Method, system and device for feedback of campus multimedia advertising effect

Abstract

The present invention discloses a method, system and device for feedback on the effect of campus multimedia advertising delivery, the method comprising the following steps: obtaining and counting the data of personnel passing through the campus multimedia advertising delivery equipment; obtaining the facial image of the person to be analyzed in response to a request for triggering a facial image capture action; establishing a facial image database and determining the number of times the person has watched the advertisement played by the campus multimedia advertising delivery equipment; analyzing the facial images in the facial image database based on a preset facial algorithm to obtain basic information and viewing records of the personnel corresponding to the facial images; and then obtaining the effective viewing situation and the quality index of the advertisement playback; analyzing the playback effect of the multimedia advertisement in each time period to obtain the analysis result. The present invention can analyze the number of effective viewing personnel and calculate the playback content quality index; through the analysis of the multimedia announcement delivery effect, the multimedia delivery plan can be accurately improved to improve the delivery efficiency of the multimedia announcement.

Description

Technical Field

[0001] The present invention relates to the technical field of advertisement delivery, and in particular to a method, system and device for feedback of campus multimedia advertisement delivery effect. Background Art

[0002] Multimedia announcement broadcasting is one of the important ways to spread information on campus, as one of the ways to advertise. At present, the channels for campus multimedia delivery are relatively simple, and the delivery locations are basically located downstairs of buildings and public display screens, which can display the announcement content in a carousel. The existing solutions are basically: edit the multimedia announcement in the background, then put it on the big screen, and end the multimedia announcement delivery when the time comes.

[0003] Existing solutions have many shortcomings: on the one hand, it is impossible to count and analyze the actual effective viewing of multimedia announcements, and it is impossible to know whether the multimedia announcements have been conveyed to the personnel; on the other hand, there is no intuitive understanding of the quality of the broadcast content, and there is a lack of a quantitative content quality index evaluation system. Summary of the invention

[0004] The present invention aims at the shortcomings of the prior art and provides a method, system and device for providing feedback on the effect of multimedia advertising on campus.

[0005] In order to solve the above technical problems, the present invention is solved by the following technical solutions:

[0006] A campus multimedia advertising delivery effect feedback method comprises the following steps:

[0007] Obtain and count the data of people passing through campus multimedia advertising equipment;

[0008] In response to a request to trigger a facial image capture action, obtaining a facial image of a person to be analyzed;

[0009] Establish a facial image database and determine the number of times a person has viewed advertisements played by campus multimedia advertising devices;

[0010] Analyze the face images in the face image database based on a preset face algorithm to obtain basic information and viewing records of the person corresponding to the face image, wherein the basic information includes at least gender and age group;

[0011] Analyze the number of ad viewings, basic information and viewing records to obtain effective viewing and ad quality index;

[0012] The playing effect of the multimedia advertisements in each time period is analyzed based on the quality index of the advertisement playing to obtain an analysis result.

[0013] As an implementable method, the personnel data passing through the campus multimedia advertising delivery equipment is obtained in real time, and statistics are made according to time periods to obtain the total number of people in each time period, wherein the personnel data includes valid viewing personnel data, invalid viewing personnel data and no viewing personnel data.

[0014] As an implementable method, the establishment of a face image database and the determination of the number of times a person has watched an advertisement played by a campus multimedia advertising delivery device include the following steps:

[0015] Compare the acquired face image with the original face database to determine whether the face image exists in the original face database;

[0016] If it exists, the number of times the person corresponding to the face image has watched the advertisement is increased by 1. If not, the face image is stored in the original face database to update the original face database, and the number of times the person corresponding to the face image has watched the advertisement is increased by 1.

[0017] As an implementable method, the viewing record is obtained by the following steps:

[0018] Based on the important positions in the face image, confirm whether the viewing behavior occurs;

[0019] If so, determining the effective viewing duration and viewing coefficient of the advertisement based on the viewing behavior;

[0020] The viewing behavior is determined as follows: based on the face image in the face database, the positions of the eyes and the mouth in the face image are confirmed, and the center position of the mouth and the center position of the two eyes are regarded as a triangle in a two-dimensional plane. Then, the change value of the angle between the mouth and the two eyes changes with the viewing behavior, and the calculation formula of the change value is:

[0021]

[0022] Among them, Y is the change value of the angle between the mouth and the two eyes, A is the angle between the center of the mouth and the centers of the two eyes, L1 is the distance from the center of the mouth to the center of the left eye, and L2 is the distance from the center of the mouth to the center of the right eye;

[0023] A change threshold for viewing behavior is preset. If the change value is within the range of the change threshold, viewing behavior occurs.

[0024] The effective duration of viewing an advertisement is determined by obtaining the start time and the completion time of the viewing behavior, and the effective duration of the viewing behavior is the difference between the completion time and the start time;

[0025] The viewing coefficient is determined by the ratio of the effective viewing time of the advertisement to the total duration of the advertisement.

[0026] As an implementable method, when determining the effective duration of viewing an advertisement, if the same person has multiple effective durations of viewing the advertisement, the effective durations of viewing the advertisement by the same person are summed up to obtain the total effective duration of viewing the advertisement by the same person.

[0027] As an implementable method, the effective viewing situation and the quality index of the advertisement playback are obtained by analyzing the personnel data, viewing records and basic information, specifically:

[0028] Obtain personnel data and personnel viewing coefficients, obtain age viewing coefficients of different age groups and gender viewing coefficients of different genders;

[0029] The coefficient of each statistical dimension is calculated to obtain the quality index of the playback content. The quality index formula is as follows:

[0030]

[0031] Among them, V represents the quality index, Lx represents the viewing data of the people, Ni represents the number of times the people have viewed, Si represents the age viewing coefficient, Di represents the gender viewing coefficient, and i represents the time period.

[0032] As an implementable method, analyzing the playing effect of multimedia advertisements in each time period based on the quality index of advertisement playing includes the following steps:

[0033] Obtaining quality indexes of multimedia advertisements in different time periods;

[0034] Compare and analyze the playback effects of the same placement in different time periods based on the quality index;

[0035] Quality Index V i for:

[0036]

[0037] Among them, Vi represents the quality index of different time periods, Lx represents the viewing personnel data, Ni represents the number of times a person has viewed, Si represents the age viewing coefficient, and Di represents the gender viewing coefficient.

[0038] A campus multimedia advertising delivery effect feedback system, comprising a data acquisition module, a response acquisition module, an establishment and determination module, a data analysis module, an analysis and calculation module and an analysis and confirmation module;

[0039] The data acquisition module is used to acquire and count the data of people passing through the campus multimedia advertising delivery equipment;

[0040] The response acquisition module is used to acquire the facial image of the person to be analyzed in response to the request for triggering the facial image capture action;

[0041] The establishment and determination module is used to establish a facial image database and determine the number of times a person has watched an advertisement played by a campus multimedia advertising delivery device;

[0042] The data analysis module analyzes the face images in the face image database based on a preset face algorithm to obtain basic information and viewing records of the person corresponding to the face image, wherein the basic information includes at least gender and age group;

[0043] The analysis and calculation module is used to analyze the number of times the advertisement is viewed, basic information and viewing records to obtain the effective viewing situation and the quality index of the advertisement playback;

[0044] The analysis and confirmation module analyzes the playing effect of the multimedia advertisements in each time period based on the quality index of the advertisement playing to obtain an analysis result.

[0045] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following method steps are implemented:

[0046] Obtain and count the data of people passing through campus multimedia advertising equipment;

[0047] In response to a request to trigger a facial image capture action, obtaining a facial image of a person to be analyzed;

[0048] Establish a facial image database and determine the number of times a person has viewed advertisements played by campus multimedia advertising devices;

[0049] Analyze the face images in the face image database based on a preset face algorithm to obtain basic information and viewing records of the person corresponding to the face image, wherein the basic information includes at least gender and age group;

[0050] Analyze the number of ad viewings, basic information and viewing records to obtain effective viewing and ad quality index;

[0051] The playing effect of the multimedia advertisements in each time period is analyzed based on the quality index of the advertisement playing to obtain an analysis result.

[0052] A campus multimedia advertising delivery effect feedback device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following method steps are implemented:

[0053] Obtain and count the data of people passing through campus multimedia advertising equipment;

[0054] In response to a request to trigger a facial image capture action, obtaining a facial image of a person to be analyzed;

[0055] Establish a facial image database and determine the number of times a person has viewed advertisements played by campus multimedia advertising devices;

[0056] Analyze the face images in the face image database based on a preset face algorithm to obtain basic information and viewing records of the person corresponding to the face image, wherein the basic information includes at least gender and age group;

[0057] Analyze the number of ad viewings, basic information and viewing records to obtain effective viewing and ad quality index;

[0058] The playing effect of the multimedia advertisements in each time period is analyzed based on the quality index of the advertisement playing to obtain an analysis result.

[0059] The present invention has significant technical effects due to the adoption of the above technical solution:

[0060] The present invention can analyze the number of effective viewers and obtain the analysis results of the multimedia announcement delivery effect; it can also analyze the gender and age group of the personnel; calculate the playback content quality index through statistical data dimensions; through the analysis of the multimedia announcement delivery effect, accurately improve the multimedia delivery plan and improve the delivery efficiency of multimedia announcements. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0062] Figure 1 It is a schematic diagram of the overall process of the method of the present invention;

[0063] Figure 2 It is a schematic diagram of a flow chart of an embodiment of the method of the present invention;

[0064] Figure 3 is a schematic diagram of another embodiment of the method of the present invention;

[0065] Figure 4 It is a schematic diagram of the overall structure of the system of the present invention;

[0066] Figure 5 It is a schematic diagram of the positioning of the five sense organs captured by a person when viewing the announcement in the present invention;

[0067] Figure 6 It is a schematic diagram of the change curve of the Y value when people watch the announcement of the present invention. DETAILED DESCRIPTION

[0068] The present invention is further described in detail below in conjunction with embodiments. The following embodiments are for explanation of the present invention but the present invention is not limited to the following embodiments.

[0069] In the prior art, multimedia advertising playback equipment has been widely used. Multimedia announcement delivery can play announcement content in various formats such as rich text, video, and pictures, and also supports the playback of announcement content in various formats in turn. Multimedia equipment can be used in a variety of occasions, such as elevator entrances, campuses, etc. The present invention focuses on analyzing and providing feedback on the effects of campus multimedia advertising delivery. At present, the playback of announcement content in various formats meets the school's needs for the playback of multimedia announcements, and the playback time can be set, without the need to manually start and end the playback of multimedia announcements. However, there is relatively little feedback on the effects of campus multimedia advertising delivery, so the playback effect of multimedia advertisements cannot be obtained. The present invention finally analyzes the playback effect of multimedia advertisements by acquiring the personnel data of campus multimedia advertising delivery equipment. For specific methods, please refer to the following embodiments.

[0070] Embodiment 1:

[0071] A method for feedback on the effect of campus multimedia advertising, such as Figure 1 As shown, the following steps are included:

[0072] S100, obtaining and counting data of people passing through campus multimedia advertising delivery equipment;

[0073] S200, in response to a request for triggering a facial image capture action, obtaining a facial image of a person to be analyzed;

[0074] S300, establishing a facial image database and determining the number of times a person has watched an advertisement played by a campus multimedia advertising device;

[0075] S400, analyzing the face images in the face image database based on a preset face algorithm to obtain basic information and viewing records of the person corresponding to the face image, wherein the basic information includes at least gender and age group;

[0076] S500, analyzing the number of times the advertisement is viewed, basic information and viewing records to obtain effective viewing conditions and a quality index of the advertisement playback;

[0077] S600: Analyze the playing effect of the multimedia advertisement in each time period based on the advertisement playing quality index to obtain an analysis result.

[0078] The present invention can analyze the number of effective viewers and obtain the analysis results of the multimedia announcement delivery effect; it can also analyze the gender and age group of the personnel; calculate the playback content quality index through statistical data dimensions; through the analysis of the multimedia announcement delivery effect, accurately improve the multimedia delivery plan and improve the delivery efficiency of multimedia announcements.

[0079] In one embodiment, in step S100, obtaining and counting the data of people passing through the campus multimedia advertising delivery device can be: obtaining the data of people passing through the campus multimedia advertising delivery device in real time, and counting according to time periods to obtain the total number of people in each time period, wherein the personnel data includes valid viewing personnel data, invalid viewing personnel data, and no viewing personnel data. The acquisition of personnel data can be obtained by the built-in camera of the campus multimedia advertising delivery device, or by the external camera of the campus multimedia advertising delivery device, which will not be elaborated here. The total number of people must be data greater than 0, so that the results of the analysis are meaningful.

[0080] In step S300, the process of establishing a facial image database and determining the number of times a person has watched an advertisement played by a campus multimedia advertising device comprises the following steps:

[0081] S310, comparing the acquired face image with the original face database to determine whether the face image exists in the original face database;

[0082] S320. If it exists, the number of times the person corresponding to the face image has watched the advertisement is increased by 1. If not, the face image is stored in the original face database to update the original face database, and the number of times the person corresponding to the face image has watched the advertisement is increased by 1.

[0083] The construction of a face database is a long-term accumulation process. The construction process of a face database from 0 to 1 can directly reflect the effect of the playback content. The larger the face database, the better the playback effect.

[0084] Define N as the number of visits by a person, and the number of visits by each person N i =N1, N2, N3...

[0085] Get the face image transmitted by the camera; compare the image with the face database to determine whether the person is already in the face database; the number of views of the person is increased by 1, that is, N i =N i-1 +1; add the person to the face database, that is, P i =P i-1 +1, then continue to step S240, the number of views of the person is increased by 1, that is, N i=1; The construction of the face database is conducive to deduplication of viewers and obtaining the accurate number of viewers, and the number of views can also be used as an important basis for judgment.

[0086] In addition, in one embodiment, in step S400, the viewing record is obtained by the following steps:

[0087] S410, confirming whether viewing behavior occurs based on important positions in the face image;

[0088] S420: If yes, determine the effective duration and viewing coefficient of the advertisement based on the viewing behavior;

[0089] The viewing behavior is determined as follows: based on the face image in the face database, the positions of the eyes and the mouth in the face image are confirmed, and the center position of the mouth and the center position of the two eyes are regarded as a triangle in a two-dimensional plane. Then, the change value of the angle between the mouth and the two eyes changes with the viewing behavior, and the calculation formula of the change value is:

[0090]

[0091] Among them, Y is the change value of the angle between the mouth and the two eyes, A is the angle between the center of the mouth and the centers of the two eyes, L1 is the distance from the center of the mouth to the center of the left eye, and L2 is the distance from the center of the mouth to the center of the right eye;

[0092] A change threshold for viewing behavior is preset. If the change value is within the range of the change threshold, viewing behavior occurs.

[0093] The effective duration of viewing an advertisement is determined by obtaining the start time and the completion time of the viewing behavior, and the effective duration of the viewing behavior is the difference between the completion time and the start time;

[0094] The viewing coefficient is determined by the ratio of the effective viewing time of the advertisement to the total duration of the advertisement.

[0095] In this embodiment, the gaze duration of a person can be calculated by capturing important positions on the face, such as the positions of the eyes and lips. Figure 5 and attached Figure 6 As shown, A is defined as the anchor point of the lips in the face, B is defined as the anchor point of the left eye in the face, and C is defined as the anchor point of the right eye in the face. Therefore, the three points can be thought of as a triangle in a two-dimensional plane, and the length of each side of the triangle can be obtained. When a person passes by looking up or looking straight at the announcement, or lowering his head and not looking at the announcement, the triangle angle A of his face will change accordingly. Define Y as the value that changes with the change of angle A, and the formula can be obtained: and

[0096] The Y value will be inconsistent when a person is watching or not watching the announcement. Therefore, it can be defined according to the height of the device that when the Y value is in the range (Y1, Y2), it is considered that a viewing behavior has occurred. The critical height for the viewing behavior is the action that triggers the capture of the facial image.

[0097] Define T as the time when a person appears, and T at different time nodes i =T1, T2, T3, etc. Therefore, when a person passes by and looks up to leave, it is defined that when Y=Y1, T=T1, and when Y=Y2, T=T2, and the range value of T can be obtained (T1, T2). If the person is watching the announcement and the face is not captured, T1=0, T2=0 is defined.

[0098] Define L as the person's gaze time, and the gaze time of each person L i It can be obtained by the formula: L i =T1-T1

[0099] Define L0 as the time required for effective viewing of the announcement; define L x is the personnel viewing coefficient, and the corresponding value can be obtained through the formula: In one embodiment, there may be a situation where a person may not watch an advertisement continuously. For example, he may watch for a few minutes, then shift his gaze, and then continue watching when he hears the advertisement words or sounds that interest him. In this case, if the effective duration of viewing the advertisement is to be determined, it is necessary to calculate the total effective duration of viewing the advertisement. The total effective duration is the sum of the effective duration of viewing the advertisement in each time period, and finally the total effective duration of viewing the advertisement is obtained.

[0100] In one embodiment, the analysis of personnel data, viewing records and basic information to obtain effective viewing conditions and an advertisement playback quality index is specifically as follows:

[0101] Obtain personnel data and personnel viewing coefficients, obtain age viewing coefficients of different age groups and gender viewing coefficients of different genders;

[0102] The coefficient of each statistical dimension is calculated to obtain the quality index of the playback content. The quality index formula is as follows:

[0103]

[0104] Among them, V represents the quality index, Lx represents the viewing data of the people, Ni represents the number of times the people have viewed, Si represents the age viewing coefficient, Di represents the gender viewing coefficient, and i represents the time period.

[0105] In this embodiment, S is defined as the viewing coefficient of different age groups, and the viewing coefficient S of different age groups is i= S1, S2, S3..., the age group should be affected by external factors and equipment function limitations, and can be roughly divided into teenagers, young people, middle-aged people and the elderly. Define D as the viewing coefficient of different genders, and the viewing coefficient of different genders D i =D1, D2; the coefficient of each statistical dimension is calculated, and finally the quality index of the playback content can be calculated through the formula.

[0106] In addition, based on the above embodiments, the playing effect of multimedia advertisements in each time period can be analyzed based on the quality index of advertisement playing, including the following steps:

[0107] Obtaining quality indexes of multimedia advertisements in different time periods;

[0108] Compare and analyze the playback effects of the same placement in different time periods based on the quality index;

[0109] Quality Index V i for:

[0110]

[0111] Among them, Vi represents the quality index of different time periods, Lx represents the viewing personnel data, Ni represents the number of times a person has viewed, Si represents the age viewing coefficient, and Di represents the gender viewing coefficient;

[0112] When analyzing the playback effects of different placements in the same time period, the key data to analyze is the number of people who effectively watched. Based on this quality index Vi, the changes in the number of people who effectively watched in different time periods and different placements can be intuitively obtained.

[0113] Embodiment 2:

[0114] A campus multimedia advertising effect feedback system, such as Figure 4 As shown, it includes a data acquisition module 100, a response acquisition module 200, an establishment determination module 300, a data analysis module 400, an analysis calculation module 500 and an analysis confirmation module 600;

[0115] The data acquisition module 100 is used to acquire and count the data of people passing through the campus multimedia advertising delivery equipment;

[0116] The response acquisition module 200 is used to acquire the facial image of the person to be analyzed in response to the request for triggering the facial image capture action;

[0117] The establishment and determination module 300 is used to establish a facial image database and determine the number of times a person has watched an advertisement played by a campus multimedia advertisement delivery device;

[0118] The data analysis module 400 analyzes the face images in the face image database based on a preset face algorithm to obtain basic information and viewing records of the person corresponding to the face image, wherein the basic information includes at least gender and age group;

[0119] The analysis and calculation module 500 is used to analyze the number of times the advertisement is viewed, basic information and viewing records to obtain the effective viewing situation and the quality index of the advertisement playback;

[0120] The analysis and confirmation module 600 analyzes the playing effect of the multimedia advertisement in each time period based on the advertisement playing quality index to obtain an analysis result.

[0121] Embodiment 3:

[0122] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following method steps are implemented:

[0123] S100, obtaining and counting data of people passing through campus multimedia advertising delivery equipment;

[0124] S200, in response to a request for triggering a facial image capture action, obtaining a facial image of a person to be analyzed;

[0125] S300, establishing a facial image database and determining the number of times a person has watched an advertisement played by a campus multimedia advertising device;

[0126] S400, analyzing the face images in the face image database based on a preset face algorithm to obtain basic information and viewing records of the person corresponding to the face image, wherein the basic information includes at least gender and age group;

[0127] S500, analyzing the number of times the advertisement is viewed, basic information and viewing records to obtain effective viewing conditions and a quality index of the advertisement playback;

[0128] S600: Analyze the playing effect of the multimedia advertisement in each time period based on the advertisement playing quality index to obtain an analysis result.

[0129] Embodiment 4:

[0130] In one embodiment, a campus multimedia advertising delivery effect feedback device is provided, which can be a server or a mobile terminal. The campus multimedia advertising delivery effect feedback device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the campus multimedia advertising delivery effect feedback device is used to provide computing and control capabilities. The memory of the campus multimedia advertising delivery effect feedback device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database stores all data of the campus multimedia advertising delivery effect feedback device. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for implementing campus multimedia advertising delivery effect feedback is implemented.

[0131] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0132] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0133] The present invention is described with reference to the flowcharts and / or block diagrams of the method, terminal device (system), and computer program product according to the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0134] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0136] It should be noted that:

[0137] The "one embodiment" or "embodiment" mentioned in the specification means that the specific features, structures or characteristics described in conjunction with the embodiment are included in at least one embodiment of the present invention. Therefore, the phrases "one embodiment" or "embodiment" appearing in various places throughout the specification do not necessarily refer to the same embodiment.

[0138] In addition, it should be noted that the shapes and names of the parts and components of the specific embodiments described in this specification may be different. Any equivalent or simple changes made based on the structure, features and principles described in the patent concept of the present invention are included in the protection scope of the patent of the present invention. The technicians in the technical field of the present invention can make various modifications or supplements to the specific embodiments described or replace them in a similar manner, as long as they do not deviate from the structure of the present invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A method for providing feedback on the effect of multimedia advertising on campus, characterized in that: The following steps are involved: Obtain and count the data of people passing through campus multimedia advertising equipment; In response to a request to trigger a facial image capture action, obtaining a facial image of a person to be analyzed; Establish a facial image database and determine the number of times a person has viewed advertisements played by campus multimedia advertising devices; Analyze the face images in the face image database based on a preset face algorithm to obtain basic information and viewing records of the person corresponding to the face image, wherein the basic information includes at least gender and age group; Analyze the number of ad viewings, basic information and viewing records to obtain effective viewing and ad quality index; Analyze the playing effect of multimedia advertisements in each time period based on the quality index of advertisement playing to obtain analysis results; The viewing record is obtained by following the steps below: Based on the important positions in the face image, confirm whether the viewing behavior occurs; If so, determining the effective viewing duration and viewing coefficient of the advertisement based on the viewing behavior; The viewing behavior is determined as follows: based on the face image in the face database, the positions of the eyes and the mouth in the face image are confirmed, and the center position of the mouth and the center position of the two eyes are regarded as a triangle in a two-dimensional plane. Then, the change value of the angle between the mouth and the two eyes changes with the viewing behavior, and the calculation formula of the change value is: Among them, Y is the change in the angle between the mouth and the two eyes, and A is the angle between the center of the mouth and the center of the two eyes. Indicates the distance from the center of the mouth to the center of the left eye. Indicates the distance from the center of the mouth to the center of the right eye; A change threshold for viewing behavior is preset. If the change value is within the range of the change threshold, viewing behavior occurs. The effective duration of viewing an advertisement is determined by obtaining the start time and the completion time of the viewing behavior, and the effective duration of the viewing behavior is the difference between the completion time and the start time; The viewing coefficient is determined by the ratio of the effective viewing time of the advertisement to the total duration of the advertisement. Among them, through the analysis of personnel data, viewing records and basic information, the effective viewing situation and the quality index of advertising playback are obtained, specifically: Obtain personnel data and personnel viewing coefficients, obtain age viewing coefficients of different age groups and gender viewing coefficients of different genders; The coefficient of each statistical dimension is calculated to obtain the quality index of the playback content. The quality index formula is as follows: Where V represents the quality index, Indicates the viewing personnel data. Indicates the number of views by people. Indicates the age viewing coefficient, represents the gender viewing coefficient, and i represents the time period.

2. The campus multimedia advertising delivery effect feedback method according to claim 1 is characterized in that: The personnel data passing through the campus multimedia advertising delivery equipment is obtained in real time, and statistics are made according to time periods to obtain the total number of people in each time period, wherein the personnel data includes valid viewing personnel data, invalid viewing personnel data and no viewing personnel data.

3. The campus multimedia advertising delivery effect feedback method according to claim 1 is characterized in that: The method of establishing a face image database and determining the number of times a person watches advertisements played by a campus multimedia advertising delivery device comprises the following steps: Compare the acquired face image with the original face database to determine whether the face image exists in the original face database; If it exists, the number of times the person corresponding to the face image has watched the advertisement is increased by 1. If not, the face image is stored in the original face database to update the original face database, and the number of times the person corresponding to the face image has watched the advertisement is increased by 1.

4. The campus multimedia advertising delivery effect feedback method according to claim 1 is characterized in that: When determining the effective duration of viewing an advertisement, if the same person has multiple effective durations of viewing the advertisement, the effective total duration of viewing the advertisement by the same person is summed up to obtain the total effective duration.

5. The campus multimedia advertising delivery effect feedback method according to claim 1 is characterized in that: The playing effect of multimedia advertisements in each time period is analyzed based on the quality index of advertisement playing, including the following steps: Obtaining quality indexes of multimedia advertisements in different time periods; Compare and analyze the playback effects of the same placement in different time periods based on the quality index; Quality Index V i for: in, Represents the quality index of different time periods, Indicates the viewing personnel data. Indicates the number of views by people. Indicates the age viewing coefficient, represents the gender viewing coefficient, and i represents the time period.

6. A campus multimedia advertising delivery effect feedback system implemented based on the method described in any one of claims 1 to 5, characterized in that: It includes a data acquisition module, a response acquisition module, an establishment and determination module, a data analysis module, an analysis and calculation module and an analysis and confirmation module; The data acquisition module is used to acquire and count the data of people passing through the campus multimedia advertising delivery equipment; The response acquisition module is used to acquire the facial image of the person to be analyzed in response to the request for triggering the facial image capture action; The establishment and determination module is used to establish a facial image database and determine the number of times a person has watched an advertisement played by a campus multimedia advertising delivery device; The data analysis module analyzes the face images in the face image database based on a preset face algorithm to obtain basic information and viewing records of the person corresponding to the face image, wherein the basic information includes at least gender and age group; The analysis and calculation module is used to analyze the number of times the advertisement is viewed, basic information and viewing records to obtain the effective viewing situation and the quality index of the advertisement playback; The analysis and confirmation module analyzes the playing effect of the multimedia advertisements in each time period based on the quality index of the advertisement playing to obtain the analysis result; The viewing record is obtained by following the steps below: Based on the important positions in the face image, confirm whether the viewing behavior occurs; If so, determining the effective viewing duration and viewing coefficient of the advertisement based on the viewing behavior; The viewing behavior is determined as follows: based on the face image in the face database, the positions of the eyes and the mouth in the face image are confirmed, and the center position of the mouth and the center position of the two eyes are regarded as a triangle in a two-dimensional plane. Then, the change value of the angle between the mouth and the two eyes changes with the viewing behavior, and the calculation formula of the change value is: Among them, Y is the change in the angle between the mouth and the two eyes, and A is the angle between the center of the mouth and the center of the two eyes. Indicates the distance from the center of the mouth to the center of the left eye. Indicates the distance from the center of the mouth to the center of the right eye; A change threshold for viewing behavior is preset. If the change value is within the range of the change threshold, viewing behavior occurs. The effective duration of viewing an advertisement is determined by obtaining the start time and the completion time of the viewing behavior, and the effective duration of the viewing behavior is the difference between the completion time and the start time; The viewing coefficient is determined by the ratio of the effective viewing time of the advertisement to the total duration of the advertisement. Among them, through the analysis of personnel data, viewing records and basic information, the effective viewing situation and the quality index of advertising playback are obtained, specifically: Obtain personnel data and personnel viewing coefficients, obtain age viewing coefficients of different age groups and gender viewing coefficients of different genders; The coefficient of each statistical dimension is calculated to obtain the quality index of the playback content. The quality index formula is as follows: Where V represents the quality index, Indicates the viewing personnel data. Indicates the number of views by people. Indicates the age viewing coefficient, represents the gender viewing coefficient, and i represents the time period.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

8. A campus multimedia advertising delivery effect feedback device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

Images