Advertisement putting method based on user portrait

Abstract

The invention relates to the technical field of directional advertisement, in particular to an advertisement putting method based on a user portrait, which comprises the following steps of: acquiring equipment use time of a target user, recording use types and corresponding use frequencies of software and corresponding advertisement response information, dividing the equipment use time into a plurality of putting characteristic time periods, determining the advertisement putting type of each putting characteristic time period; according to the advertisement feedback attitude of the user in each feature time period, determining an advertisement effective tendency category of the current user in each putting feature time period so as to determine a basic advertisement putting mode; and according to the duration percentage in each time period, determining an advertisement acceptance fluctuation parameter of the user in the current time period so as to judge whether to adjust the advertisement putting content in the current characteristic time period, and according to the advertisement watching duration percentage of each use type of software, determining an adjustment direction. And the overall advertisement putting effect is improved.

Description

Technical Field

[0001] The present invention relates to the field of targeted advertising technology, and in particular to a method for delivering advertisements based on user portraits. Background Art

[0002] Advertisement delivery is supported by big data and artificial intelligence. It obtains basic user information and behavioral data through multi-channel data collection technology (covering dimensions such as social media interaction, browsing tracks, and consumption records), and combines device fingerprints, browser tracking and other tools to achieve cross-scenario behavior linkage. It builds dynamic user portraits with the help of machine learning algorithms (such as cluster analysis and feature engineering), extracts interest tags, consumption capacity, potential needs and other features from massive data, and relies on AI models to iterate portrait dimensions in real time. In the delivery process, it uses keyword matching, interest targeting and other algorithms to achieve precise coupling of advertising content and user characteristics, and dynamically adjusts the delivery strategy with the real-time bidding (RTB) system. At the same time, it uses differential privacy, federated learning and other technologies to balance data utilization and privacy protection within a compliance framework, ultimately forming a full-process technical closed loop from data collection, portrait construction to precise reach.

[0003] Chinese Patent Publication No.: CN116805255B discloses an automatic optimization and delivery system for advertisements based on user portrait analysis, which includes an intelligent push module, a user portrait module, a delivery optimization module and an effect analysis module. The user portrait module is used to label user information based on shopping information to obtain a user portrait model of the user. The intelligent push module is used to automatically deliver advertisements to the user based on the user portrait model. The effect analysis module is used to analyze the traffic effect of the product after the advertisement is delivered, and generate a poor benefit signal, a slow benefit signal or a normal benefit signal. The delivery optimization module is used to receive a delivery optimization instruction and optimize the delivery of the corresponding advertisement of the product. It can be seen that the automatic optimization and delivery system for advertisements based on user portrait analysis has the following problems: it does not take into account the actual needs of the users at different times, and only delivers according to the content, resulting in inaccurate delivery in different time periods. Summary of the Invention

[0004] To this end, the present invention provides an advertising delivery method based on user portraits to overcome the problem in the prior art that the actual needs of the users at different times are not considered, and delivery is only based on the content, resulting in inaccurate delivery in different time periods.

[0005] To achieve the above objectives, the preferred technical solution for the user portrait-based advertising method includes: Obtain the target user's device usage time, software usage type and usage frequency of each software, and advertising response information during the use of each software, wherein the advertising response information includes viewing time percentage and advertising feedback attitude; Divide device usage time into several delivery feature time periods based on the usage type and corresponding usage frequency of each software, and determine the advertising delivery type for each delivery feature time period based on the software usage type and usage frequency; Based on the user's advertising feedback attitude during each characteristic time period, determine the current user's advertising effectiveness tendency category during each delivery characteristic time period to determine the basic advertising delivery method, including: reverse advertising delivery, or targeted delivery based on the advertising delivery type during the characteristic time period; The user's advertising acceptance fluctuation parameter in the current time period is determined based on the percentage of duration monitored in real time during each of the said feature time periods to determine whether to adjust the advertising content of the current feature time period, and the adjustment direction is determined based on the percentage of advertising viewing duration of each type of software used.

[0006] As a preferred technical solution for the user portrait-based advertising method, the device usage time is divided into several characteristic time periods according to the usage type and corresponding usage frequency of each software, including: Divide a single delivery cycle into several delivery feature time periods based on the total usage frequency of all software; Determine the type of advertisement placement for the current characteristic time period based on the type of software used most frequently during each characteristic time period; The lengths of the characteristic delivery time periods are different.

[0007] As a preferred technical solution for the user portrait-based advertising delivery method, the delivery characteristic time period is divided into three types according to the total frequency of software use, including inactive delivery time period, active delivery time period and general delivery time period; If the total usage frequency of all software is less than the inactive frequency threshold, the current delivery feature time period is an inactive delivery time period. If the total usage frequency of all software is greater than or equal to the active frequency threshold, the current delivery feature time period is the active delivery time period; If the total usage frequency of all the software is greater than or equal to the inactive frequency threshold and less than the active frequency threshold, the current delivery feature time period is a general delivery time period.

[0008] As a preferred technical solution for the user portrait-based advertising delivery method, the current user's advertising effectiveness tendency category in each delivery feature time period is determined based on the target user's advertising feedback attitude in each feature time period, including: Determining the target user's attitude towards each advertisement feedback, wherein the advertisement feedback attitude includes positive feedback and negative feedback; Determine the advertising effectiveness trend category for the current time period based on the proportion of negative feedback; If the number of negative feedbacks is greater than the preset negative feedback threshold, the advertisement effectiveness tendency category for the current time period is the advertisement delivery ineffective category; If the number of negative feedbacks is less than or equal to a preset negative feedback threshold, the advertisement effectiveness tendency category in the current time period is the advertisement delivery effectiveness category.

[0009] As a preferred technical solution for the user portrait-based advertising delivery method, the basic advertising delivery method is determined according to the advertising effective tendency category in the current feature time period, including: If the effective advertising tendency category is an effective advertising delivery category, the basic advertising delivery method is to carry out targeted delivery according to the advertising delivery type in the characteristic time period; If the advertisement effective tendency category is the advertisement delivery invalid category, the basic advertisement delivery method is to deliver advertisements in the reverse direction.

[0010] As a preferred technical solution for the user portrait-based advertising method, reverse advertising delivery includes: In response to the user being active in the corresponding delivery time period, an advertisement that is significantly different from the user's information record is delivered, and the user's advertising feedback attitude is recorded, and the delivery is changed in the direction of decreasing difference.

[0011] As a preferred technical solution for the user portrait-based advertising delivery method, determining the advertising acceptance fluctuation parameters within the current delivery feature time period includes: Determine the percentage of viewing time of all ads during the current feature time period and calculate the average; Calculate the average deviation of the percentage of viewing time for all ads; The advertisement acceptance fluctuation parameter is determined according to a ratio of the average deviation to the viewing time percentage and an average value.

[0012] As a preferred technical solution of the user portrait-based advertising delivery method, determining whether to adjust the advertising delivery content in the current characteristic time period according to the advertising acceptance fluctuation parameter includes: If the advertisement acceptance fluctuation parameter is less than or equal to the standard acceptance fluctuation parameter, it is determined that the advertisement delivery content in the current characteristic time period will not be adjusted; If the advertisement acceptance fluctuation parameter is greater than the standard acceptance fluctuation parameter, it is determined to adjust the advertisement delivery content in the current characteristic time period.

[0013] As a preferred technical solution for the user portrait-based advertising delivery method, the adjustment direction is determined according to the percentage of ad viewing time of each type of software, including: Determine the software usage type with the largest average percentage of viewing time as the optimal advertising type; Associate the advertisements for other types of software with the optimal advertisement delivery type and deliver them to the corresponding software.

[0014] The beneficial effects of the present invention are: The present invention analyzes the target users' advertising feedback attitudes in detail, accurately locates the effective advertising tendency categories in each characteristic time period, and determines the basic advertising delivery method based on this. Combined with the reasonable negative feedback threshold setting, it can effectively distinguish between effective and ineffective advertising delivery categories, thereby achieving accurate advertising resource delivery and enhancing the efficiency of advertising delivery; for active delivery time periods, delivery of advertisements that are significantly different from the information obtained by users can avoid information cocoons, enhance the freshness and attractiveness of advertisements, and increase clicks and conversions; in inactive and general time periods, a reverse advertising delivery strategy is adopted to change the advertising content recommendation method, re-increase advertising attention, and optimize delivery efficiency, so that advertising resources can accurately reach users in different time periods. users, improving the overall advertising effect; by calculating the average and average deviation of the viewing time percentage, and further calculating their ratio to determine the advertising acceptance fluctuation parameter, it can accurately reflect the discrete degree of user viewing behavior, effectively avoid misjudgment due to differences in user viewing habits, and comprehensively improve advertising effect and user acceptance; by quantitatively analyzing the percentage of advertising viewing time of different software usage types, accurately identifying the software type that users are most interested in as the optimal advertising type, and linking advertisements of other types of software with it, it can accurately locate user interests and improve the relevance of advertising, thereby increasing the click-through rate and conversion rate of advertisements, optimizing the allocation of advertising resources, and improving the overall advertising effect.

[0015] In particular, the present invention meticulously analyzes the target user's advertising feedback attitudes, accurately identifies the effective advertising tendency categories in each characteristic time period, and uses this as a basis to determine the basic advertising delivery method. By setting a reasonable negative feedback threshold and combining it with the user's negative feedback behavior, it can effectively distinguish between effective and ineffective advertising delivery categories. When the feedback is positive, targeted delivery is implemented to improve advertising effectiveness; when the negative feedback exceeds the threshold, a reverse delivery strategy is initiated, using adversarial training to generate new reach content, avoiding traditional invalid traffic, thereby optimizing delivery efficiency, achieving precise delivery of advertising resources, and enhancing the efficiency of advertising delivery.

[0016] In particular, this method avoids information cocoons by placing ads that differ significantly from the information users acquire during active time periods. By rotating ads based on decreasing differences, the ads become more fresh and engaging, increasing clicks and conversions. During inactive and general time periods, maintaining the same ad type but modifying the recommendation method—for example, using a different tone, image, and copy—can re-engage the ads. This approach also avoids traditional ineffective traffic, optimizes delivery efficiency, and allows advertising resources to precisely reach users during different time periods, improving overall advertising effectiveness.

[0017] In particular, in the present invention, by calculating the average value and the average deviation of the viewing time percentage, and further calculating their ratio to determine the advertising acceptance fluctuation parameter, it can accurately reflect the discrete degree of user viewing behavior and effectively avoid misjudgment caused by differences in user viewing habits. This parameter does not simply rely on a fixed viewing time, but considers the discrete degree of the viewing time percentage, which can more comprehensively reflect the user's average satisfaction with the advertisement and improve the advertising delivery effect.

[0018] In particular, in the present invention, by quantitatively analyzing the percentage of advertisement viewing time of different software usage types, the software type that users are most interested in is accurately identified as the optimal advertisement delivery type, and advertisements of other types of software are associated with it for delivery. This can accurately locate user interests, improve the relevance of advertisement delivery, and thus increase the click-through rate and conversion rate of advertisements; in addition, it can also optimize the allocation of advertising resources, and allocate more resources to software types that users are more concerned about, avoid wasting resources on inefficient types, and improve the overall delivery effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flow chart of a method for delivering advertisements based on user portraits according to an embodiment of the present invention; Figure 2 A logic diagram for determining advertisement effectiveness tendency categories according to an embodiment of the present invention; Figure 3 This is a logic diagram for determining whether to adjust the advertisement delivery content during the current feature time period according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] 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 merely used to explain the present invention and are not intended to limit the present invention.

[0021] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0022] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0023] See also Figure 1 As shown, it is a flow chart of an advertising delivery method based on user portraits according to an embodiment of the present invention. The present invention provides an advertising delivery method based on user portraits, comprising: Step S1, obtaining the target user's device usage time, software usage type and usage frequency of each software, and advertising response information during the use of each software, wherein the advertising response information includes viewing time percentage and advertising feedback attitude; Step S2: Divide the device usage time into several delivery feature time periods according to the usage type of each software combined with the corresponding usage frequency, and determine the advertisement delivery type for each delivery feature time period based on the software usage type combined with the usage frequency; Step S3, based on the user's advertising feedback attitude in each characteristic time period, determining the current user's advertising effectiveness tendency category in each delivery characteristic time period, so as to determine a basic advertising delivery method, including: reverse advertising delivery, or targeted delivery based on the advertising delivery type in the characteristic time period; Step S4, determining the user's advertising acceptance fluctuation parameter in the current time period based on the percentage of duration monitored in real time during each of the said feature time periods, to determine whether to adjust the advertising delivery content of the current feature time period, and determining the adjustment direction based on the percentage of advertising viewing duration of each type of software used.

[0024] In implementation, software usage types include social entertainment, office tools, life services, and education and culture.

[0025] It should be noted that the target user information involved in this implementation (including but not limited to account device information, user personal information, etc.) and related data are all information authorized by the account or authorized by all parties.

[0026] The present invention analyzes the target users' advertising feedback attitudes in detail, accurately locates the effective advertising tendency categories in each characteristic time period, and determines the basic advertising delivery method based on this. Combined with the reasonable negative feedback threshold setting, it can effectively distinguish between effective and ineffective advertising delivery categories, thereby achieving accurate advertising resource delivery and enhancing the efficiency of advertising delivery; for active delivery time periods, delivery of advertisements that are significantly different from the information obtained by users can avoid information cocoons, enhance the freshness and attractiveness of advertisements, and increase clicks and conversions; in inactive and general time periods, a reverse advertising delivery strategy is adopted to change the advertising content recommendation method, re-increase advertising attention, and optimize delivery efficiency, so that advertising resources can accurately reach users in different time periods. users, improving the overall advertising effect; by calculating the average and average deviation of the viewing time percentage, and further calculating their ratio to determine the advertising acceptance fluctuation parameter, it can accurately reflect the discrete degree of user viewing behavior, effectively avoid misjudgment due to differences in user viewing habits, and comprehensively improve advertising effect and user acceptance; by quantitatively analyzing the percentage of advertising viewing time of different software usage types, accurately identifying the software type that users are most interested in as the optimal advertising type, and linking advertisements of other types of software with it, it can accurately locate user interests and improve the relevance of advertising, thereby increasing the click-through rate and conversion rate of advertisements, optimizing the allocation of advertising resources, and improving the overall advertising effect.

[0027] Specifically, in step S2, the device usage time is divided into several characteristic time periods according to the usage type and corresponding usage frequency of each software, including: Divide a single delivery cycle into several delivery feature time periods based on the total usage frequency of all software; Determine the type of advertisement placement for the current characteristic time period based on the type of software used most frequently during each characteristic time period; The lengths of the characteristic delivery time periods are different.

[0028] It is understandable that for a single user, the type and frequency of use of each software on the device will change over time. For example, during working hours, the frequency of use of social entertainment software is relatively low, while the frequency of use of office tools is relatively high, and the total frequency of software use is also relatively low. On the contrary, for non-working hours, such as leisure time at night, the frequency of users using social entertainment, life services, and education and culture software will increase significantly, and the total frequency of software use will also increase. During inactive time, such as deep sleep, users will hardly actively use any software, and the device is usually in standby or locked state. The frequency and duration of software use are reduced to extremely low levels. In contrast, when it is difficult to fall asleep or when about to fall asleep, some users may briefly use some sleep-aid software, such as light music players, white noise applications, etc. Therefore, the frequency of use in this part of the feature time period is not 0.

[0029] Specifically, the delivery characteristic time period includes the total frequency of software use, which is divided into three types, including inactive delivery time period, active delivery time period and general delivery time period; If the total usage frequency of all software is less than the inactive frequency threshold, the current delivery feature time period is an inactive delivery time period. If the total usage frequency of all software is greater than or equal to the active frequency threshold, the current delivery feature time period is the active delivery time period; If the total usage frequency of all the software is greater than or equal to the inactive frequency threshold and less than the active frequency threshold, the current delivery feature time period is a general delivery time period.

[0030] In implementation, the inactive frequency threshold is initially set to less than 5 times of use per hour, and the active frequency threshold is initially set to greater than or equal to 20 times of use per hour. Each threshold can be adaptively adjusted according to the actual usage frequency and life time of the target user. It is sufficient to divide each target user according to actual usage without making specific restrictions.

[0031] Understandably, software usage is generally very low during inactive periods, such as when users are in deep sleep or busy working. For example, from late night to early morning, most people are asleep and rarely use software. A lower threshold can effectively identify these inactive periods and avoid unnecessary advertising during these times, thereby reducing user disruption and improving the effectiveness and targeting of advertising.

[0032] During active periods like leisure time, entertainment time, or weekday breaks, users have more free time and are more willing to use various apps. For example, between 7:00 PM and 10:00 PM, people tend to relax and frequently use social, entertainment, and shopping apps. During weekday lunch breaks, some users also browse news and play music. A higher active frequency threshold accurately captures these peak usage times. Placing ads during these times can increase ad exposure and click-through rates, effectively reaching target users.

[0033] Typically, the usage frequency corresponding to the advertising time period falls between inactive and active. Users' software usage frequency during this time period is relatively moderate, with a certain demand for software usage, but not yet reaching a high level of activity. For example, during weekday mornings and afternoons, users may occasionally use work-related tools, but the frequency of use is relatively low. Alternatively, during the daytime on weekends, users may intermittently use software while performing household chores or other leisure activities. When targeting advertising during these time periods, advertisers can choose advertising content that is relevant to the user behavior characteristics during this time period, based on their goals, to achieve optimal advertising results.

[0034] See also Figure 2 As shown in FIG. , it is a logic diagram for determining the effective advertising tendency category according to an embodiment of the present invention. In step S3, the effective advertising tendency category of the current user in each delivery feature time period is determined based on the advertising feedback attitude of the target user in each feature time period, including: Determining the target user's attitude towards each advertisement feedback, wherein the advertisement feedback attitude includes positive feedback and negative feedback; Determine the advertising effectiveness trend category for the current time period based on the proportion of negative feedback; If the number of negative feedbacks is greater than the preset negative feedback threshold, the advertisement effectiveness tendency category for the current time period is the advertisement delivery ineffective category; If the number of negative feedbacks is less than or equal to a preset negative feedback threshold, the advertisement effectiveness tendency category in the current time period is the advertisement delivery effectiveness category.

[0035] In practice, negative feedback means that the advertisement stays on the screen for less than 2 seconds, or an option such as blocking is selected in which the viewer hopes not to see the advertisement again. Negative feedback on the advertisement is considered positive feedback.

[0036] The preset negative feedback threshold is determined based on industry reports in the e-commerce advertising field. The negative feedback threshold is usually set at 8% to 15%, and 11.5% is preferably used as the preset negative feedback threshold.

[0037] Specifically, determining a basic advertising delivery method according to the advertising effectiveness tendency category in the current characteristic time period includes: If the effective advertising tendency category is an effective advertising delivery category, the basic advertising delivery method is to carry out targeted delivery according to the advertising delivery type in the characteristic time period; If the advertisement effective tendency category is the advertisement delivery invalid category, the basic advertisement delivery method is to deliver advertisements in the reverse direction.

[0038] It is understandable that, based on negative feedback data on users’ ad avoidance behavior (such as blocking frequency and exposure termination speed), adversarial training mechanisms are used to generate counterintuitive engagement content, avoiding traditional invalid traffic and optimizing overall delivery efficiency.

[0039] In this invention, by meticulously analyzing target users' advertising feedback attitudes, we accurately identify the effective advertising categories during each characteristic time period, and based on this, determine the basic advertising delivery method. By setting a reasonable negative feedback threshold and combining it with users' negative feedback behavior, we can effectively distinguish between effective and ineffective advertising delivery categories. When feedback is positive, targeted delivery is implemented to improve advertising effectiveness. When negative feedback exceeds the threshold, a reverse delivery strategy is initiated, using adversarial training to generate new reach content, avoiding traditional invalid traffic, thereby optimizing delivery efficiency, achieving precise delivery of advertising resources, and enhancing the efficiency of advertising delivery.

[0040] Specifically, reverse advertising includes: In response to the user being active in the corresponding delivery time period, an advertisement that is significantly different from the user's information record is delivered, and the user's advertising feedback attitude is recorded, and the delivery is changed in the direction of decreasing difference.

[0041] In practice, for reverse advertising during inactive and general delivery periods, the type of advertising delivered is the same as that during the user's current feature period, but with a different advertising content recommendation method. The different ways of recommending the content of the advertisement include that the tone, images, and copy of the advertisement are opposite to the common content of this type of advertisement.

[0042] In this method, during active time periods, ads that differ significantly from the information users acquire can avoid information cocoons. Alternating ads based on the difference from largest to smallest enhances the freshness and appeal of ads, increasing clicks and conversions. During inactive and general time periods, maintaining the same ad type but varying the recommendation method—for example, using a different tone, image, and copy—can re-engage ad attention. This approach also avoids traditional ineffective traffic, optimizes delivery efficiency, and allows ad resources to precisely reach users during different time periods, improving overall ad delivery effectiveness.

[0043] Specifically, in step S4, determining the advertisement acceptance fluctuation parameter within the current delivery characteristic time period includes: Determine the percentage of viewing time of all ads during the current feature time period and calculate the average; Calculate the average deviation of the percentage of viewing time for all ads; The advertisement acceptance fluctuation parameter is determined according to a ratio of the average deviation to the viewing time percentage and an average value.

[0044] Advertisement acceptance fluctuation parameter is used to characterize the degree of dispersion of advertisement viewing time distribution.

[0045] See also Figure 3 As shown, it is a logic diagram of determining whether to adjust the advertising content of the current characteristic time period according to an embodiment of the present invention. The determination of whether to adjust the advertising content of the current characteristic time period according to the advertisement acceptance fluctuation parameter includes: If the advertisement acceptance fluctuation parameter is less than or equal to the standard acceptance fluctuation parameter, it is determined that the advertisement delivery content in the current characteristic time period will not be adjusted; If the advertisement acceptance fluctuation parameter is greater than the standard acceptance fluctuation parameter, it is determined to adjust the advertisement delivery content in the current characteristic time period.

[0046] In practice, the standard acceptance fluctuation parameter is determined based on the interval formed by the difference between the mean and twice the standard deviation of the historically recorded advertising acceptance fluctuation parameter for the same type of advertising, without instances of ineffective advertising. In statistics, approximately 95% of data under a normal distribution falls within the interval of ±2 standard deviations from the mean. Using this interval as a reference effectively filters out interference from extreme outliers, making the standard more stable and reliable.

[0047] It's understandable that using the ad acceptance fluctuation parameter to determine whether to adjust content delivery is based on its accurate reflection of the discrete degree of user viewing behavior. This measurement method effectively captures average user satisfaction with ads and avoids misjudgments due to differences in viewing habits (such as accelerated playback, half-watching, and skipping). Different viewing habits can result in varying viewing times for the same ad. The ad acceptance fluctuation parameter, by calculating the discrete degree of viewing time percentages rather than relying solely on fixed time periods, more comprehensively reflects the stability of user acceptance and overall satisfaction with ad content. This measurement standard allows advertisers to adjust their advertising strategies promptly and accurately based on actual user feedback, thereby improving ad delivery effectiveness and user acceptance.

[0048] In the present invention, the advertising acceptance fluctuation parameter is determined by calculating the average value and average deviation of the viewing time percentage and further calculating their ratio, which can accurately reflect the discrete degree of user viewing behavior and effectively avoid misjudgment caused by differences in user viewing habits. This parameter does not simply rely on a fixed viewing time, but considers the discrete degree of the viewing time percentage, which can more comprehensively reflect the user's average satisfaction with the advertisement and improve the advertising delivery effect.

[0049] Specifically, the adjustment direction is determined based on the percentage of ad viewing time for each type of software, including: Determine the software usage type with the largest average percentage of viewing time as the optimal advertising type; Associate the ads for other types of software with the optimal ad placement type and place them in the corresponding software.

[0050] In the present invention, by quantitatively analyzing the percentage of advertisement viewing time of different software usage types, the software type that users are most interested in is accurately identified as the optimal advertisement delivery type, and advertisements of other types of software are associated with it for delivery. This can accurately locate user interests and improve the relevance of advertisement delivery, thereby increasing the click-through rate and conversion rate of advertisements. In addition, it can also optimize the allocation of advertising resources, and allocate more resources to software types that users are more concerned about, avoiding waste on inefficient types, and improving the overall delivery effect.

[0051] If the user profile-based advertising delivery method of the present invention is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0052] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions and operations of the devices, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of the code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based device that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0053] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0054] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A method for delivering advertisements based on user portraits, characterized in that: include: Obtain the target user's device usage time, software usage type and usage frequency of each software, and advertising response information during the use of each software, wherein the advertising response information includes viewing time percentage and advertising feedback attitude; Divide device usage time into several delivery feature time periods based on the usage type and corresponding usage frequency of each software, and determine the advertising delivery type for each delivery feature time period based on the software usage type and usage frequency; Based on the user's advertising feedback attitude during each characteristic time period, determine the current user's advertising effectiveness tendency category during each delivery characteristic time period to determine the basic advertising delivery method, including: reverse advertising delivery, or targeted delivery based on the advertising delivery type during the characteristic time period; The user's advertising acceptance fluctuation parameter in the current time period is determined based on the percentage of duration monitored in real time during each of the said feature time periods to determine whether to adjust the advertising content of the current feature time period, and the adjustment direction is determined based on the percentage of advertising viewing duration of each type of software used.

2. The method for delivering advertisements based on user portraits according to claim 1, characterized in that: The device usage time is divided into several characteristic time periods based on the usage type and corresponding usage frequency of each software, including: Divide a single delivery cycle into several delivery feature time periods based on the total usage frequency of all software; Determine the type of advertisement placement for the current characteristic time period based on the type of software used most frequently during each characteristic time period; The lengths of the characteristic delivery time periods are different.

3. The method for delivering advertisements based on user portraits according to claim 2, characterized in that: The delivery characteristic time period is divided into three types according to the total frequency of software use, including an inactive delivery time period, an active delivery time period, and a general delivery time period; If the total usage frequency of all software is less than the inactive frequency threshold, the current delivery feature time period is an inactive delivery time period. If the total usage frequency of all software is greater than or equal to the active frequency threshold, the current delivery feature time period is the active delivery time period; If the total usage frequency of all the software is greater than or equal to the inactive frequency threshold and less than the active frequency threshold, the current delivery feature time period is a general delivery time period.

4. The method for delivering advertisements based on user portraits according to claim 3, characterized in that: Determining the advertising effectiveness tendency category of the current user in each delivery feature time period based on the target user's advertising feedback attitude in each feature time period includes: Determining the target user's attitude towards each advertisement feedback, wherein the advertisement feedback attitude includes positive feedback and negative feedback; Determine the advertising effectiveness trend category for the current time period based on the proportion of negative feedback; If the number of negative feedbacks is greater than the preset negative feedback threshold, the advertisement effectiveness tendency category for the current time period is the advertisement delivery ineffective category; If the number of negative feedbacks is less than or equal to a preset negative feedback threshold, the advertisement effectiveness tendency category in the current time period is the advertisement delivery effectiveness category.

5. The method for delivering advertisements based on user portraits according to claim 4, characterized in that: The basic advertising delivery method is determined according to the advertising effective tendency category in the current characteristic time period, including: If the effective advertising tendency category is an effective advertising delivery category, the basic advertising delivery method is to carry out targeted delivery according to the advertising delivery type in the characteristic time period; If the advertisement effective tendency category is the advertisement delivery invalid category, the basic advertisement delivery method is to deliver advertisements in the reverse direction.

6. The method for delivering advertisements based on user portraits according to claim 5, characterized in that: Reverse advertising includes: In response to the user being active in the corresponding delivery time period, an advertisement that is significantly different from the user's information record is delivered, and the user's advertising feedback attitude is recorded, and the delivery is changed in the direction of decreasing difference.

7. The method for delivering advertisements based on user portraits according to claim 6, characterized in that: Determine the advertising acceptance fluctuation parameters within the current delivery feature time period, including: Determine the percentage of viewing time of all ads during the current feature time period and calculate the average; Calculate the average deviation of the percentage of viewing time for all ads; The advertisement acceptance fluctuation parameter is determined according to a ratio of the average deviation to the viewing time percentage and an average value.

8. The method for delivering advertisements based on user portraits according to claim 7, characterized in that: Determining whether to adjust the advertisement delivery content in the current characteristic time period according to the advertisement acceptance fluctuation parameter includes: If the advertisement acceptance fluctuation parameter is less than or equal to the standard acceptance fluctuation parameter, it is determined that the advertisement delivery content in the current characteristic time period will not be adjusted; If the advertisement acceptance fluctuation parameter is greater than the standard acceptance fluctuation parameter, it is determined to adjust the advertisement delivery content in the current characteristic time period.

9. The method for delivering advertisements based on user portraits according to claim 8, characterized in that: The adjustment direction is determined based on the percentage of ad viewing time for each type of software, including: Determine the software usage type with the largest average percentage of viewing time as the optimal advertising type; Associate the advertisements for other types of software with the optimal advertisement delivery type and deliver them to the corresponding software.

Images