CN120563178B - Personalized advertisement content accurate delivery method and system based on user portrait - Google Patents
Personalized advertisement content accurate delivery method and system based on user portraitInfo
- Publication number
- CN120563178B CN120563178B CN202510700618.7A CN202510700618A CN120563178B CN 120563178 B CN120563178 B CN 120563178B CN 202510700618 A CN202510700618 A CN 202510700618A CN 120563178 B CN120563178 B CN 120563178B
- Authority
- CN
- China
- Prior art keywords
- advertisement
- played
- playing
- advertisements
- display unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0244—Optimization
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0247—Calculate past, present or future revenues
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明公开了基于用户画像的个性化广告内容精准投放方法与系统，属于智能推广技术领域，该方法结合性别/年龄等用户画像特征与电梯场景实时数据，通过动态计算广告播放效益得分R，实现广告内容与当前受众的精准匹配，提升单次广告的转化效率。另外本发明采用效益得分排序与广告重要性双重评估机制，通过H1值最小化算法动态生成最优播放方案，既保障高价值广告的曝光权益，又能根据历史效果实时优化播放策略。本发明通过引入完成比例标准差监测，通过动态调整播放顺序平衡各广告的进度差异。有效避免部分广告因效益得分低而长期积压。
This invention discloses a method and system for precise delivery of personalized advertising content based on user profiles, belonging to the field of intelligent promotion technology. This method combines user profile characteristics such as gender/age with real-time data from elevator scenarios, dynamically calculating the advertising playback effectiveness score R to achieve precise matching between advertising content and the current audience, thereby improving the conversion efficiency of a single advertisement. Furthermore, this invention employs a dual evaluation mechanism of effectiveness score ranking and advertising importance, dynamically generating the optimal playback plan through an H1 minimum algorithm. This ensures the exposure rights of high-value advertisements while optimizing the playback strategy in real time based on historical performance. By introducing completion ratio standard deviation monitoring, this invention balances the progress differences of various advertisements by dynamically adjusting the playback order, effectively preventing some advertisements from accumulating due to low effectiveness scores.
Description
Technical Field
The invention belongs to the technical field of intelligent popularization, and particularly relates to a personalized advertisement content accurate delivery method and system based on user portraits.
Background
Since the birth of the 90 th century of the 20 th century, elevator advertisements are subjected to three main technical development stages, namely static plane advertisements mainly comprise paper or frame posters, and are put in depending on limited tags such as building types, people stream time periods and the like, so that the problems of extensive put in, difficulty in quantification of effects, homogenization of contents and the like exist. Outside-elevator LCD advertisements, which are characterized in that dynamic video advertisements are introduced by enterprises such as mass media, so that visual impact is enhanced, the outside-elevator LCD advertisements are still limited by short waiting time (usually less than 10 seconds) and cannot be matched with user attributes accurately. And the intelligent screen advertisement in the elevator adopts a digital screen for enterprises such as new trend media and the like, supports the functions of dynamic content update, AI visual identification, time-period throwing and interaction, and gradually replaces the traditional frame advertisement and outside the elevator.
Although intelligent screen technology has significantly improved advertising efficiency, there is a technical bottleneck that the lack of dynamic analysis of the real-time behavior of the elevator passengers results in a lower interest prediction accuracy. The putting mode still has resource waste, the traditional CPD (daily charge) mode is easy to cause 'empty ladder playing', the content generation and scene suitability are poor, the advertisement content is mostly a fixed template, and the advertisement content cannot be adjusted in real time according to the characteristics (such as age and sex) of a person taking a ladder. For example, when the maternal and infant advertisement is put in the aged community, the conversion rate is reduced by more than 40 percent, and the invention provides the following technical scheme for solving the problems.
Disclosure of Invention
The invention aims to provide a personalized advertisement content accurate delivery method and system based on user portraits, which solve the problems of poor advertisement delivery flexibility and low conversion rate in the prior art.
The aim of the invention can be achieved by the following technical scheme:
The personalized advertisement content accurate delivery method based on the user portrait comprises the following steps:
First, confirming audience group types and corresponding image data of each advertisement;
acquiring the duty ratio ai of the audience group types corresponding to each advertisement;
i takes the value of 1 to n, n represents the audience group category number;
Secondly, at the moment t1 before the next advertisement is played, acquiring image information in the elevator through an image acquisition unit in the elevator, wherein t1 is a preset value;
Analyzing and obtaining the gender and age of each person in the elevator;
dividing the personnel in the elevator into a plurality of person groups according to the gender and age of each personnel in the elevator, wherein each person group corresponds to one audience group type;
Acquiring each advertisement playable by the display unit and recording the advertisement as an advertisement to be played;
acquiring an advertisement playing benefit score R corresponding to the character composition in the current elevator when each advertisement to be played is supposed to be played;
And thirdly, adopting the advertisement to be played with the corresponding advertisement playing benefit score Rmax as the finally determined advertisement to be played next.
When the audience group category number is determined, the duty ratio of each audience group is ordered according to the order from big to small, then the duty ratios are added according to the order from big to small until the comprehensive duty ratio exceeds a preset proportion coefficient, the audience group participating in the summation calculation is taken as the audience group category of the finally confirmed advertisement, and the duty ratio normalization processing is carried out.
As a further scheme of the invention, the method for calculating the advertisement playing benefit score R is as follows
Where ai represents the corresponding duty ratio of each person group, bi represents the number of people in each person group in the elevator.
As a further scheme of the invention, the method also comprises an advertisement playing scheme optimizing strategy, comprising the following steps:
Acquiring advertisement playing benefit scores R of advertisements played by each display unit in a past preset time range;
For a display unit, ordering all advertisements played by the display unit according to the sequence from the higher to the lower of the sum of corresponding advertisement playing benefit scores R, and representing the advertisement as ek;
wherein k represents the corresponding order of each advertisement, ek represents the sum of specific advertisement playing benefit scores R;
Sequencing according to the sequence of the advertisement importance from big to small, and then determining display units for each advertisement according to the sequence to form a plurality of schemes;
For one scheme, after all advertisements are determined by the display units, calculating the sequence of each advertisement in a plurality of corresponding display units, and further calculating the sum H of the sequences corresponding to each advertisement;
The sum H1 of the sum H of all advertisement corresponding sequences is calculated;
And sequentially calculating H1 values corresponding to the schemes, determining a set of scheme with the minimum H1 as a finally determined advertisement playing scheme, and playing the advertisement according to the advertisement playing scheme in the next period.
As a further scheme of the invention, when the number of advertisements to be played changes:
If the number is reduced on the basis of the prior art, deleting the playing of the advertisement which is correspondingly reduced in the advertisement playing scheme;
When the number is increased, the increased advertisements are subjected to trial playing in each display unit, and then an advertisement playing scheme optimizing strategy is executed according to the playing result.
As a further scheme of the present invention, when the number of advertisements to be played and the playing amount requirement of each advertisement are determined, the playing order of each advertisement is further allocated, and the specific steps are as follows:
sequentially calculating to obtain advertisement playing benefit scores R of the advertisements to be played;
acquiring the completion proportion cj of each advertisement to be played in the current period, wherein j is 1 to m, and m represents the number of advertisements to be played;
The completion proportion refers to the sum of the corresponding advertisement playing benefit scores R of each time of playing the advertisement to be played in the current period and/or the sum of the advertisement playing benefit scores R required to be completed in the current period;
Before a new advertisement to be played is played, calculating the completion proportion cj of each advertisement to be played, and then calculating the standard deviation S1 of m cj values;
calculating a standard deviation S2 corresponding to the advertisements to be played after the proportion cj is updated after the advertisements to be played are played;
And calculating m corresponding |S1-S2| values, selecting an advertisement to be played corresponding to an S2 value with the minimum corresponding |S1-S2| value, and taking the advertisement to be played as an advertisement to be played next by the display unit.
As a further scheme of the invention, the method for adjusting the quantity of the advertisements to be played of each display unit is further included, and specifically comprises the following steps:
When one display unit finishes playing of the advertisement to be played in one period;
Firstly, confirming whether time remains in the period, and if so, adding the number of advertisements to be played in the display unit;
If not, the following steps:
for one advertisement, acquiring the order g of the corresponding advertisement playing benefits R when the advertisement is used as the advertisement to be played every time;
acquiring an average value G of an order G corresponding to each play of the advertisement in the whole period;
Acquiring an average value Gp of G values of all advertisements to be played after one display unit finishes playing the advertisements to be played in one period;
And when the average value Gp is larger than a preset value Gy, adding the number of advertisements to be played in the display unit.
The invention also discloses a personalized advertisement content accurate delivery system based on the user portrait, which is used for executing the delivery method, and comprises the following steps:
the image acquisition unit is used for acquiring scene images in the elevator and transmitting the acquired scene image information to the image analysis unit;
The image analysis unit is used for analyzing the scene image and identifying the number, sex and age information of the people in the scene image;
the main control unit is used for determining the next played advertisement according to the crowd figure data in the elevator analyzed by the image analysis unit;
and the display unit is used for playing the advertisement.
The invention has the beneficial effects that:
According to the invention, by combining the user portrait characteristics such as gender/age and the elevator scene real-time data and dynamically calculating the advertisement playing benefit score R, the accurate matching of advertisement content and current audience is realized, and the conversion efficiency of single advertisement is improved.
The invention adopts a benefit score ordering and advertisement importance dual evaluation mechanism, dynamically generates an optimal playing scheme through an H1 value minimization algorithm, ensures the exposure rights and interests of high-value advertisements, and can optimize the playing strategy in real time according to the historical effect.
The invention balances the progress difference of each advertisement by dynamically adjusting the playing sequence by introducing the standard deviation monitoring (|S1-S2|minimization principle) of the completion proportion. Experimental data shows that the method can reduce the advertisement progress deviation by about 37 percent (taking a week as a unit for periodic test), and effectively avoid long-term backlog of partial advertisements due to low benefit scores.
According to the invention, the advertisement bearing capacity of the low-efficiency display unit is intelligently expanded through comparison of the advertisement benefit sequence average value Gp and the threshold value Gy. Practical application shows that the strategy can improve advertising benefit of a single elevator screen by 15-22%.
According to the invention, through space-time double-dimensional intelligent decision, the optimal balance of accurate delivery, dynamic tuning and resource utilization is realized in an elevator advertisement scene, and the method is particularly suitable for advertisement value mining of a high-fluidity closed space.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a flow chart of a personalized advertising content accurate delivery method based on user portraits according to an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
The personalized advertisement content accurate delivery method based on the user portrait, as shown in fig. 1, comprises the following steps:
the first step, confirming the audience group types of each advertisement and the image data of each audience group;
acquiring the duty ratio ai of the audience group types corresponding to each advertisement;
i takes the value of 1 to n, n represents the audience group category number;
because the audience group composition of many products is complex, besides the main audience groups, the audience group composition also comprises many other audience groups with smaller occupation ratio, in order to simplify calculation, the occupation ratios of the audience groups can be ordered from big to small, and then added according to the order of the occupation ratios until the comprehensive occupation ratio exceeds a preset proportionality coefficient, the audience group participating in the summation calculation is taken as the audience group type of the finally confirmed advertisement, and the occupation ratio of the audience group types of the finally confirmed advertisement is expanded in equal proportion, so that the sum of the occupation ratios of the audience group types of the finally confirmed advertisement is 1;
the audience group portrait data here includes gender and age;
specifically, audience images of the products corresponding to the advertisements can be obtained through purchasing records, questionnaires, and the like, and the method for obtaining the audience images is a common known technology in investigation, so that specific description and limitation are not made here;
Secondly, at the moment t1 before the next advertisement is played, acquiring image information in the elevator through an image acquisition unit in the elevator, wherein t1 is a preset value;
the image analysis unit is used for analyzing the image information acquired by the image acquisition unit to acquire the gender and age of each person in the elevator;
classifying the personnel in the elevator according to the gender and age of each personnel in the elevator, dividing the personnel into a plurality of person groups, wherein each person group corresponds to one audience group type;
acquiring advertisements which can be played by the display unit, and marking the advertisements as advertisements to be played for the clarity of subsequent expression;
acquiring an advertisement playing benefit score R corresponding to the character composition in the current elevator when each advertisement to be played is supposed to be played;
The method for calculating the advertisement playing benefit score R is as follows
Wherein ai represents the corresponding duty ratio of each person group, bi represents the number of people in each person group in the elevator;
After being calculated according to the method, the larger the primary advertisement playing benefit score R of one advertisement to be played is, the higher the playing effect and benefit are.
And thirdly, adopting the advertisement to be played with the corresponding advertisement playing benefit score R with the largest value as the finally determined advertisement to be played next, and fully utilizing the stream resources in the mode to maximize the benefit of advertisement playing.
Fourthly, obtaining advertisement playing benefit scores R of advertisements played by the display units in a past preset time range;
For a display unit, ordering all advertisements played by the display unit according to the sequence from the higher to the lower of the sum of corresponding advertisement playing benefit scores R, and representing the advertisement as ek;
wherein k represents the corresponding order of each advertisement, ek represents the sum of specific advertisement playing benefit scores R;
Fifthly, sequencing all advertisements according to the sequence from big to small of importance scores of the advertisements, and then determining a display unit for playing all advertisements according to the sequence;
according to different choices, a plurality of schemes are formed;
For one scheme, after all advertisements are determined by the display units, calculating the sequence of each advertisement in a plurality of corresponding display units, and further calculating the sum H of the sequences corresponding to each advertisement;
The sum H1 of the sum H of all advertisement corresponding sequences is calculated;
And sequentially calculating H1 values corresponding to the schemes, determining a set of scheme with the minimum H1 as a finally determined advertisement playing scheme, and playing the advertisement according to the advertisement playing scheme in the next period.
The importance score of the advertisement may be determined based on revenue of the advertisement, the higher the revenue, the higher the corresponding score.
When the number of advertisements to be played changes:
If the number is reduced on the basis of the prior art, deleting the playing of the advertisement which is correspondingly reduced in the advertisement playing scheme;
When the number is increased, the increased advertisements are subjected to trial playing in each display unit (namely, the increased advertisements are added to the advertisements to be played in each display unit), and then the operations in the fourth step and the fifth step are executed according to the playing result.
Example two
In practical operation, the method in the first embodiment promotes the effect of delivering partial advertisements, and has a negative effect on the effect of delivering other partial advertisements, so that the embodiment further distributes the playing order of each advertisement when the number of advertisements to be played and the playing amount requirement of each advertisement are determined based on the first embodiment, and the specific steps are as follows:
according to the method in the second step in the first embodiment, sequentially calculating to obtain advertisement playing benefit scores R of the advertisements to be played;
Acquiring the completion proportion cj of each advertisement to be played in the current period, wherein j takes a value of 1 to m, and m represents the number of advertisements to be played;
the period may be one day, one week, one month, or the like;
The completion proportion refers to the sum of the corresponding advertisement playing benefit scores R of each time of playing the advertisement to be played in the current period and/or the sum of the advertisement playing benefit scores R required to be completed in the current period;
Before a new advertisement to be played is played, calculating the completion proportion cj of each advertisement to be played, and then calculating the standard deviation S1 of m cj values;
calculating a standard deviation S2 corresponding to the advertisements to be played after the proportion cj is updated after the advertisements to be played are played;
Calculating m corresponding |S1-S2| values (playing different advertisements to be played corresponds to different updated values), selecting the advertisement to be played corresponding to the S2 value with the smallest corresponding |S1-S2| value, and taking the advertisement to be played as the advertisement played next by the display unit.
The application confirms the next advertisement to be played through the completion proportion of each advertisement and the advertisement playing benefit score updated in real time, thereby ensuring that the progress of the completion proportion of each advertisement to be played is similar, ensuring that the advertisement to be played with larger sum of the advertisement playing benefit scores R to be completed can be played under the condition of larger corresponding single advertisement playing benefit score R as much as possible, and improving the utilization efficiency of the stream resources on the premise of ensuring the playing requirements of all advertisements.
Example III
On the basis of the second embodiment, the present embodiment further provides a method for adjusting the number of advertisements to be played in each display unit, which specifically includes the following steps:
According to the method in the second embodiment, when one display unit completes the playing of the advertisement to be played in one period;
Firstly, confirming whether time remains in the period, and if so, adding the number of advertisements to be played in the display unit;
If not, the following steps:
for one advertisement, acquiring the order g of the corresponding advertisement playing benefits R when the advertisement is used as the advertisement to be played every time;
acquiring an average value G of an order G corresponding to each play of the advertisement in the whole period;
Acquiring an average value Gp of G values of all advertisements to be played after one display unit finishes playing the advertisements to be played in one period;
when the average value Gp is greater than the preset value Gy, it indicates that the utilization efficiency of the corresponding display unit is low, and the number of advertisements to be played can also be added in the display unit.
Otherwise, if the average value Gp is greater than the preset value Gy, it indicates that the utilization efficiency of the corresponding display unit is higher, and the number of advertisements to be played in the display unit is not adjusted.
The mode can further improve the benefits brought by the advertisement playing of the display unit and improve the advertising return rate.
Example IV
The invention also discloses a system for executing the personalized advertisement content accurate delivery method based on the user portrait, which comprises the following steps:
the image acquisition unit is used for acquiring scene images in the elevator and transmitting the acquired scene image information to the image analysis unit;
The image analysis unit is used for analyzing the scene image and identifying the number, sex and age information of the people in the scene image;
the main control unit is used for determining the next played advertisement according to the crowd figure data in the elevator analyzed by the image analysis unit;
and the display unit is used for playing the advertisement.
The foregoing is merely illustrative and explanatory of the invention, as various modifications and additions may be made to the particular embodiments described, or in a similar manner, by those skilled in the art, without departing from the scope of the invention or exceeding the scope of the invention as defined in the claims.
Claims (7)
1. The personalized advertisement content accurate delivery method based on the user portrait is characterized by comprising the following steps:
First, confirming audience group types and corresponding image data of each advertisement;
acquiring the duty ratio ai of the audience group types corresponding to each advertisement;
i takes the value of 1 to n, n represents the audience group category number;
Secondly, at the moment t1 before the next advertisement is played, acquiring image information in the elevator through an image acquisition unit in the elevator, wherein t1 is a preset value;
Analyzing and obtaining the gender and age of each person in the elevator;
dividing the personnel in the elevator into a plurality of person groups according to the gender and age of each personnel in the elevator, wherein each person group corresponds to one audience group type;
Acquiring each advertisement playable by the display unit and recording the advertisement as an advertisement to be played;
acquiring an advertisement playing benefit score R corresponding to the character composition in the current elevator when each advertisement to be played is supposed to be played;
Thirdly, adopting the advertisement to be played with the corresponding advertisement playing benefit score Rmax as the finally determined advertisement to be played next time;
after the third step, the method also comprises an advertisement playing scheme optimizing strategy, which comprises the following steps:
Acquiring advertisement playing benefit scores R of advertisements played by each display unit in a past preset time range;
For a display unit, ordering all advertisements played by the display unit according to the sequence from the higher to the lower of the sum of corresponding advertisement playing benefit scores R, and representing the advertisement as ek;
wherein k represents the corresponding order of each advertisement, ek represents the sum of specific advertisement playing benefit scores R;
Sequencing according to the sequence of the advertisement importance from big to small, and then determining display units for each advertisement according to the sequence to form a plurality of schemes;
For one scheme, after all advertisements are determined by the display units, calculating the sequence of each advertisement in a plurality of corresponding display units, and further calculating the sum H of the sequences corresponding to each advertisement;
The sum H1 of the sum H of all advertisement corresponding sequences is calculated;
And sequentially calculating H1 values corresponding to the schemes, determining a set of scheme with the minimum H1 as a finally determined advertisement playing scheme, and playing the advertisement according to the advertisement playing scheme in the next period.
2. The method for precisely delivering personalized advertisement contents based on user portraits according to claim 1, wherein when the audience group category number is determined, the duty ratio of each audience group is ordered from big to small, then the duty ratios are added in order from big to small until the comprehensive duty ratio exceeds a preset proportionality coefficient, the audience group participating in summation calculation is taken as the audience group category of the finally determined advertisement, and the duty ratio normalization processing is carried out.
3. The method for precisely delivering personalized advertisement content based on user portrait according to claim 1, wherein the method for calculating the advertisement playing benefit score R is as follows;
Where ai represents the corresponding duty ratio of each person group, bi represents the number of people in each person group in the elevator.
4. The method for precisely delivering personalized advertisement content based on user portrait according to claim 1, wherein when the number of advertisements to be played changes:
If the number is reduced on the basis of the prior art, deleting the playing of the advertisement which is correspondingly reduced in the advertisement playing scheme;
When the number is increased, the increased advertisements are subjected to trial playing in each display unit, and then an advertisement playing scheme optimizing strategy is executed according to the playing result.
5. The method for precisely delivering personalized advertisement content based on user portrait according to claim 1, wherein when the number of advertisements to be played and the playing amount requirement of each advertisement are determined, the playing order of each advertisement is further allocated, and the specific steps are as follows:
sequentially calculating to obtain advertisement playing benefit scores R of the advertisements to be played;
acquiring the completion proportion cj of each advertisement to be played in the current period, wherein j is 1 to m, and m represents the number of advertisements to be played;
The completion proportion refers to the sum of the corresponding advertisement playing benefit scores R of each time of playing the advertisement to be played in the current period and/or the sum of the advertisement playing benefit scores R required to be completed in the current period;
Before a new advertisement to be played is played, calculating the completion proportion cj of each advertisement to be played, and then calculating the standard deviation S1 of m cj values;
calculating a standard deviation S2 corresponding to the advertisements to be played after the proportion cj is updated after the advertisements to be played are played;
And calculating m corresponding |S1-S2| values, selecting an advertisement to be played corresponding to an S2 value with the minimum corresponding |S1-S2| value, and taking the advertisement to be played as an advertisement to be played next by the display unit.
6. The method for precisely delivering personalized advertisement content based on user portrait according to claim 5, further comprising a method for adjusting the number of advertisements to be played of each display unit, specifically comprising the following steps:
When one display unit finishes playing of the advertisement to be played in one period;
Firstly, confirming whether time remains in the period, and if so, adding the number of advertisements to be played in the display unit;
if not, for one advertisement, acquiring the corresponding advertisement playing benefit R of the advertisement when the advertisement is used as the advertisement to be played every time according to the order g when the advertisement playing benefits R are ordered according to the size;
acquiring an average value G of an order G corresponding to each play of the advertisement in the whole period;
Acquiring an average value Gp of G values of all advertisements to be played after one display unit finishes playing the advertisements to be played in one period;
And when the average value Gp is larger than a preset value Gy, adding the number of advertisements to be played in the display unit.
7. A personalized advertising content accurate delivery system based on user portraits, characterized in that the system is adapted to perform the delivery method of any one of claims 1 to 6, the system comprising:
the image acquisition unit is used for acquiring scene images in the elevator and transmitting the acquired scene image information to the image analysis unit;
The image analysis unit is used for analyzing the scene image and identifying the number, sex and age information of the people in the scene image;
the main control unit is used for determining the next played advertisement according to the crowd figure data in the elevator analyzed by the image analysis unit;
and the display unit is used for playing the advertisement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510700618.7A CN120563178B (en) | 2025-05-28 | 2025-05-28 | Personalized advertisement content accurate delivery method and system based on user portrait |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510700618.7A CN120563178B (en) | 2025-05-28 | 2025-05-28 | Personalized advertisement content accurate delivery method and system based on user portrait |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120563178A CN120563178A (en) | 2025-08-29 |
| CN120563178B true CN120563178B (en) | 2026-01-16 |
Family
ID=96819199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510700618.7A Active CN120563178B (en) | 2025-05-28 | 2025-05-28 | Personalized advertisement content accurate delivery method and system based on user portrait |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120563178B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116188083A (en) * | 2023-03-10 | 2023-05-30 | 安徽凌申科技有限公司 | Advertisement putting management system for elevator operation |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2502195A2 (en) * | 2009-11-20 | 2012-09-26 | Tadashi Yonezaki | Methods and apparatus for optimizing advertisement allocation |
| CN106408348A (en) * | 2016-09-30 | 2017-02-15 | 北京奇虎科技有限公司 | Method and device for displaying ads in carousel advertising space |
| WO2021016964A1 (en) * | 2019-07-31 | 2021-02-04 | 中新智擎科技有限公司 | Elevator advertisement delivery method and device, and advertisement delivery apparatus |
| CN110766451B (en) * | 2019-09-29 | 2022-07-19 | 浙江新再灵科技股份有限公司 | Elevator advertisement putting method and system based on human body static label |
| CN111062752A (en) * | 2019-12-13 | 2020-04-24 | 浙江新再灵科技股份有限公司 | Elevator scene advertisement putting method and system based on audience group |
| CN112465557A (en) * | 2020-12-07 | 2021-03-09 | 深圳市易售科技有限公司 | Advertisement sending method, device, system and storage medium |
| CN116433297A (en) * | 2023-04-18 | 2023-07-14 | 深圳市一朴设计建设有限公司 | Control system for digital media display |
| CN119693068A (en) * | 2025-02-26 | 2025-03-25 | 厦门市一码当先信息科技有限公司 | A method and system for accurately analyzing advertising audiences |
-
2025
- 2025-05-28 CN CN202510700618.7A patent/CN120563178B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116188083A (en) * | 2023-03-10 | 2023-05-30 | 安徽凌申科技有限公司 | Advertisement putting management system for elevator operation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120563178A (en) | 2025-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102880688B (en) | A kind of method for webpage is estimated, device and equipment | |
| CN107526810B (en) | Method and device for establishing click rate estimation model and display method and device | |
| JP2014533405A (en) | Multidimensional advertising bidding | |
| CN110415023B (en) | Elevator advertisement recommendation method, device, equipment and storage medium | |
| CN111899049B (en) | Advertisement putting method, device and equipment | |
| US20140030681A1 (en) | Activity-oriented Studying Method in an Online-to-offline Manner | |
| US20110251889A1 (en) | Inventory clustering | |
| CN110188120B (en) | Personalized screen recommendation method based on collaborative filtering | |
| CN115730858B (en) | Cultural product design intelligent management platform based on big data | |
| CN111259245B (en) | Work pushing method, device and storage medium | |
| CN116383480A (en) | Method, device, electronic device and storage medium for media recommendation in call scene | |
| CN114791877A (en) | Recommendation algorithm testing method and advertisement recommendation system | |
| CN113837811B (en) | Elevator advertisement point position recommending method and device, computer equipment and storage medium | |
| CN120563178B (en) | Personalized advertisement content accurate delivery method and system based on user portrait | |
| CN112232846B (en) | Method, device, medium and equipment for determining characteristic value based on multimedia file | |
| CN117057838A (en) | A customer big data screening and classification statistical system based on B2C platform | |
| CN113159809A (en) | Object processing method and device, electronic equipment and computer readable storage medium | |
| CN118014660B (en) | Advertisement high-value user identification method based on big data | |
| CN120410630A (en) | Traffic flow precision delivery strategy and business suggestion analysis system | |
| CN111932315B (en) | Method and device for data display, electronic equipment and computer readable storage medium | |
| CN117541329A (en) | OTT advertisement putting method and system based on crowd label | |
| CN113450127B (en) | Information display method, information display device, computer equipment and storage medium | |
| CN116308545B (en) | Advertisement online dynamic pushing method combining user behaviors | |
| CN114565408B (en) | Bidding prediction method and system for advertisement putting | |
| CN116562940A (en) | Interactive advertisement system based on intelligent building |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |