information of several years, j represents the serial number of any month; where U = 1, 2, 3 ... U, U is a positive integer, U represents the year of the calendar year, u represents the serial number of any year; take any section of a certain year and a certain month, and click D iju 、Collection S iju 、CommentsP iju and forward Z iju Substitute the value of into the formula F iju =c1×D iju +c2×S iju +c3×P iju +c4×Z iju Calculate the feedback value F iju , where c1, c2, c3 and c4 are the set weight factors respectively; thus, the feedback value of each section in each month of each year can be obtained; a feedback threshold interval is set, when the feedback value is greater than the maximum value of the feedback threshold interval, it is marked as a high feedback value; when the feedback value is within the feedback threshold interval, it is marked as a medium feedback value; when the feedback value is less than the minimum value of the feedback threshold interval, it is marked as a low feedback value; the number of high feedback values, the number of medium feedback values ​​and the number of low feedback values ​​are counted respectively; the high feedback value, the medium feedback value and the low feedback value are summed up to obtain the high display value, the medium display value and the low display value, and they are recorded as N4, N5 and N6 respectively;

[0010] Substitute the values ​​of the number of high feedback values ​​N1, the number of medium feedback values ​​N2, the number of low feedback values ​​N3, the high display value N4, the medium display value N5, and the low display value N6 into the formula Calculate and obtain the tendency value H, where r1, r2 and r3 are respectively the set weight factors, and r1>r2>r3>0; set a tendency threshold interval, when the tendency value is greater than the maximum value in the set tendency threshold interval, execute the associated display strategy of step 2; when the tendency value is within the set tendency threshold interval, execute the theme display strategy of step 3; when the tendency value is less than the minimum value in the set tendency threshold interval, execute the light display strategy of step 4.

[0011] As a preferred implementation of the present invention, the user's browsing behavior is analyzed, and the specific steps are as follows:

[0012] The Huizhou culture is divided into i sections, where i = 1, 2, 3...I, where I is a positive integer, I represents the total number of sections corresponding to the Huizhou culture, and i represents the serial number of any section; the Huizhou culture section specifically includes: Huizhou architecture, Huizhou calligraphy and seal carving, Huizhou humanities and culture, Huizhou cuisine, and Huizhou traditional crafts, etc.; obtain the time period in which the user uses the user terminal every day, and count the number of times the user clicks on the recommendation and the number of times the user directly closes the recommendation in each time period; obtain the start time and end time of each click of the recommendation by the user in the time period, and calculate the time difference between the two to obtain the browsing time; sort the browsing time in the time period in chronological order, sum up all the browsing time to obtain the total browsing time, and mark it as L i Calculate the difference between the start time of the adjacent browsing time and the end time of the adjacent browsing time to get the browsing interval time, sum up all the browsing interval time to get the total browsing interval time, and mark it as W i ; The total browsing time will be L i and the total browsing interval duration W i Substitute into the formula The browse value Ti is calculated, where a1 and a2 are the set weight factors respectively;

[0013] Get the number of times the user directly closes the recommendation within a time period; set a threshold interval for the number of times the recommendation is closed. When the number of times the user directly closes the recommendation is greater than the maximum value of the threshold interval for the number of times the recommendation is closed, it is marked as a high-frequency closure; when the number of times the user directly closes the recommendation is within the threshold interval for the number of times the recommendation is closed, it is marked as a medium-frequency closure; when the number of times the user directly closes the recommendation is less than the minimum value of the threshold interval for the number of times the recommendation is closed, it is marked as a low-frequency closure; count the number of high-frequency closures, medium-frequency closures, and low-frequency closures, and record them as K1, K2, and K3, respectively;

[0014] Substitute the values ​​of browse value Ti, high frequency shutdown times K1, medium frequency shutdown times K2 and low frequency shutdown times K3 into the formula The recommendation value Q is calculated, where a3, b1, b2 and b3 are respectively the set weight factors; a two-dimensional rectangular coordinate system is constructed with the time period as the horizontal coordinate and the recommendation value as the vertical coordinate, the recommendation value of each time period is input into the coordinate system in chronological order, and connected in sequence with line segments to obtain a line graph of the relationship between the recommendation value of the user's use of the user terminal in one day and the time period; a recommendation threshold is set, and the recommendation value is compared with the set recommendation threshold. When the recommendation value is greater than the set recommendation threshold, it means that the time period corresponding to the user can be recommended normally; when the recommendation value is less than or equal to the set recommendation threshold, it means that the time period corresponding to the user should be recommended less, and whether to recommend or not is determined based on the fact that the smaller the recommendation value, the fewer the number of recommendations, and the user's user terminal and the corresponding recommendation value are sent to the recommendation display module.

[0015] As a preferred implementation of the present invention, the specific process of the association display strategy is:

[0016] Based on the user's feedback data and historical points of interest, the Apriori algorithm is used to mine association rules to find content related to the section of interest, and other sections that are highly related to the Hui culture section of interest to the user are determined as related sections;

[0017] Set up a "Related Recommendations" area in the user interface to centrally display related sections, and highlight the related sections. Adjust the related recommendation content in a timely manner according to the user's interaction. Three or different numbers of related sections can be displayed in the "Related Recommendations" area. If the user's propensity value decreases, execute step three. If the customer's propensity value still remains at a highly interested stage, continue with step one.

[0018] As a preferred embodiment of the present invention, the specific process of the theme display strategy is as follows:

[0019] According to the user's feedback data and tendency value, call another high tendency value section and set this section as the theme section;

[0020] A "related content" area is set in the user interface, but the subject section is not highlighted; the display strategy is adjusted in a timely manner according to the user's subsequent feedback data; when the tendency value is greater than the maximum value of the set tendency threshold, the recommendation behavior of the user end recommending the subject section is sent to step two; when the tendency value is less than the minimum value of the set tendency threshold, the recommendation behavior of the user end recommending the subject section is sent to step four.

[0021] As a preferred embodiment of the present invention, the specific process of the light display strategy is:

[0022] Since the user's feedback data and tendency value are low, the "related recommendation" area and the "related content" area can be reduced to allow users to have more independent browsing choices; the "related recommendation" area and the "related content" area are placed at the bottom or secondary position of the recommendation list to ensure that their display frequency is lower than the user's current preferred content; the display frequency and content are adjusted appropriately according to the user's feedback and tendency value; when the tendency value is within the set tendency threshold, the recommendation behavior of the user-side recommended topic section is sent to step three; when the tendency value is still less than the minimum value of the set tendency threshold, the display format is adjusted or other relevant information is added to increase its attractiveness. The display of Hui culture content can be reviewed regularly. If user interest picks up, the display frequency of Hui culture content can be gradually increased.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] 1. Through in-depth analysis of user behavior, combined with precise calculation and feedback mechanisms, the accuracy of content recommendations and user experience can be significantly improved, and more personalized recommended content can be provided to users. It can identify user behavior patterns and understand their interests and changes in needs. The platform can dynamically adjust the recommendation strategy to ensure that the most relevant content is pushed to users at the right time. By reducing recommended content that users are not interested in, user interference can be reduced, the overall user experience and platform user stickiness can be improved, thereby promoting platform user retention and satisfaction.

[0025] 2. By analyzing the likes, favorites, comments and reposts of each section every month, we can accurately evaluate the user's interest and feedback on each section, which can help the system understand the user's preferences and assign appropriate feedback values ​​to each section. By dividing the feedback values ​​into high feedback, medium feedback and low feedback, we can clearly identify the user's interest in different sections and formulate more targeted display strategies. Through the classification of feedback values, the system can flexibly adjust the recommendation strategy to improve the relevance of recommendations and user satisfaction. By determining the display strategy based on the propensity value, personalized recommendations can be achieved. Users with high propensity values ​​will see more relevant content, while users with low propensity values ​​will see fewer recommendations, which can improve users' acceptance of recommended content. The dynamic calculation and adjustment of the propensity value can reflect the changes in user interests in real time, ensuring that the recommended content always remains relevant and attractive. The association rules mined by the Apriori algorithm can discover sections related to user interests and display them in a centralized manner, allowing users to discover more content they may be interested in and increase user interaction. Through detailed analysis and multi-level classification of feedback information, more accurate and personalized recommendations can be provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0027] Figure 1 It is a schematic diagram of the connection of various modules in the system of the present invention. DETAILED DESCRIPTION

[0028] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so as to describe the embodiments of the present invention described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0032] According to an embodiment of the present invention, Figure 1 As shown in the figure, the data-driven Hui culture display system includes a data collection module, a data analysis module and a recommendation display module; the specific steps are:

[0033] The data collection module collects user browsing information and interactive feedback information displayed by Hui culture through data-driven technology; the user browsing information displayed by Hui culture includes the start time, end time and number of times the user directly closes the recommendation when clicking on the recommended browsing; user interactive feedback information includes likes, collections, comments and forwarding; the data-driven technology collects massive amounts of user data through the Internet or other related software, and converts the data into user browsing information and interactive feedback information.

[0034] The data analysis module obtains the recommended value of the user end by analyzing the user's browsing behavior and sends it to the recommendation display module; the specific steps are:

[0035] The Huizhou culture is divided into i sections, where i = 1, 2, 3...I, where I is a positive integer, I represents the total number of sections corresponding to the Huizhou culture, and i represents the serial number of any section; the Huizhou culture section specifically includes: Huizhou architecture, Huizhou calligraphy and seal carving, Huizhou humanities and culture, Huizhou cuisine, and Huizhou traditional crafts, etc.; obtain the time period in which the user uses the user terminal every day, and count the number of times the user clicks on the recommendation and the number of times the user directly closes the recommendation in each time period; obtain the start time and end time of each click of the recommendation by the user in the time period, and calculate the time difference between the two to obtain the browsing time; sort the browsing time in the time period in chronological order, sum up all the browsing time to obtain the total browsing time, and mark it as L i Calculate the difference between the start time of the adjacent browsing time and the end time of the adjacent browsing time to get the browsing interval time, sum up all the browsing interval time to get the total browsing interval time, and mark it as W i ; The total browsing time will be L i and the total browsing interval duration W i Substitute the set formula Calculate the browse value T i , where a1 and a2 are the set weight factors respectively;

[0036] Get the number of times the user directly closes the recommendation within a time period; set a threshold interval for the number of times the recommendation is closed. When the number of times the user directly closes the recommendation is greater than the maximum value of the threshold interval for the number of times the recommendation is closed, it means that the user in this time period is in a state of frequently closing the recommended content, and the user is marked as a high-frequency close; when the number of times the user directly closes the recommendation is within the threshold interval for the number of times the recommendation is closed, the user is marked as a medium-frequency close; when the number of times the user directly closes the recommendation is less than the minimum value of the threshold interval for the number of times the recommendation is closed, the user is marked as a low-frequency close; count the number of high-frequency closes, medium-frequency closes, and low-frequency closes, and record them as K1, K2, and K3, respectively;

[0037] Substitute the values ​​of browse value Ti, high frequency closing times K1, medium frequency closing times K2 and low frequency closing times K3 into the set formula The recommendation value Q is calculated, where a3, b1, b2 and b3 are respectively set weight factors; a two-dimensional rectangular coordinate system is constructed with the time period as the horizontal coordinate and the recommendation value as the vertical coordinate, and the recommendation value of each time period is input into the coordinate system in chronological order, and connected in sequence with line segments to obtain a line graph of the relationship between the recommendation value of the user's use of the user terminal in one day and the time period; a recommendation threshold is set, and the recommendation value is compared with the set recommendation threshold. When the recommendation value is greater than the set recommendation threshold, it means that the user's corresponding time period can be recommended normally; when the recommendation value is less than or equal to the set recommendation threshold, it means that the user's corresponding time period should be recommended less, and the recommendation is judged based on the fact that the smaller the recommendation value, the fewer the number of recommendations, and the user's user terminal and the corresponding recommendation value are sent to the recommendation display module;

[0038] Through in-depth analysis of user behavior, combined with precise calculation and feedback mechanisms, the accuracy of content recommendations and user experience can be significantly improved, and more personalized recommendations can be provided to users. User behavior patterns can be identified and their interests and demand changes can be understood. The platform can dynamically adjust recommendation strategies to ensure that the most relevant content is pushed to users at the right time. By reducing recommended content that users are not interested in, user interference can be reduced, the overall user experience and platform user stickiness can be improved, thereby promoting platform user retention and satisfaction.

[0039] The recommendation display module analyzes and judges the user's browsing behavior and feedback information to execute the corresponding recommendation display strategy; the specific steps are:

[0040] Step 1: Obtain the interactive feedback information of the forums in previous years, and obtain the likes, favorites, comments, and reposts of each forum each month, and record them as D ijk , S ijk , P ijk and Z ijk ; where j = 1, 2, 3 ... J, J is a positive integer, J represents the total number of months of the section information of several years, j represents the serial number of any month; where U = 1, 2, 3 ... U, U is a positive integer, U represents the year of the calendar year, u represents the serial number of any year; take any section of a certain year and a certain month, and click D iju 、Collection S iju 、CommentsP iju and forward Z iju Substitute the value into the formula F iju =c1×D iju +c2×S iju +c3×Piju +c4×Z iju Calculate the feedback value F iju , where c1, c2, c3 and c4 are the set weight factors respectively; thus, the feedback value F of each section in each month of each year is obtained. iju ; Set a feedback threshold interval. When the feedback value is greater than the maximum value of the feedback threshold interval, it is marked as a high feedback value; when the feedback value is within the feedback threshold interval, it is marked as a medium feedback value; when the feedback value is less than the minimum value of the feedback threshold interval, it is marked as a low feedback value; count the number of high feedback values, the number of medium feedback values, and the number of low feedback values, and mark them as N1, N2, and N3 respectively; sum the high feedback values, the medium feedback values, and the low feedback values ​​to obtain the high display value, the medium display value, and the low display value, and record them as N4, N5, and N6 respectively;

[0041] Substitute the values ​​of the number of high feedback values ​​N1, the number of medium feedback values ​​N2, the number of low feedback values ​​N3, the high display value N4, the medium display value N5 and the low display value N6 into the set formula Calculate to obtain the tendency value H, where r1, r2 and r3 are respectively the set weight factors, and r1>r2>r3>0; set a tendency threshold interval, when the tendency value is greater than the maximum value in the set tendency threshold interval, it means that the user is interested in the recommended section, then execute the associated display strategy of step 2; when the tendency value is within the set tendency threshold interval, execute the theme display strategy of step 3; when the tendency value is less than the minimum value in the set tendency threshold interval, execute the light display strategy of step 4;

[0042] Step 2: The specific process of the associated display strategy is as follows:

[0043] According to the user's feedback data (likes, favorites, comments and forwarding) and historical points of interest, the Apriori algorithm is used to mine association rules to find the content related to the section of interest, and determine other sections that are highly related to the Huizhou culture section that the user is interested in as related sections; it should be noted that if the target section is Huizhou humanities and culture, it can be associated with Huizhou cuisine, and Huizhou cuisine derived from Huizhou humanities and culture, where the section content is highly related, this is a related section;

[0044] Set up a "Related Recommendations" area in the user interface to centrally display related sections and highlight them. Adjust the related recommendations in a timely manner based on the user's likes, favorites, comments, and forwarding interactions. You can display three or different numbers of related sections in the "Related Recommendations" area. If the user's propensity value decreases, execute step three. If the customer's propensity value remains at a highly interested stage, continue to execute step one.

[0045] Step 3: The specific process of the theme display strategy is:

[0046] According to the user's feedback data (likes, favorites, comments and reposts) and propensity values, another high propensity value section is retrieved and set as the theme section; it should be noted that the relevant cultural sections can be grouped and displayed thematically according to the attributes; for example, the relevant contents such as Huizhou humanities culture and Huizhou traditional crafts can be grouped together to facilitate users to gain a deeper understanding of specific cultural themes;

[0047] A "related content" area is set in the user interface, but the topic section is not highlighted; according to the user's subsequent feedback data (likes, favorites, comments and forwarding), the display strategy is adjusted in a timely manner; when the tendency value is greater than the maximum value of the set tendency threshold, the user's recommended behavior of recommending the topic section is sent to step two; when the tendency value is less than the minimum value of the set tendency threshold, the user's recommended behavior of recommending the topic section is sent to step four;

[0048] Step 4: The specific process of the light display strategy is:

[0049] Since the user's feedback data (likes, favorites, comments and forwarding) and tendency value are low, the "related recommendation" area and the "related content" area can be reduced to allow users to have more independent browsing choices; the "related recommendation" area and the "related content" area are placed at the bottom or secondary position of the recommendation list to ensure that their display frequency is lower than the user's current preferred content; the display frequency and content are appropriately adjusted according to the user's feedback (likes, favorites, comments and forwarding) and tendency value; when the tendency value is within the set tendency threshold, the recommendation behavior of the user-side recommended topic section is sent to step three; when the tendency value is still less than the minimum value of the set tendency threshold, the "related recommendation" area and the "related content" area can be reduced to allow users to have more independent browsing choices to increase its attractiveness, and the display of Hui culture content can be reviewed regularly. If the user's interest recovers, the display frequency of Hui culture content can be gradually increased;

[0050] By analyzing the likes, favorites, comments and reposts of each section every month, we can accurately evaluate the user's interest and feedback on each section, which can help the system understand the user's preferences and assign appropriate feedback values ​​to each section; by dividing the feedback values ​​into high feedback, medium feedback and low feedback, we can clearly identify the user's interest in different sections and formulate more targeted display strategies; through the classification of feedback values, the system can flexibly adjust the recommendation strategy to improve the relevance of recommendations and user satisfaction; by determining the display strategy based on the propensity value, personalized recommendations can be achieved. Users with high propensity values ​​will see more relevant content, while users with low propensity values ​​will see fewer recommendations, which can improve users' acceptance of recommended content; and the dynamic calculation and adjustment of the propensity value can reflect the changes in user interests in real time, ensuring that the recommended content always remains relevant and attractive; using the association rules mined by the Apriori algorithm, sections related to user interests can be discovered and displayed in a centralized manner, allowing users to discover more content they may be interested in and increase user interaction; through detailed analysis and multi-level classification of feedback information, more accurate and personalized recommendations can be provided.

[0051] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0052] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. The data-driven Hui culture display system is characterized by: Including data collection module, data analysis module and recommendation display module; The data collection module collects user browsing information and interactive feedback information displayed by Huiwenhua; the user browsing information includes the start time, end time and number of times the user directly closes the recommendation when clicking on the recommended browsing; the user interactive feedback information includes likes, collections, comments and forwarding; The data analysis module analyzes the user's browsing information to obtain the recommended value of the user end, and sends it to the recommendation display module; The recommendation display module analyzes and judges the user's browsing behavior and feedback information to execute the corresponding recommendation display strategy; the specific steps are: Obtain the interactive feedback information of the forums in previous years, and obtain the values ​​of likes, favorites, comments and reposts for each forum every month; select any forum in a certain year and month, and normalize the values ​​of likes, favorites, comments and reposts to obtain the feedback value; then obtain the feedback value of each forum in each month of each year; set a feedback threshold interval, when the feedback value is greater than the maximum value of the feedback threshold interval, it is marked as a high feedback value; when the feedback value is within the feedback threshold interval, it is marked as a medium feedback value; when the feedback value is less than the minimum value of the feedback threshold interval, it is marked as a low feedback value; count the number of high feedback values, the number of medium feedback values ​​and the number of low feedback values ​​respectively; sum the high feedback values, the medium feedback values ​​and the low feedback values ​​to obtain the high display value, the medium display value and the low display value respectively; The number of high feedback values, the number of medium feedback values, the number of low feedback values, the high display value, the medium display value and the low display value are normalized to obtain a tendency value; a tendency threshold interval is set, and when the tendency value is greater than the maximum value in the set tendency threshold interval, the associated display strategy is executed; when the tendency value is within the set tendency threshold interval, the theme display strategy is executed; when the tendency value is less than the minimum value in the set tendency threshold interval, the light display strategy is executed.

2. The data-driven Hui culture display system according to claim 1 is characterized in that: Analyze the user's browsing behavior. The specific steps are as follows: The Hui culture is divided into several sections; the time period in which the user uses the user terminal every day is obtained, and the number of times the user clicks on the recommendation and the number of times the user directly closes the recommendation in each time period is counted respectively; the start time and the end time of each click of the recommendation by the user in the time period are obtained, and the time difference between the two is calculated to obtain the browsing time; the browsing time in the time period is sorted in chronological order, and all the browsing time is summed up to obtain the total browsing time; the start time of adjacent browsing time and the end time of adjacent browsing time are calculated to obtain the browsing interval time, and all the browsing interval time are summed up to obtain the total browsing interval time, and the total browsing time and the total browsing interval time are normalized to obtain the browsing value; Get the number of times the user directly closes the recommendation within a time period; set a threshold interval for the number of times the recommendation is closed. When the number of times the user directly closes the recommendation is greater than the maximum value of the threshold interval for the number of times the recommendation is closed, it is marked as a high-frequency closure; when the number of times the user directly closes the recommendation is within the threshold interval for the number of times the recommendation is closed, it is marked as a medium-frequency closure; when the number of times the user directly closes the recommendation is less than the minimum value of the threshold interval for the number of times the recommendation is closed, it is marked as a low-frequency closure; count the number of high-frequency closures, medium-frequency closures, and low-frequency closures respectively; The values ​​of the browse value, the high frequency closing times, the medium frequency closing times and the low frequency closing times are normalized to obtain the recommended value; A two-dimensional rectangular coordinate system is constructed with the time period as the horizontal axis and the recommended value as the vertical axis. The recommended value of each time period is input into the coordinate system in chronological order, and connected in sequence with line segments to obtain a line graph showing the relationship between the recommended value of the user end used by the user in one day and the time period; Set a recommendation threshold and compare the recommendation value with the set recommendation threshold. When the recommendation value is greater than the set recommendation threshold, the time period corresponding to the user is a normal recommendation; when the recommendation value is less than or equal to the set recommendation threshold, the time period corresponding to the user is a reduced recommendation. The smaller the recommendation value, the fewer the number of recommendations, and the user's client and the corresponding recommendation value are sent to the recommendation display module.

3. The data-driven Hui culture display system according to claim 1 is characterized in that: The specific process of the association display strategy is as follows: Based on the user's feedback data and historical points of interest, the Apriori algorithm is used to mine association rules to find content related to the section of interest, and other sections that are highly related to the Hui culture section of interest to the user are determined as related sections; Set up a "Related Recommendations" area in the user-side interface to centrally display related sections, and highlight the related sections. Adjust the related recommendation content in a timely manner according to the user's interaction. Display three or more related sections in the "Related Recommendations" area. If the user's propensity value decreases, execute the theme display strategy. If the customer's propensity value remains at a highly interested stage, continue to execute the related display strategy.

4. The data-driven Hui culture display system according to claim 1 is characterized in that: The specific process of the theme display strategy is: According to the user's feedback data and tendency value, call another high tendency value section and set this section as the theme section; A "related content" area is set in the user interface, but the subject section is not highlighted; the display strategy is adjusted in a timely manner according to the user's subsequent feedback data; when the tendency value is greater than the maximum value of the set tendency threshold, the user end will execute the associated display strategy; when the tendency value is less than the minimum value of the set tendency threshold, the user end will execute the light display strategy.

5. The data-driven Hui culture display system according to claim 1 is characterized in that: The specific process of the light display strategy is as follows: Place the "Related Recommendations" area and the "Related Content" area at the bottom or secondary position of the recommendation list to ensure that their display frequency is lower than the user's current preferred content; subsequently adjust the display frequency and content appropriately based on user feedback and tendency values; when the tendency value is within the set tendency threshold, the user end will execute the theme display strategy; when the tendency value is still less than the minimum value of the set tendency threshold, place the "Related Recommendations" area and the "Related Content" area at the bottom or secondary position of the recommendation list to ensure that their display frequency is lower than the user's current preferred content.

Images