Advertisement design display system and method based on big data

Abstract

The invention discloses an advertisement design display system and method based on big data, and relates to the technical field of data intelligent identification. Comprising an advertisement design module and an advertisement display module. The advertisement design module obtains a user tendency value through comprehensive analysis according to factors such as behavior data, interest preference, geographic position and seasonality of a user, and matches an advertisement template according to the user tendency value; the advertisement display module accurately displays the personalized advertisement content generated by the advertisement design module, and selects an advertisement display strategy according to the browsing tendency and the area tendency of the user; the system further comprises a data acquisition module and a server. The data acquisition module is used for acquiring user behavior data and regional information and sending the acquired data to the server for storage; through multi-dimensional analysis and evaluation, the scene correlation of the advertisement content is enhanced, and the user attraction and the putting accuracy of the advertisement are improved; and the display priority and the advertisement strategy are dynamically adjusted through user behaviors and environment changes.

Description

Technical Field

[0001] The present invention relates to the technical field of advertising design and display, and more particularly, to a big data-based advertising design and display system and method. Background Art

[0002] Advertising design is a professional activity that creates content through multimedia forms such as vision, text, audio, and video to attract the attention of the target audience and convey brand information. It combines artistry and commerciality, using creative means to promote products, services, brands, or ideas; a well-designed and excellently displayed advertisement can not only convey information but also touch people's hearts, achieving the long-term development goals of the brand; advertising design and display refer to the process of presenting the carefully designed advertising content through various media channels; Although advertising design and display play an important role in commercial promotion, with the intensification of market competition and the change of consumer demands, many advertising designs still use unified templates and fail to be customized according to the user's interests, demands, and behavior data, resulting in a low correlation between the advertisement and the audience and making it difficult to attract the user's attention. Summary of the Invention

[0003] The main object of the present invention is to provide a big data-based advertising design and display system and method to overcome the problems mentioned in the above background art.

[0004] To achieve the above object, according to one aspect of the present invention, there is provided a big data-based advertising design and display system, which includes: an advertising design module and an advertising display module; The advertising design module comprehensively analyzes the user's behavior data, interest preferences, geographical location, seasonality, etc. to obtain a user preference value, and matches an advertising template according to the user preference value; the specific steps are as follows: It is assumed that there is an advertising template library with several advertising templates; it is assumed that each user has several corresponding search keywords, and the number of keywords is marked as Yn, where n = 1, 2, 3... N, N is a positive integer, N represents the total number of advertising templates, and n represents the serial number of any one advertising template; it is assumed that each advertising template has several keywords. The user keywords are compared and matched with the advertising templates in the template library. When there is one or more overlapping keywords between the user's keywords and the keywords of the advertising template, the advertising template is marked as a preliminary selection template, and the number of keywords overlapping with the user in the preliminary selection template is marked as Zn; the number of users using each preliminary selection template is counted and recorded as Qn; the ages of each user are retrieved, the users corresponding to each age are counted, and the age with the largest number of corresponding users is selected as the target audience age and marked as C1; the user ages of each advertising template are retrieved, the user ages corresponding to each advertising template are counted, and the age with the largest number of corresponding users is selected as the template audience age and marked as C2; the industry categories of the historical use of each preliminary selection template are obtained, the industry category where the user is located is obtained, the industry category of the user is compared and analyzed with the industry category of the preliminary selection template, and the number of industry categories where the industry category of the user overlaps with the industry category of the preliminary selection template is obtained and marked as C3; the values of the user keyword quantity Yn, the number of keywords Zn overlapping between the preliminary selection template and the user, the number of users Qn using the preliminary selection template, the target audience age C1, the template audience age C2, and the number of overlapping industry categories C3 are substituted into the formula The selection value Xn of the preliminary selection template is calculated, where a1, a2, a3, and a4 are respectively set weight factors, and e is the natural constant; It is assumed that there is a selection threshold interval for the preliminary selection template. The selection value of the preliminary selection template is compared and analyzed with the set selection threshold interval for the preliminary selection template; when the selection value of the preliminary selection template is greater than the maximum value of the set selection threshold interval for the preliminary selection template, the template is marked as a high-level template; when the selection value of the preliminary selection template is within the set selection threshold interval for the preliminary selection template, the template is marked as an intermediate-level template; when the selection value of the preliminary selection template is less than the minimum value of the set selection threshold interval for the preliminary selection template, the template is marked as a basic template; the high-propensity users, medium-propensity users, and low-propensity users are respectively matched with high-level templates, intermediate-level templates, and basic templates, and the preliminary selection template with the largest selection value among the high-level templates, intermediate-level templates, and basic templates is selected as the final advertising template for high-propensity users, medium-propensity users, and low-propensity users; The advertisement display module accurately displays the personalized advertisement content generated by the advertisement design module and selects an advertisement display strategy according to the user's browsing tendency and regional tendency.

[0005] Furthermore, it also includes: a data collection module and a server; The data collection module is used to collect user behavior data and regional information, and send the collected data to the server for storage; the user behavior data includes: browsing records, browsing duration, click data, and search keywords; the regional information includes: the location and meteorological information of the user's location.

[0006] Furthermore, the specific analysis steps for high-propensity users, medium-propensity users, and low-propensity users are as follows: Substitute the numerical values of the user's browsing evaluation value and the regional evaluation value into the set formula to calculate the user propensity value , where and are respectively the set weight factors; Set a user propensity threshold range, and compare and analyze the user propensity value with the set advertisement propensity threshold range; when the user propensity value is greater than the maximum value of the set user propensity threshold range, the user is marked as a high-propensity user; when the user propensity value is within the set user propensity threshold range, the user is marked as a medium-propensity user; when the user propensity value is less than the minimum value of the set user propensity threshold range, the user is marked as a low-propensity user.

[0007] Furthermore, the specific analysis steps for the browsing evaluation value are as follows: Obtain the number of times each user views each advertisement when logging in to the website, and record it as Lij, where i = 1, 2, 3... I, I takes positive integer values, I represents the total number of users, and i represents the number of any one user; where j = 1, 2, 3... J, J takes positive integer values, J represents the total number of advertisements, and j represents the serial number of any one advertisement; set the average number of views of users on the website as , then the effective browsing rate of the user is ; obtain the number of clicks of the user on each advertisement, and record it as Dij, obtain the number of displayed advertisements as , then the advertisement click-through rate of the user is ; obtain the residence time of the user on the advertisement page, calculate its average value to obtain the average residence time on the advertisement page each time, and record it as Tij; set the average residence time of users in the industry on advertisements as , then the effective residence rate of the user is ; substitute the numerical values of the user's effective browsing rate , the user's advertisement click-through rate and the user's effective residence rate into the formula to calculate the browsing evaluation value of the user for each advertisement, where , and are respectively the set weight factors.

[0008] Furthermore, the specific analysis steps of the regional evaluation value are as follows: Obtain the area where the user is currently located, and record the number of advertisements related to the geographical location of the area where the user browses the advertisement content as G1; set the total number of advertisements in the area where the user is located as , then the demand matching degree between the advertisement content browsed by the user and the area where the user is located is ; obtain the season in the area where the user is located, and record the number of advertisements related to the season in the area where the user browses the advertisement content as G2, then the seasonal relevance between the advertisement content browsed by the user and the area where the user is located is ; obtain the temperature in the area where the user is located and record it as G3; set the comfortable temperature in the area where the user is located as , then the climate impact degree of the user is ; substitute the demand matching degree , seasonal relevance and climate impact degree of the area where the user is located into the formula to calculate and obtain the regional evaluation value , where , and are respectively the set weight factors.

[0009] Furthermore, the specific advertisement display strategy is as follows: Set an advertisement display threshold interval, and compare and analyze the advertisement display priority with the set advertisement display threshold interval; when the advertisement display priority is greater than the maximum value of the set advertisement display threshold interval, the display strategy is high priority, and the advertisement is directly pushed; when the advertisement display priority is within the set advertisement display threshold interval, the display strategy is medium priority, and the advertisement is displayed according to the user's active time; when the advertisement display priority is less than the minimum value of the set advertisement display threshold interval, the display strategy is low priority, and the display frequency is reduced.

[0010] Furthermore, the specific analysis steps of the advertisement display priority value are as follows: Substitute the advertisement display tendency value and the advertisement area tendency value into the formula to calculate and obtain the advertisement display priority value , where and are respectively the set weight factors.

[0011] Further, the specific analysis steps for the advertisement display tendency value are as follows: Obtain the user behavior data and use the formula to calculate the effective browsing rate of each user on the website; use the formula to calculate the advertisement browsing rate of each user on the website; use the formula to calculate the effective browsing rate of each user on the website; substitute the effective browsing rate of each user , advertisement click-through rate and effective browsing rate into the formula to calculate the advertisement display tendency value , where , and are respectively the set weight factors.

[0012] Further, the specific analysis steps for the advertisement area tendency value are as follows: Obtain the regional information of the user and use the formula to calculate the demand matching degree of each user on the website; use the formula to calculate the seasonal relevance of each user on the website; use the formula to calculate the climate impact degree of each user on the website; substitute the demand matching degree of each user , seasonal relevance and climate impact degree into the formula to calculate the advertisement area tendency value , where , and are respectively the set weight factors.

[0013] To achieve the above object, according to another aspect of the present invention, there is provided an advertisement design and display method based on big data, and the method includes the following steps: S1: Collect user behavior data, interest preferences, geographical locations, social interaction data, and historical advertisement response data, and store the collected data; S2: Comprehensively analyze the user tendency value based on factors such as the user's behavior data, interest preferences, geographical location, seasonality, etc., and match the advertisement template according to the user tendency value; the specific steps are as follows: Normalize the numerical values of the user's browsing evaluation value and regional evaluation value to obtain the user's advertising preference value; set an advertising preference threshold range, and compare and analyze the user preference value with the set user preference threshold range; when the user preference value is greater than the maximum value of the set user preference threshold range, mark the user as a high-preference user; when the user preference value is within the set user preference threshold range, mark the user as a medium-preference user; when the user preference value is less than the minimum value of the set user preference threshold range, mark the user as a low-preference user; Set that there is an advertising template library with several advertising templates; set that each user has several corresponding search keywords and mark the number of keywords; set that each advertising template has several keywords, compare and match the user keywords with the advertising templates in the template library, when there is one or more overlapping keywords between the user's keywords and the keywords of the advertising template, mark the advertising template as a preliminary selection template and mark the number of keywords overlapping with the user in the preliminary selection template; count the number of users using each preliminary selection template; retrieve the ages of each user, count the users corresponding to each age, and select the age with the largest number of corresponding users as the target audience age; retrieve the user ages of each advertising template, count the user ages corresponding to each advertising template, and select the age with the largest number of corresponding users as the template audience age; obtain the industry categories of the historical uses of each preliminary selection template, obtain the industry category where the user is located, compare and analyze the industry category of the user with the industry categories of the preliminary selection templates, and obtain the number of industry categories where the industry category of the user coincides with the industry categories of the preliminary selection templates; normalize the numerical values of the number of user keywords, the number of keywords overlapping with the user in the preliminary selection template, the number of users using the preliminary selection template, the target audience age, the template audience age, and the number of coincident industry categories to obtain the selection value of the preliminary selection template; Set that there is a preliminary selection template selection threshold range, and compare and analyze the selection value of the preliminary selection template with the set preliminary selection template selection threshold range; when the selection value of the preliminary selection template is greater than the maximum value of the set preliminary selection template selection threshold range, mark the template as a high-level template; when the selection value of the preliminary selection template is within the set preliminary selection template selection threshold range, mark the template as a medium-level template; when the selection value of the preliminary selection template is less than the minimum value of the set preliminary selection template selection threshold range, mark the template as a basic template; match high-preference users, medium-preference users, and low-preference users with high-level templates, medium-level templates, and basic templates respectively, and select the preliminary selection template with the largest selection value among the high-level templates, medium-level templates, and basic templates as the final advertising template for high-preference users, medium-preference users, and low-preference users; S3: Precisely display the personalized advertising content generated by the advertising design module, and further optimize the advertising display strategy according to the user's browsing preference and regional preference.

[0014] Advantages of the present invention: 1. By integrating user behavior data, geographical information, and brand characteristics, the present invention designs highly customized advertising content, improving the user attractiveness and delivery accuracy of advertisements; by evaluating effective viewing rate, click-through rate, and dwell time, it identifies user interest hotspots, optimizes the design of advertising content, and increases click-through rate and conversion rate; it matches regional needs, season, and climate information, enhances the situational relevance of advertising content, and boosts user participation willingness; by incorporating brand characteristic values, the advertising content can better convey the core concept of the brand, enhance brand recognition, match the characteristics of the brand audience (target age group), and improve the attractiveness of the advertisement to the brand's target group; by continuously updating user behavior data and regional characteristics, it constantly adjusts advertising content and delivery strategies to maintain the continuous attractiveness and effectiveness of the advertisement; the analysis of the user's industry and the industries where the advertising templates have been historically used helps to discover potential industry trends and user needs; 2. By combining user behavior data (such as viewing rate, click-through rate, dwell time) and regional information (such as geographical location, season, climate), the present invention comprehensively analyzes to obtain the display priority, ensuring a high degree of match between the advertising content and user interests; by preferentially displaying highly relevant advertisements and avoiding displaying advertisements that do not meet user needs, it optimizes the utilization rate of advertising resources; it displays advertising content related to user behavior and environment, enhancing the visual attractiveness and information relevance of the advertisement; it uses regional relevance data (demand matching degree, season relevance degree, climate impact degree) to deliver advertisements, increasing the interest and purchase conversion of regional users; it dynamically adjusts the display priority and advertising strategy according to changes in user behavior and environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings, which form a part of the present invention, are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings: Figure 1 is a schematic diagram of the connection of system modules of the present invention; Figure 2 is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] It should be noted that, without conflict, the embodiments in 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 conjunction with the embodiments.

[0017] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0018] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so as to implement the embodiments of the present invention described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0019] In order to make the purpose and advantages of the present invention more clear and understandable, the present invention will be 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.

[0020] According to the embodiments of the present invention, as Figure 1 shown, an advertising design and display system based on big data is provided. The system includes: a data collection module, a server, an advertising design module, and an advertising display module; The data collection module is used to collect user behavior data and regional information, and send the collected data to the server for storage; the user behavior data includes: browsing records, browsing stay duration, click data, and search keywords; the regional information includes: the location and meteorological information of the area where the user is located; The advertising design module comprehensively analyzes the user preference value based on factors such as the user's behavior data, interest preferences, geographical location, seasonality, etc., and matches the advertising template according to the user preference value; the specific steps are as follows: Obtain the number of times each user views each advertisement when logging in to the website, and record it as Lij, where i = 1, 2, 3... I, I takes positive integer values, I represents the total number of users, and i represents the number of any one user; where j = 1, 2, 3... J, J takes positive integer values, J represents the total number of advertisements, and j represents the serial number of any one advertisement; set the average number of views of users on the website as , then the effective viewing rate of the user is ; Obtain the number of clicks on each advertisement by the user, denoted as Dij, and obtain the number of displayed advertisements as , then the advertisement click-through rate of the user is ; Obtain the residence time of the user on the advertisement web page, calculate its average value to obtain the average residence time on the advertisement web page each time, and denote it as Tij; Set the average residence time of users in the industry for advertisements as , then the effective residence rate of the user is ; The effective browsing rate of the user , the advertisement click-through rate of the user and the effective residence rate of the user Substitute the numerical values into the set formula Calculate to obtain the browsing evaluation value of each advertisement by the user, where , and are the set weight factors respectively; It can be seen from the formula that the more times the user browses the advertisement, the greater the advertisement browsing evaluation value; The more times the user clicks on the advertisement, the greater the advertisement browsing evaluation value; The longer the average browsing residence time of the user, the greater the advertisement browsing evaluation value; Obtain the area where the user is currently located, and record the number of advertisements related to the geographical location of the area where the user browses the advertisement content as G1; Set the total number of advertisements in the area where the user is located as , then the demand matching degree of the advertisement content browsed by the user with the area where the user is located is ; Obtain the season in the area where the user is located, and record the number of advertisements related to the season in the area where the user browses the advertisement content as G2, then the season relevance of the advertisement content browsed by the user with the area where the user is located is ; Obtain the temperature in the area where the user is located, and denote it as G3; Set the comfortable temperature in the area where the user is located as , then the climate impact degree of the user is ; Substitute the demand matching degree , season relevance and climate impact degree of the area where the user is located into the set formula Calculate to obtain the area evaluation value , where , and are the set weight factors respectively; It can be seen from the formula that the more area advertisements the user browses, the greater the area evaluation value; The more season-related advertisements the user browses, the greater the area evaluation value; The closer the temperature in the area where the user is located is to the comfortable temperature, the greater the area evaluation value; The browsing evaluation value of the user and the area evaluation value Substitute the value into the set formula Calculate the user preference value , where and are the set weight factors respectively; It can be seen from the formula that the larger the user's browsing evaluation value, the larger the user preference value; The larger the user's regional evaluation value, the larger the user preference value; Set a user preference threshold range, and compare and analyze the user preference value with the set user preference threshold range; When the user preference value is greater than the maximum value of the set user preference threshold range, the user is marked as a high-preference user; When the user preference value is within the set user preference threshold range, the user is marked as a medium-preference user; When the user preference value is less than the minimum value of the set user preference threshold range, the user is marked as a low-preference user; Set that there is an advertisement template library, and there are several advertisement templates in the advertisement template library; Set that each user has several corresponding search keywords, and mark the number of keywords as Yn, where n = 1, 2, 3... N, N takes positive integers, N represents the total number of advertisement templates, and n represents the serial number of any one advertisement template; Set that each advertisement template has several keywords, compare and match the user keywords with the advertisement templates in the template library. When there is one or more overlapping keywords between the user's keywords and the advertisement template's keywords, mark the advertisement template as a preliminary selection template, and mark the number of keywords overlapping with the user in the preliminary selection template as Zn; Count the number of users of each preliminary selection template and record it as Qn; Retrieve the age of each user, count the users corresponding to each age, select the age with the largest number of corresponding users as the target audience age and mark it as C1; Retrieve the user age of each advertisement template, count the user age corresponding to each advertisement template, select the age with the largest number of corresponding users as the template audience age and mark it as C2; Obtain the industry categories used by each preliminary selection template in history, obtain the industry category where the user is located, compare and analyze the user's industry category with the industry category of the preliminary selection template, obtain the number of industry categories overlapping between the user's industry category and the industry category of the preliminary selection template, and mark it as C3; Substitute the values of the user keyword number Yn, the number of keywords overlapping between the preliminary selection template and the user Zn, the number of users of the preliminary selection template Qn, the target audience age C1, the template audience age C2, and the number of overlapping industry categories C3 into the set formula The selection value Xn of the initially selected template is calculated, where a1, a2, a3, and a4 are respectively set weight factors, and e is the natural constant; it can be seen from the formula that the closer the number of keywords that the initially selected template coincides with the user's keywords, the larger the selection value of the initially selected template; the more people use the initially selected template, the larger the selection value of the initially selected template; the closer the age of the target audience and the age of the template audience, the larger the selection value of the initially selected template; the more the number of industry categories that the user and the template coincide, the larger the selection value of the initially selected template. It is set that there is an initially selected template selection threshold range, and the selection value of the initially selected template is compared and analyzed with the set initially selected template selection threshold range; when the selection value of the initially selected template is greater than the maximum value of the set initially selected template selection threshold range, then this template is marked as a high-level template, and the content of the high-level template is highly personalized and has strong visual attraction; when the selection value of the initially selected template is within the set initially selected template selection threshold range, then this template is marked as a medium-level template, and the medium-level template pays attention to partial personalization; when the selection value of the initially selected template is less than the minimum value of the set initially selected template selection threshold range, then this template is marked as a basic template; match high-propensity users, medium-propensity users, and low-propensity users with high-level templates, medium-level templates, and basic templates respectively, and select the initially selected template with the largest selection value among the high-level template, medium-level template, and basic template as the final advertising template for high-propensity users, medium-propensity users, and low-propensity users. By comprehensively integrating user behavior data, geographical information, and brand characteristics, highly customized advertising content is designed to improve the user attraction and delivery accuracy of the advertisement; through the evaluation of the effective viewing rate, click-through rate, and stay time, user interest hotspots are identified to optimize the advertisement content design and improve the click-through rate and conversion rate; match regional needs, seasons, and climate information to enhance the situational relevance of the advertisement content and increase the user's willingness to participate; by integrating brand characteristic values, the advertisement content can better convey the core concept of the brand, enhance brand recognition, match the characteristics of the brand audience (target age group), and improve the attraction of the advertisement to the brand target group; through the real-time update of user behavior data and regional characteristics, the advertisement content and delivery strategy are continuously adjusted to maintain the continuous attraction and effect of the advertisement; the analysis of the user's industry and the industries where the advertisement template has been used in the past helps to discover potential industry trends and user needs. The advertisement display module accurately displays the personalized advertisement content generated by the advertisement design module and selects an advertisement display strategy according to the user's browsing tendency and regional tendency; the specific steps are as follows: Obtain the user's behavior data and use the formula Calculate the effective viewing rate of each user on the website; use the formula Calculate the advertisement viewing rate of each user on the website; use the formula Calculate the effective viewing rate of each user on the website; take the effective viewing rate of each user 、Advertising click-through rate and effective view rate are substituted into the set formula to calculate the display tendency value of the advertisement , where 、 and are respectively set weight factors; it can be seen from the formula that the higher the effective view rate of each user, the higher the display tendency value of the advertisement; the higher the advertising click-through rate of each user, the higher the display tendency value of the advertisement; the higher the effective view rate of each user, the higher the display tendency value of the advertisement; Obtain the regional information of the user, and use the formula to calculate the demand matching degree of each user in the website; use the formula to calculate the seasonal relevance of each user in the website; use the formula to calculate the climate impact degree of each user in the website; substitute the demand matching degree 、seasonal relevance and climate impact degree into the set formula to calculate the regional tendency value of the advertisement , where 、 and are respectively set weight factors; it can be seen from the formula that the higher the demand matching degree of each user, the higher the regional tendency value of the advertisement; the higher the seasonal relevance of each user, the higher the regional tendency value of the advertisement; the higher the climate impact degree of each user, the higher the regional tendency value of the advertisement; Substitute the display tendency value of the advertisement and the regional tendency value of the advertisement into the set formula to calculate the advertisement display priority value , where and are respectively set weight factors; it can be seen from the formula that the higher the display tendency value of the advertisement, the more opportunities it has to be displayed preferentially, and the higher the advertisement display priority value; the higher the regional tendency value of the advertisement, the more the advertisement content fits the user's region and environment, and the higher the advertisement display priority value; It is set that there is an advertising display threshold range, and the advertising display priority value is compared and analyzed with the set advertising display threshold range; when the advertising display priority value is greater than the maximum value of the set advertising display threshold range, the display strategy is high priority, and the advertisement is directly pushed; when the advertising display priority value is within the set advertising display threshold range, the display strategy is medium priority, and the advertisement is displayed according to the user's active time; when the advertising display priority value is less than the minimum value of the set advertising display threshold range, the display strategy is low priority, and the display frequency is reduced; after confirming the display strategy of the advertisement, the advertisement display module also needs to generate an effect report to help advertisers or platform administrators analyze the advertisement effect. The content of the report includes the total number of times the advertisement is displayed, the click-through rate of the advertisement, and the user's interaction behaviors (such as sharing, commenting, forwarding, etc.); By combining user behavior data (such as browsing rate, click-through rate, and stay time) and regional information (such as geographical location, season, and climate), the display priority is comprehensively analyzed to ensure a high degree of matching between the advertisement content and the user's interests; by preferentially displaying highly relevant advertisements and avoiding displaying advertisements that do not meet the user's needs, the utilization rate of advertising resources is optimized; display advertisement content related to user behavior and environment to improve the visual attractiveness and information relevance of the advertisement; use regional correlation data (demand matching degree, season correlation degree, climate impact degree) to place advertisements to increase the interest and purchase conversion of regional users; dynamically adjust the display priority and advertisement strategy according to user behavior and environmental changes.

[0021] According to an embodiment of the present invention, as Figure 2 shown, there is also provided an advertisement design and display method based on big data. The method includes the following steps: S1: By collecting user behavior data and regional information and sending the collected data to the server for storage; the user behavior data includes: browsing records, browsing stay durations, click data, and search keywords; the regional information includes: the location and meteorological information of the region where the user is located; S2: By comprehensively analyzing factors such as the user's behavior data, interest preferences, geographical location, and seasonality, the user inclination value is obtained, and the advertisement template is matched according to the user inclination value; the specific steps are as follows: Substitute the numerical values of the user's browsing evaluation value and the regional evaluation value into the set formula to calculate the user's advertisement inclination value , where and are respectively the set weight factors; it can be seen from the formula that the larger the user's browsing evaluation value, the larger the user's advertisement inclination value; the larger the user's regional evaluation value, the larger the user's advertisement inclination value; Set an advertising preference threshold range, and compare and analyze the user's advertising preference value with the set advertising preference threshold range; when the user's advertising preference value is greater than the maximum value of the set advertising preference threshold range, mark the user as a high-preference user; when the user's advertising preference value is within the set advertising preference threshold range, mark the user as a medium-preference user; when the user's advertising preference value is less than the minimum value of the set advertising preference threshold range, mark the user as a low-preference user; Set that there is an advertising template library with several advertising templates; set that each user has several corresponding search keywords, and mark the number of keywords as Yn, where n = 1, 2, 3... N, N is a positive integer, N represents the total number of advertising templates, and n represents the serial number of any one advertising template; set that each advertising template has several keywords, compare and match the user's keywords with the advertising templates in the template library, and when there is one or more overlapping keywords between the user's keywords and the advertising template's keywords, mark the advertising template as a preliminary selection template, and mark the number of keywords overlapping with the user in the preliminary selection template as Zn; count the number of users using each preliminary selection template and record it as Qn; retrieve the age of each user, count the users corresponding to each age, select the age with the largest number of corresponding users as the target audience age and mark it as C1; retrieve the user age of each advertising template, count the user age corresponding to each advertising template, select the age with the largest number of corresponding users as the template audience age and mark it as C2; obtain the industry categories used by each preliminary selection template in history, obtain the industry category where the user is located, compare and analyze the user's industry category with the industry category of the preliminary selection template, obtain the number of industry categories where the user's industry category overlaps with the industry category of the preliminary selection template, and mark it as C3; substitute the values of the user keyword quantity Yn, the number of keywords overlapping between the preliminary selection template and the user Zn, the number of users using the preliminary selection template Qn, the target audience age C1, the template audience age C2, and the number of overlapping industry categories C3 into the set formula Calculate the selection value Xn of the preliminary selection template, where a1, a2, a3, and a4 are respectively set weight factors, and e is the natural constant; it can be seen from the formula that the closer the number of keywords overlapping between the preliminary selection template and the user's keywords, the larger the selection value of the preliminary selection template; the more users use the preliminary selection template, the larger the selection value of the preliminary selection template; the closer the target audience age and the template audience age, the larger the selection value of the preliminary selection template; the more the number of overlapping industry categories between the user and the template, the larger the selection value of the preliminary selection template; It is set that there is a threshold range for selecting the primary template, and the selected value of the primary template is compared and analyzed with the set threshold range for selecting the primary template; when the selected value of the primary template is greater than the maximum value of the set threshold range for selecting the primary template, then this template is marked as a high-level template, and the content of the high-level template is highly personalized and has strong visual appeal; when the selected value of the primary template is within the set threshold range for selecting the primary template, then this template is marked as a medium-level template, and the medium-level template pays attention to partial personalization; when the selected value of the primary template is less than the minimum value of the set threshold range for selecting the primary template, then this template is marked as a basic template; the high-propensity users, medium-propensity users, and low-propensity users are respectively matched with high-level templates, medium-level templates, and basic templates, and the primary template with the largest selected value among the high-level templates, medium-level templates, and basic templates is selected as the final advertisement template for high-propensity users, medium-propensity users, and low-propensity users. S3: Accurately display the personalized advertisement content generated by the advertisement design module, and select an advertisement display strategy according to the browsing propensity and regional propensity of the user.

[0022] The above are only embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, various changes and modifications can be made to the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims

1. The advertising design and display system based on big data is characterized by: include: Advertisement design module and advertisement display module; The advertising design module obtains the user propensity value based on comprehensive analysis of the user's behavior data, interest preferences, geographic location, and seasonal factors, and matches the advertising template based on the user propensity value; The specific steps are as follows: An advertisement template library is set, and there are several advertisement templates in the advertisement template library; each user is set to have several corresponding search keywords, and the number of keywords is marked; each advertisement template is set to have several keywords, and the user keywords are compared and matched with the advertisement templates in the template library. When the user's keyword and the advertisement template's keyword have one or more overlapping keywords, the advertisement template is marked as a preliminary template, and the number of keywords in the preliminary template that overlap with the user is marked; the number of users of each preliminary template is counted; the age of each user is retrieved, the users corresponding to each age are counted, and the user with the most corresponding age is selected as the target audience age; Retrieve the user age of each advertising template, count the user ages corresponding to each advertising template, and select the user with the largest age correspondence as the template audience age; Obtain the industry categories that have been used historically by each preliminary template, obtain the industry category to which the user belongs, compare and analyze the industry category of the user with the industry category of the preliminary template, and obtain the number of industry categories that overlap between the user's industry category and the industry category of the preliminary template; normalize the number of user keywords, the number of keywords that overlap between the preliminary template and the user, the number of people using the preliminary template, the age of the target audience, the age of the template audience, and the number of industry category overlaps to obtain the selection value of the preliminary template; A threshold interval for selecting a preliminary template is set, and a selection value of the preliminary template is compared and analyzed with the set threshold interval for selecting the preliminary template; When the selection value of the initial template is greater than the maximum value of the initial template selection threshold interval, the template is marked as an advanced template; when the selection value of the initial template is within the initial template selection threshold interval, the template is marked as an intermediate template; when the selection value of the initial template is less than the minimum value of the initial template selection threshold interval, the template is marked as a basic template; Matching high-inclination users, medium-inclination users and low-inclination users with advanced templates, intermediate templates and basic templates respectively, and selecting the primary template with the largest selection value among the advanced templates, intermediate templates and basic templates as the final advertisement template for high-inclination users, medium-inclination users and low-inclination users; The advertising display module accurately displays the personalized advertising content generated by the advertising design module, and selects advertising display strategies based on users' browsing tendencies and regional tendencies.

2. The advertising design and display system based on big data according to claim 1 is characterized in that: Also includes: Data acquisition module and server; The data collection module is used to collect user behavior data and regional information, and send the collected user behavior data and regional information to the server for storage; User behavior data includes: browsing history, browsing duration, click data and search keywords; regional information includes: location and weather information of the user's area.

3. The advertising design and display system based on big data according to claim 1 is characterized in that: The specific analysis steps for high-intention users, medium-intention users, and low-intention users are as follows: Normalizing the user's browsing evaluation value and the area evaluation value to obtain the user's tendency value; A user tendency threshold interval is set, and the user tendency value is compared with the set advertising tendency threshold interval for analysis; when the user tendency value is greater than the maximum value of the set user tendency threshold interval, the user is marked as a high tendency user; when the user tendency value is within the set user tendency threshold interval, the user is marked as a medium tendency user; when the user tendency value is less than the minimum value of the set user tendency threshold interval, the user is marked as a low tendency user.

4. The advertising design and display system based on big data according to claim 3 is characterized in that: The specific analysis steps for browsing the evaluation value are: Get the number of times a user views each ad on the website each time they log in; set the average number of times users view the website, and divide the two to calculate the user's effective browsing rate; get the number of clicks on each ad by the user, get the number of ads displayed, and divide the two to calculate the user's ad click-through rate; get the time a user stays on the ad webpage, and calculate the average time they stay on the ad webpage each time; The average duration of users' ad viewing in the industry is set, and the effective user viewing rate is calculated by dividing the two. The effective browsing rate, the ad click rate, and the effective user viewing rate are normalized to obtain the browsing evaluation value of each ad.

5. The advertising design and display system based on big data according to claim 3 is characterized in that: The specific analysis steps of regional assessment value are as follows: Get the area where the user is currently located, get the number of advertisements that the user browses and the geographical location of the user's area; get the total number of advertisements in the user's area, divide the two to calculate the matching degree between the advertisements browsed by the user and the demand of the user's area; get the season of the user's area, mark the number of advertisements that the user browses and the season of the user's area, divide the two to calculate the seasonal correlation between the advertisements browsed by the user and the user's area; get the temperature of the user's area; get the comfortable temperature of the user's area, divide the two to calculate the user's climate impact; normalize the values ​​of demand matching, seasonal correlation and climate impact of the user's area to obtain the regional evaluation value.

6. The advertising design and display system based on big data according to claim 1 is characterized in that: The specific advertising display strategy is: An ad display threshold interval is set, and the ad display priority is compared and analyzed with the set ad display threshold interval; when the ad display priority is greater than the maximum value of the set ad display threshold interval, the display strategy is high priority, and the ad is pushed directly; when the ad display priority is within the set ad display threshold interval, the display strategy is medium priority, and the ad is displayed according to the user's active time; when the ad display priority is less than the minimum value of the set ad display threshold interval, the display strategy is low priority, and the display frequency is reduced.

7. The advertising design and display system based on big data according to claim 6 is characterized in that: The specific analysis steps for ad display priority value are as follows: The display tendency value of an advertisement and the regional tendency value of an advertisement are normalized to obtain the display priority value of the advertisement; the higher the display tendency value of an advertisement, the more likely it is to be displayed first, and the higher the display priority of the advertisement; the higher the regional tendency value of an advertisement, the more suitable the advertisement content is for the user's region and environment, and the higher the display priority of the advertisement.

8. The big data-based advertising design and display system according to claim 7, characterized in that: The specific analysis steps of the ad display propensity value are as follows: The effective browsing rate, ad click rate and effective browsing rate of each user are normalized to obtain the display tendency value of the ad.

9. The advertising design and display system based on big data according to claim 1 is characterized in that: The specific analysis steps of the advertising area propensity value are as follows: The values ​​of each user's demand matching, seasonal relevance, and climate influence are normalized to obtain the regional preference value of the advertisement.

10. The advertising design and display method based on big data is characterized by Applied to the big data-based advertising design display system as described in any one of claims 1 to 9, the method comprises the following steps: S1: Collect user behavior data, interest preferences, geographic location, social interaction data and historical advertising response data, and store the collected data; S2: Obtain user propensity values ​​through comprehensive analysis based on user behavior data, interest preferences, geographic location, and seasonal factors, and match advertising templates based on user propensity values; S3: Accurately display the personalized advertising content generated by the advertising design module and select advertising display strategies based on users' browsing preferences and regional preferences.

Images