CN110689367A

CN110689367A - Data acquisition method and device, computer device and storage medium

Info

Publication number: CN110689367A
Application number: CN201910772280.0A
Authority: CN
Inventors: 周陈龙
Original assignee: OneConnect Smart Technology Co Ltd
Current assignee: OneConnect Smart Technology Co Ltd
Priority date: 2019-08-21
Filing date: 2019-08-21
Publication date: 2020-01-14
Also published as: WO2021031600A1

Abstract

A data collection method for advertisement push comprises the following steps: acquiring a target figure image of each target figure in front of the advertisement display platform; acquiring an identifier, a display area and advertisement information of a target advertisement display platform; analyzing the face image area and the behavior information of the target person, and judging the personalized preference of the target person to the advertisement information; searching whether an advertisement audience matched with the identity information of the target person exists in a preset database, and if so, adding the personalized preference of the target person to the advertisement information, the identifier of an advertisement display platform for displaying the advertisement information, a display area and the acquisition time of the target person image to the personal data of the target advertisement audience. The invention also provides a data acquisition device, a computer device and a storage medium, and the database is updated through face comparison so as to be convenient for subsequent targeted advertisement push.

Description

Data acquisition method and device, computer device and storage medium

Technical Field

The invention relates to the technical field of computers, in particular to a data acquisition method, a data acquisition device, a computer device and a computer readable storage medium for advertisement push.

Background

With the continuous promotion of social commercialization, the diversity of advertisement services is also continuously developed. For example, television advertisements, outdoor multimedia advertisements, network advertisements, newspaper and magazine advertisements, posters and the like, and the appearance of these advertisement media plays an important role in product popularization. Current advertising systems have in common: the advertising format is primarily a one-way infusion, and the viewer is passively receiving and has no idea of whether the product is of interest. On the other hand, the audience passively receives various kinds of advertisement information, and if the advertisement information contains a large amount of advertisement content which is not interested by the audience, the user experience is reduced.

Therefore, the method and the device are particularly important for collecting the personalized preferences of audiences on various kinds of advertisement information, so that the advertisements can be put in a targeted manner aiming at different audiences in the later period, and the user experience is improved.

Disclosure of Invention

In view of the foregoing, there is a need for a data collection method, device, computer device and computer readable storage medium capable of improving user experience, so as to solve the above problems.

A first aspect of the present application provides a data collection method for advertisement delivery, which is applied in a computer device, where the computer device can communicate with a plurality of advertisement display platforms, and the method includes:

acquiring a target character image of each target character in a specific area in front of at least one advertisement display platform;

for each target person image, the following steps are performed:

determining an advertisement display platform corresponding to the target character image as a target advertisement display platform, and acquiring a first identifier of the target advertisement display platform, a display area where the target character image is located and first advertisement information displayed by the target advertisement display platform at the acquisition time of the target character image;

analyzing the identity information of the target person according to the target person image, wherein the identity information comprises a face image area of the target person in the target person image;

analyzing the behavior information of the target person according to the face image area, and judging the personalized preference of the target person on the first advertisement information according to the behavior information;

searching whether an advertising audience matched with the identity information of the target person exists in a preset database, wherein personal data of a plurality of advertising audiences are stored in the preset database, and the personal data of each advertising audience comprises the identity information of the advertising audience, personalized preference of at least one piece of advertising information, a first identifier of an advertising display platform for displaying the at least one piece of advertising information, a display area where the advertising audience is located and the time when the advertising audience appears in the display area where the first advertising display platform is located; and

when the advertising audience matched with the identity information of the target person exists, determining the matched advertising audience as a target advertising audience, and adding the personalized preference of the target person on the first advertising information, the first identifier of the target advertising display platform, the display area and the acquisition time of the target person image into the personal data of the target advertising audience.

A second aspect of the present application provides a data acquisition device for advertisement delivery, wherein the device comprises:

the first acquisition module is used for acquiring a target character image of each target character in a specific area in front of at least one advertisement display platform;

the second acquisition module is used for determining that the advertisement display platform corresponding to the target character image is a target advertisement display platform, and acquiring a first identifier of the target advertisement display platform, a display area where the target character image is located and first advertisement information displayed by the target advertisement display platform at the acquisition time of the target character image;

the first analysis module is used for analyzing the identity information of the target person according to the target person image, wherein the identity information comprises a face image area of the target person in the target person image;

the second analysis module is used for analyzing the behavior information of the target person according to the face image area and judging the personalized preference of the target person on the advertisement information according to the behavior information;

the searching module is used for searching whether a target advertisement audience matched with the identity information of the target character exists in a preset database, wherein personal data of a plurality of advertisement audiences are stored in the preset database, and the personal data of each advertisement audience comprises the identity information of the advertisement audience, personalized preference of at least one piece of advertisement information, a first identifier of an advertisement display platform for displaying the at least one piece of advertisement information, a display area where the advertisement audience is located and the time when the advertisement audience appears in the display area where the first advertisement display platform is located; and

and the adding module is used for determining the matched advertising audience as the target advertising audience when the advertising audience matched with the identity information of the target person exists, and adding the personalized preference of the target person on the first advertising information, the first identifier of the target advertising display platform, the display area where the target person is located and the acquisition time of the target person image into the personal data of the target advertising audience.

A third aspect of the application provides a computer arrangement comprising a processor for implementing the data acquisition method for advertisement push as described above when executing a computer program stored in a memory.

A fourth aspect of the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the data collection method for advertisement push as described above.

When the information is collected, the collected information is high in richness and comprises a target character image, advertisement information, a first identifier of an advertisement display platform, a display area where the advertisement display platform is located, the collection time of the target character image and the like, so that the characteristics of multiple dimensions of identity information (including a face image area, gender, race, age and occupation), behavior information (including micro expression and attention duration) and the like of the target character can be determined, the personalized preference, the appearing position, the frequency, the pedestrian flow information, the advertisement putting effect and the like of the target character on the advertisement information are further determined, the advertisements can be put in a targeted mode aiming at different audiences in the later period, and the user experience is improved.

Drawings

Fig. 1 is a flowchart of a data collection method for advertisement push according to an embodiment of the present invention.

Fig. 2 is a schematic structural diagram of a data acquisition device for advertisement delivery according to a second embodiment of the present invention.

Fig. 3 is a schematic diagram of a computer device according to a third embodiment of the present invention.

Description of the main elements

Computer device 1

Memory 20

Processor 30

Computer program 40

Data acquisition device 10 for advertisement push

First acquisition module 101

Second acquisition Module 102

First analysis module 103

Second analysis Module 104

Search module 105

Add module 106

First summarization module 107

Second summarization module 108

The following detailed description will further illustrate the invention in conjunction with the above-described figures.

Detailed Description

In order that the above objects, features and advantages of the present invention can be more clearly understood, a detailed description of the present invention will be given below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.

In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention, and the described embodiments are merely a subset of the embodiments of the present invention, rather than a complete embodiment. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

Example one

Fig. 1 is a flowchart illustrating a data collection method for advertisement delivery according to a first embodiment of the present invention. The data acquisition method is applied to a computer device, and the computer device can be communicated with a plurality of advertisement display platforms. The order of the steps in the flow chart may be changed and some steps may be omitted according to different needs. The method comprises the following steps:

in step S11, a target person image of each target person entering a specific area in front of at least one advertisement display platform is obtained.

Wherein, all advertisement show platforms are respectively installed in different show areas. The computer device can be an advertisement management and control platform held by an advertiser, and can specifically survey all advertisement display platforms in a certain display area according to requirements, namely, only obtain target character images collected by each advertisement display platform in a certain display area (such as Shanghai subway No. 2 line Longyang road station). The advertisement display platform can be a television, an advertisement broadcasting display screen, an advertisement propaganda poster and the like. In this embodiment, each advertisement display platform is provided with at least one camera device, the shooting range of the camera device of each advertisement display platform at least includes the specific area located on the advertisement display platform, and the camera device is used for collecting the image of the target person within the shooting range. The camera may include a visible light camera, an infrared camera, a thermal imaging camera, or the like.

In this embodiment, the crowd entering the shooting range may include people passing by the advertisement display platform, people facing away from the advertisement display platform (e.g., may face away from the advertisement display platform when waiting for a bus), and viewers watching the advertisement display platform. The target person of this embodiment is limited to the audience who watches the advertisement display platform. Specifically, each camera device continuously acquires images of persons in a specific range in front of the corresponding advertisement display platform in real time or periodically. The computer device acquires all the character images at each advertisement display platform, detects whether each character image comprises a face image area by utilizing a deep convolutional neural network, and further judges whether the face image area continuously appears in the continuous character images and whether the continuous duration of the continuous character images is greater than or equal to a first preset duration if the face image area continuously appears in the continuous character images. If so, indicating that the corresponding figure in the figure image is the target figure for watching the advertisement display platform, and judging that the figure image is the target figure image by the computer device.

Step S12, determining that the advertisement display platform corresponding to the target person image is a target advertisement display platform, and acquiring a first identifier of the target advertisement display platform, a display area where the target person image is located, and first advertisement information displayed by the target advertisement display platform at the acquisition time of the target person image.

The target advertisement display platform refers to an advertisement display platform in a specific area where a target person enters. The first identifier may be an identification name or an identification code of the targeted advertisement presentation platform that is distinguished from other advertisement presentation platforms. In this embodiment, each of the target person images includes a second identifier of an image capture device used to capture the target image. The computer device stores a first corresponding relationship between unique identifiers of different advertisement display platforms and a second identifier of a camera device installed on the advertisement display platform. After the computer device obtains the target person image, a second identifier of the camera device for collecting the target image is determined, and the first identifier corresponding to the second identifier is determined according to the first corresponding relation. In another implementation, the computer device may also obtain the first identifier of the targeted advertisement presentation platform directly from the targeted advertisement presentation platform.

In this embodiment, the computer device further stores a second corresponding relationship between the first identifier of the different advertisement display platform and the display area where the advertisement display platform is located. And after the computer device acquires the first identifier of the target advertisement display platform, determining the display area corresponding to the first identifier according to the second corresponding relation.

In this embodiment, each of the target person images further includes the capture time, and the capture time of the target person image reflects the time when the target client appears on the target advertisement display platform (or the display area). The acquisition time may be identified in the target person image in the form of a timestamp. The computer device is preset with an original advertisement putting plan aiming at each advertisement display platform, and the original advertisement putting plan comprises advertisement information which is planned to be displayed by the target advertisement display platform at each advertisement time. The computer device can determine that the advertisement information displayed by the target advertisement display platform in the advertisement time same as the acquisition time is the first advertisement information according to the acquisition time of the target character image. Wherein the advertisement information includes a type of the advertisement object being presented (i.e., a type of goods or services) and a specific characteristic of the advertisement object. For example, for an automobile advertisement, the advertisement information may include an automobile and performance indicators for the automobile.

Step S13, analyzing the identity information of the target person according to the target person image, where the identity information includes a face image region of the target person in the target person image.

Wherein the face image region is capable of reflecting the unique identity of the target person. Further, the identity information may also include the gender, race, age, occupation, etc. of the target person.

In this embodiment, the computer device detects the face image region from the target person image by using a deep convolutional neural network, and performs a cropping process on the detected face image, thereby extracting the face image region. The convolutional neural network can learn the characteristics of the human face from the target person image, and then distinguish the human face image region from the non-human face image region by using a separator, so that the aim of human face detection is fulfilled. Further, the computer device calculates the facial image region by using a trained deep learning classifier model to identify the gender, race, age, occupation, and the like of the target person. Taking the identification of the gender of the target person as an example, the calculation process includes:

a) acquiring gender characteristic parameters of the face image area and establishing a parameter model;

the gender feature parameters comprise hair (including beard) feature parameters, face organ parameters, contour parameters, sex feature parameters and the like. Taking the example of needing to obtain the characteristic parameters of the beard, firstly positioning the face characteristic points, then carrying out skin color segmentation, positioning the face characteristic points by adopting an active shape model algorithm to further obtain a chin area, then separating out a non-skin color area of the chin by utilizing a skin color segmentation algorithm, and finally detecting the non-skin color area of the chin by using a beard color discrimination method to obtain the beard, thereby carrying out parameter extraction on the characteristics of the beard. The beard feature parameter may be obtained by assigning a feature value to the beard in the face image area according to a difference in color of the beard, for example, assigning an initial value according to a color or density of the beard, and thus obtaining the characteristic parameter of the beard according to a preset initial value. In this embodiment, the gender feature parameters may be obtained by performing feature extraction and classification on the face image region by using a Local binary pattern method (Local binary patterns), a neural network method, an SVM (Support Vector Machine) and other methods.

b) Calling a face gender classifier model;

c) and comparing the parameter model with the face gender classifier model so as to identify the gender corresponding to the face image area.

Step S14, analyzing the behavior information of the target person according to the face image area, and judging the personalized preference of the target person to the first advertisement information according to the behavior information.

Wherein the behavior information includes at least one of a micro-expression of the target person and a length of time of interest of the first advertisement information.

In this embodiment, the computer device identifies a feature region (e.g., an eye region, an eyebrow region, a mouth region) in each face image region, and analyzes the micro-expression of the user according to a change in the feature regions of at least two consecutive face image regions. For example, when the eye area becomes large, the micro expression is that the eyes are enlarged; when the mouth corners on the two sides deviate upwards, the micro expression is that the mouth corners on the two sides are raised; and when the mouth angle on one side deviates upwards, the micro expression is that the mouth angle on one side rises. Then, the computer device judges the personalized preference of the target person for the first advertisement information according to the micro expression. For example, when the micro expression is a bilateral mouth corner upturn, it may be determined that the target person prefers the first advertisement information (i.e., is more interested); and when the micro expression is a one-sided mouth corner up, it may be determined that the target person does not prefer the first advertisement information (i.e., is not interested). The scope of the invention is not limited to the partitioning of personalized preferences as set forth in the present embodiment.

In this embodiment, the computer device identifies an eye region in each face image region, and determines a time length of attention of the target person to the first advertisement information according to the eye region of each face image region. Wherein the attention duration of the target person to the first advertisement information needs to use a light spot formed by reflecting light from the eyes of the target person. In this case, a collecting lamp may be further disposed at a position of the advertisement display platform near the camera device, and the collecting lamp is used for emitting light so that the camera device can collect a face image area, and an eye area of the face image area is formed by light reflected by an eyeball of the target person and collected by the collecting lamp. When the attention duration is greater than or equal to a second preset duration, judging that the target person is interested in the first advertisement information; otherwise, when the attention duration is smaller than the second preset duration, it is determined that the target person is not interested in the first advertisement information.

Step S15, searching a preset database for whether there is an advertisee matching the identity information of the target person, if yes, performing step S16, otherwise, performing step S17. The preset database stores personal data of a plurality of advertisement audiences, and the personal data of each advertisement audience comprises identity information of the advertisement audience, personalized preference of at least one piece of advertisement information, a first identifier of an advertisement display platform for displaying the at least one piece of advertisement information, a display area where the advertisement audience is located and the time when the advertisement audience appears in the display area where the first advertisement display platform is located.

Step S16, determining the matched advertisee as a target advertisee, and adding the personalized preference of the target character for the first advertising information, the first identifier of the target advertising display platform, the display area and the acquisition time of the target character image into the personal data of the target advertisee.

And adding the first advertisement information and the personalized preference of the target person for the first advertisement information into personal data of the target advertisement audience, wherein the personalized preference of the target person for the first advertisement information actually reflects the interest points of the target person, and the interest points of the target advertisement audience can be updated by adding the first advertisement information and the personalized preference of the target person for the first advertisement information. The display area actually reflects the place where the target person appears, and the display area where the target advertisement display platform is located is added into the personal data of the target advertisement audience to be used for updating the place where the target advertisement audience appears. Furthermore, the time of capturing the target character image actually reflects the time of the target character appearing in the display area, and adding the time of capturing the target character image to the personal data of the target advertisee can be used for updating the time of the advertisee appearing in the display area. Subsequently, the computer device can push the preset database to an offline marketing person, so that the offline marketing person can track each advertisement audience according to the personal data and push goods or services in which the advertisement audience commodities are interested in a targeted manner, and the purchase probability is improved.

Step S17, adding personal data of another advertisement audience in the preset database according to the identity information of the target person, and adding the personalized preference of the target person for the first advertisement information, the display area of the target advertisement display platform, and the acquisition time of the target person image to the added personal data.

In this embodiment, the identity information of the advertisee comprises a face image area of the advertisee. And the computer device compares the face image area of the target person with the face image area of each advertisement audience in the preset database, and judges that the advertisement audience is matched with the identity information of the target person when the difference value between the face image area of the target person and the face image area of one advertisement audience is smaller than a preset difference value. And if the difference value between the human face image area of the target person and the human face image area of any advertisement audience is smaller than the preset difference value, the computer device judges that the advertisement audience matched with the identity information of the target person does not exist.

Step S18, summarizing all advertisement information displayed by each advertisement display platform in the preset database, calculating satisfaction index of the advertisement information according to personalized preference of each advertisement audience to the advertisement information, adjusting original advertisement putting plan aiming at the advertisement display platform according to the satisfaction index of each advertisement information displayed by the advertisement display platform to obtain a current advertisement putting plan, and transmitting the current advertisement putting plan to the advertisement display platform.

The satisfaction index represents the overall satisfaction of all advertisement audiences of the advertisement information to the advertisement information, and can reflect the advertisement putting effect of the advertisement display platform. In this embodiment, the satisfaction index is equal to a ratio between the number of people who prefer the advertisement audience of the advertisement information and the total number of people of all the advertisement audiences of the advertisement information, the computer device compares the satisfaction index with a preset satisfaction, and when the satisfaction index is greater than or equal to the preset satisfaction, it is determined that the total satisfaction of all the advertisement audiences of the advertisement information on the advertisement information is higher. For example, for an advertisement "Jianghuai car" displayed on the Shanghai subway No. 2 line dragon sun station advertisement display platform, through statistics, 80% of all advertisement audiences who view the advertisement information prefer the advertisement information, and if the preset satisfaction is over 60%, it indicates that the overall satisfaction of all advertisement audiences of the advertisement information to the advertisement information is high.

In this embodiment, the adjusting the original advertisement delivery plan for the advertisement display platform according to the satisfaction index of each advertisement information displayed by the advertisement display platform includes: and judging whether the satisfaction index of each advertisement message exceeds the preset satisfaction, and prolonging the advertisement time of the advertisement messages in the original advertisement putting plan when the satisfaction index exceeds the preset satisfaction. Otherwise, the advertisement time of the advertisement information in the original advertisement putting technology is shortened. For example, in the original advertisement delivery plan, the advertisement display platform has an advertisement time of 3 hours for the Jianghuai car advertisement. And if the satisfaction index of the advertisement information is judged to exceed the preset satisfaction, the computer device correspondingly prolongs the advertisement time of the advertisement information in the original advertisement putting plan. By analyzing the overall satisfaction degree of all advertisement audiences of the advertisement information to the advertisement information, the advertisement putting effect of each advertisement display platform can be quantized, reference is provided for subsequent advertisement putting, and the benefit maximization of advertisers and platform parties is realized.

The method can also determine the advertisement putting effect in other ways. In other embodiments, the following steps may be included after step S18:

step S19, summarizing all advertisement audiences corresponding to each advertisement display platform in the preset database and the occurrence time of each advertisement audience to calculate the people flow rate index of the advertisement display platform, adjusting the original advertisement putting plan aiming at the advertisement display platform according to the people flow rate index to obtain a current advertisement putting plan, and transmitting the current advertisement putting plan to the advertisement display platform.

The people flow index can reflect the advertisement putting effect of the advertisement display platform from the other side, and it can be understood that the more people flow, the better the advertisement putting effect. In this embodiment, the people flow rate index is the number of the advertisement audiences who enter the specific area of the advertisement display platform within a preset time interval (e.g., every hour), and the people flow rate index can be calculated according to the advertisement audiences corresponding to each advertisement display platform in the preset database and the time when each advertisement audience appears. And if the same advertisement audience repeatedly appears at least twice in the preset time interval, calculating according to the appearance of the at least two advertisement audiences in the same advertisement display platform. In this embodiment, the adjusting the original advertisement delivery plan for the advertisement display platform according to the people flow rate index includes: and comparing the people flow index with a preset people flow, and prolonging the advertising time of the advertising information in the original advertising plan when the people flow index is greater than or equal to the preset people flow. Otherwise, the advertisement time of the advertisement information in the original advertisement putting technology is shortened.

Fig. 1 above describes the data acquisition method for advertisement delivery in detail, and in conjunction with fig. 2 and fig. 3, the functional modules of the software device for implementing the data acquisition method and the hardware device architecture for implementing the data acquisition method are described below.

It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.

Example two

Fig. 2 is a structural diagram of a data acquisition device for advertisement delivery according to a preferred embodiment of the present invention.

In some embodiments, the data acquisition device 10 operates in a computer device. The data acquisition device 10 may include a plurality of functional modules composed of program code segments. The program code of the various program segments in the data acquisition device 10 may be stored in a memory of a computer device and executed by the at least one processor to perform data acquisition functions.

In this embodiment, the data acquisition device 10 may be divided into a plurality of functional modules according to the functions performed by the data acquisition device. Referring to fig. 2, the functional modules may include: the system comprises a first acquisition module 101, a second acquisition module 102, a first analysis module 103, a second analysis module 104, a search module 105, an addition module 106, a first summarization module 107 and a second summarization module 108. The module referred to herein is a series of computer program segments capable of being executed by at least one processor and capable of performing a fixed function and is stored in memory. In the present embodiment, the functions of the modules will be described in detail in the following embodiments.

The first capturing module 101 is used for capturing a target person image of each target person entering a specific area in front of at least one advertisement display platform.

In this embodiment, the crowd entering the shooting range may include people passing by the advertisement display platform, people facing away from the advertisement display platform (e.g., may face away from the advertisement display platform when waiting for a bus), and viewers watching the advertisement display platform. The target person of this embodiment is limited to the audience who watches the advertisement display platform. Specifically, each camera device continuously acquires images of persons in a specific range in front of the corresponding advertisement display platform in real time or periodically. The first obtaining module 101 is configured to obtain all the character images at each advertisement display platform, and the first analyzing module 103 is configured to detect whether each character image includes a face image region by using a deep convolutional neural network, and if yes, further determine whether the face image region continuously appears in the continuous character images and whether the duration of the continuous character images is greater than or equal to a first predetermined duration. If so, indicating that the corresponding person in the person image is the target person who watches the advertisement display platform, and judging that the person image is the target person image.

The second obtaining module 102 is configured to determine that the advertisement display platform corresponding to the target person image is a target advertisement display platform, and obtain a first identifier of the target advertisement display platform, a display area where the target person image is located, and first advertisement information displayed by the target advertisement display platform at the acquisition time of the target person image.

The target advertisement display platform refers to an advertisement display platform in a specific area where a target person enters. The first identifier may be an identification name or an identification code of the targeted advertisement presentation platform that is distinguished from other advertisement presentation platforms. In this embodiment, each of the target person images includes a second identifier of an image capture device used to capture the target image. The computer device stores a first corresponding relationship between unique identifiers of different advertisement display platforms and a second identifier of a camera device installed on the advertisement display platform. The second obtaining module 102 is configured to, after obtaining the target person image, determine a second identifier of the image capturing device that captures the target image, and determine the first identifier corresponding to the second identifier according to the first corresponding relationship. In another embodiment, the second obtaining module 102 may also obtain the first identifier of the target advertisement presentation platform directly from the target advertisement presentation platform.

In this embodiment, the computer device further stores a second corresponding relationship between the first identifier of the different advertisement display platform and the display area where the advertisement display platform is located. After the second obtaining module 102 obtains the first identifier of the target advertisement display platform, the display area corresponding to the first identifier is determined according to the second corresponding relationship.

In this embodiment, each of the target person images further includes the capture time, and the capture time of the target person image reflects the time when the target client appears on the target advertisement display platform (or the display area). The acquisition time may be identified in the target person image in the form of a timestamp. The computer device is preset with an original advertisement putting plan aiming at each advertisement display platform, and the original advertisement putting plan comprises advertisement information which is planned to be displayed by the target advertisement display platform at each advertisement time. The computer device can determine that the advertisement information displayed by the advertisement display platform corresponding to the target character image in the advertisement time same as the acquisition time is the first advertisement information according to the acquisition time of the target character image. Wherein the advertisement information includes a type of the advertisement object being presented (i.e., a type of goods or services) and a specific characteristic of the advertisement object. For example, for an automobile advertisement, the advertisement information may include an automobile and performance indicators for the automobile.

The first analysis module 103 is configured to analyze the identity information of the target person according to the target person image, where the identity information includes a face image region of the target person in the target person image.

In this embodiment, the first analysis module 103 is configured to detect the face image region from the target person image by using a deep convolutional neural network, and perform cropping processing on the detected face image, so as to extract the face image region. The convolutional neural network can learn the characteristics of the human face from the target person image, and then distinguish the human face image region from the non-human face image region by using a separator, so that the aim of human face detection is fulfilled. Further, the first analysis module 103 calculates the facial image region by using a trained deep learning classifier model to identify the gender, race, age, occupation, etc. of the target person. Taking the identification of the gender of the target person as an example, the calculation process includes:

b) Calling a face gender classifier model;

The second analysis module 104 is configured to analyze the behavior information of the target person according to the facial image region, and determine personalized preference of the target person for the advertisement information according to the behavior information.

In this embodiment, the second analysis module 104 is configured to identify a feature region (e.g., an eye region, an eyebrow region, a mouth region) in each facial image region, and analyze the micro-expression of the user according to a change of the feature regions of at least two consecutive facial image regions. For example, when the eye area becomes large, the micro expression is that the eyes are enlarged; when the mouth corners on the two sides deviate upwards, the micro expression is that the mouth corners on the two sides are raised; and when the mouth angle on one side deviates upwards, the micro expression is that the mouth angle on one side rises. Then, the computer device judges the personalized preference of the target person for the advertisement information according to the micro expression. For example, when the micro expression is a bilateral mouth corner upturn, it may be determined that the target person prefers the first advertisement information (i.e., is more interested); and when the micro expression is a one-sided mouth corner up, it may be determined that the target person does not prefer the first advertisement information (i.e., is not interested). The scope of the invention is not limited to the partitioning of personalized preferences as set forth in the present embodiment.

In this embodiment, the second analysis module 104 identifies an eye region in each face image region, and determines the attention duration of the target person to the first advertisement information according to the eye region of each face image region. Wherein the attention duration of the target person to the first advertisement information needs to use a light spot formed by reflecting light from the eyes of the target person. In this case, a collecting lamp may be further disposed at a position of the advertisement display platform near the camera device, and the collecting lamp is used for emitting light so that the camera device can collect a face image area, and an eye area of the face image area is formed by light reflected by an eyeball of the target person and collected by the collecting lamp. When the attention duration is greater than or equal to a second preset duration, judging that the target person is interested in the first advertisement information; otherwise, when the attention duration is smaller than the second preset duration, it is determined that the target person is not interested in the first advertisement information.

The searching module 105 is configured to search in a preset database whether there is an advertisement audience matching with the identity information of the target person, where the preset database stores personal data of a plurality of advertisement audiences, and the personal data of each advertisement audience includes the identity information of the advertisement audience, personalized preferences of at least one piece of advertisement information, a first identifier of an advertisement display platform displaying the at least one piece of advertisement information, a display area where the advertisement audience is located, and a time when the advertisement audience appears in the display area where the first advertisement display platform is located.

The adding module 106 is configured to determine that the matched advertisee is a target advertisee when the advertisee matched with the identity information of the target person exists, and add personalized preference of the target person on the first advertising information, the first identifier of the target advertising display platform, the display area where the target person is located, and the acquisition time of the target person image to personal data of the target advertisee.

And adding the first advertisement information and the personalized preference of the target person for the first advertisement information into personal data of the target advertisement audience, wherein the personalized preference of the target person for the first advertisement information actually reflects the interest points of the target person, and the interest points of the target advertisement audience can be updated by adding the first advertisement information and the personalized preference of the target person for the first advertisement information. The display area actually reflects the place where the target person appears, and the obtained display area where the advertisement display platform is located is added to the personal data of the target advertisement audience and can be used for updating the place where the target advertisement audience appears. Furthermore, the time of capturing the target character image actually reflects the time of the target character appearing in the display area, and adding the time of capturing the target character image to the personal data of the target advertisee can be used for updating the time of the advertisee appearing in the display area. Subsequently, the computer device can push the preset database to an offline marketing person, so that the offline marketing person can track each advertisement audience according to the personal data and push goods or services in which the advertisement audience commodities are interested in a targeted manner, and the purchase probability is improved.

In this embodiment, the identity information of the advertisee comprises a face image area of the advertisee. The searching module 105 is configured to compare the face image area of the target person with the face image area of each advertisee in the preset database, and determine that the advertisee matches with the identity information of the target person when a difference between the face image area of the target person and the face image area of one of the advertisees is smaller than a preset difference. And if the difference value between the face image area of the target person and the face image area of any advertisement audience is smaller than the preset difference value, judging that the advertisement audience matched with the identity information of the target person does not exist. At this time, the adding module 106 newly adds personal data of another advertisement audience in the preset database according to the identity information of the target person, and adds the personalized preference of the target person for the first advertisement information, the display area where the advertisement target display platform is located, and the acquisition time of the target person image to the newly added personal data.

The first summarizing module 107 is configured to summarize all advertisement information displayed on each advertisement display platform in the preset database, calculate a satisfaction index of the advertisement information according to personalized preferences of each advertisement audience on the advertisement information, adjust an original advertisement delivery plan for the advertisement display platform according to the satisfaction index of each advertisement information displayed on the advertisement display platform to obtain a current advertisement delivery plan, and transmit the current advertisement delivery plan to the advertisement display platform.

The satisfaction index represents the overall satisfaction of all advertisement audiences of the advertisement information to the advertisement information, and can reflect the advertisement putting effect of the advertisement display platform. In this embodiment, the satisfaction index is equal to a ratio between the number of people who prefer the advertisement audience of the advertisement information and the total number of people of all the advertisement audiences of the advertisement information, the first summarizing module 107 compares the satisfaction index with a preset satisfaction, and when the satisfaction index is greater than or equal to the preset satisfaction, it is determined that the total satisfaction of all the advertisement audiences of the advertisement information on the advertisement information is higher. For example, for an advertisement "Jianghuai car" displayed on the Shanghai subway No. 2 line dragon sun station advertisement display platform, through statistics, 80% of all advertisement audiences who view the advertisement information prefer the advertisement information, and if the preset satisfaction is over 60%, it indicates that the overall satisfaction of all advertisement audiences of the advertisement information to the advertisement information is high.

In this embodiment, the adjusting, by the first summarizing module 107, the original advertisement delivery plan for the advertisement display platform according to the satisfaction index of each piece of advertisement information displayed by the advertisement display platform includes: and judging whether the satisfaction index of each advertisement message exceeds the preset satisfaction, and prolonging the advertisement time of the advertisement messages in the original advertisement putting plan when the satisfaction index exceeds the preset satisfaction. Otherwise, the advertisement time of the advertisement information in the original advertisement putting technology is shortened. For example, in the original advertisement delivery plan, the advertisement display platform has an advertisement time of 3 hours for the Jianghuai car advertisement. And if the satisfaction index of the advertisement information is judged to exceed the preset satisfaction, the computer device correspondingly prolongs the advertisement time of the advertisement information in the original advertisement putting plan. By analyzing the overall satisfaction degree of all advertisement audiences of the advertisement information to the advertisement information, the advertisement putting effect of each advertisement display platform can be quantized, reference is provided for subsequent advertisement putting, and the benefit maximization of advertisers and platform parties is realized.

The second summarizing module 108 is configured to summarize all advertisement audiences corresponding to each advertisement display platform in the preset database and the occurrence time of each advertisement audience to calculate a people flow index of the advertisement display platform, adjust an original advertisement delivery plan for the advertisement display platform according to the people flow index to obtain a current advertisement delivery plan, and transmit the current advertisement delivery plan to the advertisement display platform.

As described above, in the embodiment of the present invention, when information is acquired, the acquired information is rich, and includes a target person image, advertisement information, a first identifier of an advertisement display platform, a display area where the advertisement display platform is located, acquisition time of the target person image, and the like, so that characteristics of multiple dimensions of identity information (including a face image area, gender, race, age, and occupation), behavior information (including micro expression and duration of attention) of a target person can be determined, and personalized preference, an appearance position, frequency, people flow information, advertisement putting effect, and the like of the target person on the advertisement information are further determined; moreover, the continuously updated preset database can be pushed to offline marketing personnel, so that the offline marketing personnel can track each advertisement audience according to the personal data and push goods or services interested by the advertisement audience commodities in a targeted manner, and the purchase probability is improved; finally, by quantifying the advertisement putting effect of each advertisement display platform, reference is provided for subsequent advertisement putting, accurate advertisement putting in different time intervals is achieved, and intelligent matching of advertisers, media and platform parties is achieved so that benefits of the advertisers, the media and the platform parties are maximized.

EXAMPLE III

FIG. 3 is a diagram of a computer device according to a preferred embodiment of the present invention.

The computer device 1 comprises a memory 20, a processor 30 and a computer program 40 stored in the memory 20 and executable on the processor 30, such as a data acquisition program for advertisement push. The processor 30, when executing the computer program 40, implements the steps of the above-described data acquisition method embodiments, such as the steps S11-S19 shown in fig. 1. Alternatively, the processor 30 executes the computer program 40 to implement the functions of the modules/units in the data acquisition device embodiment, such as the units 101 and 108 in fig. 2.

Illustratively, the computer program 40 may be partitioned into one or more modules/units that are stored in the memory 20 and executed by the processor 30 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 40 in the computer apparatus 1. For example, the computer program 40 may be divided into a first acquisition module 101, a second acquisition module 102, a first analysis module 103, a second analysis module 104, an access module 105, a search module 105, an add module 106, a first summarization module 107 and a second summarization module 108 in fig. 2. See embodiment two for specific functions of each module.

The computer device 1 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. It will be appreciated by a person skilled in the art that the schematic diagram is merely an example of the computer apparatus 1, and does not constitute a limitation of the computer apparatus 1, and may comprise more or less components than those shown, or some components may be combined, or different components, for example, the computer apparatus 1 may further comprise an input and output device, a network access device, a bus, etc.

The Processor 30 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor 30 may be any conventional processor or the like, the processor 30 being the control center of the computer device 1 and connecting the various parts of the whole computer device 1 with various interfaces and lines.

The memory 20 may be used for storing the computer program 40 and/or the module/unit, and the processor 30 implements various functions of the computer device 1 by running or executing the computer program and/or the module/unit stored in the memory 20 and calling data stored in the memory 20. The memory 20 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data) created according to the use of the computer apparatus 1, and the like. Further, the memory 20 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a flash memory Card (FlashCard), at least one magnetic disk storage device, a flash memory device, or other non-volatile solid state storage device.

The modules/units integrated with the computer device 1 may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as separate products. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).

In the embodiments provided in the present invention, it should be understood that the disclosed computer apparatus and method can be implemented in other ways. For example, the above-described embodiments of the computer apparatus are merely illustrative, and for example, the division of the units is only one logical function division, and there may be other divisions when the actual implementation is performed.

In addition, functional units in the embodiments of the present invention may be integrated into the same processing unit, or each unit may exist alone physically, or two or more units are integrated into the same unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. The units or computer means recited in the computer means claims may also be implemented by the same unit or computer means, either in software or in hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A data acquisition method for advertisement push is applied to a computer device, the computer device can communicate with a plurality of advertisement display platforms, and the method is characterized by comprising the following steps:

for each target person image, the following steps are performed:

2. The data collection method for advertisement push of claim 1, wherein the computer device is pre-provisioned with an original advertisement placement plan for each advertisement presentation platform, the method further comprising:

summarizing all advertisement information displayed by each advertisement display platform in the preset database;

calculating a satisfaction index of the advertisement information according to the personalized preference of each advertisement audience to the advertisement information; and

and adjusting an original advertisement putting plan aiming at the advertisement display platform according to the satisfaction index of each piece of advertisement information displayed by the advertisement display platform to obtain a current advertisement putting plan, and transmitting the current advertisement putting plan to the advertisement display platform.

3. The data collection method for advertisement push of claim 1, wherein the computer device is pre-provisioned with an original advertisement placement plan for each advertisement presentation platform, the method further comprising:

summarizing all advertisement audiences corresponding to each advertisement display platform in the preset database and the occurrence time of each advertisement audience to calculate the people flow rate index of the advertisement display platform; and

and adjusting an original advertisement putting plan aiming at the advertisement display platform according to the people flow index to obtain a current advertisement putting plan, and transmitting the current advertisement putting plan to the advertisement display platform.

4. The data collection method for advertisement delivery according to claim 1, wherein said acquiring the target person image of each target person entering a specific area in front of at least one advertisement presentation platform comprises:

acquiring all character images at each advertisement display platform, and detecting whether each character image comprises a face image area or not by utilizing a deep convolutional neural network;

when the character images comprise human face image areas, judging whether the human face image areas continuously appear in the continuous character images and whether the continuous time length of the continuous character images is greater than or equal to a first preset time length; and

and when the duration of the character image is greater than or equal to the first preset duration, judging that the character image is the target character image.

5. The data collection method for advertisement delivery according to claim 1, wherein at least one camera device is installed on each advertisement display platform, and the camera device of each advertisement display platform is used for collecting the target person image, wherein each target person image includes a second identifier of the camera device used for collecting the target image, and the computer device stores a first correspondence between a first identifier of a different advertisement display platform and a second identifier of the camera device installed on the advertisement display platform, and the obtaining the first identifier of the target advertisement display platform comprises:

after the target person image is obtained, determining a second identifier of a camera device for collecting the target image; and

and determining the first identifier corresponding to the second identifier according to the first corresponding relation.

6. The data collection method for pushing advertisement as claimed in claim 5, wherein each of the target person images further includes the collection time, the collection time of the target person image reflects the time when the target client appears on the target advertisement display platform, the computer device is pre-configured with an original advertisement placement plan for each advertisement display platform, the original advertisement placement plan includes advertisement information that the target advertisement display platform plans to display at each advertisement time, and the computer device determines the advertisement information that the target advertisement display platform displays at the same advertisement time as the collection time is the first advertisement information according to the collection time of the target person image.

7. The data collection method for advertisement push according to claim 1, wherein the behavior information includes at least one of a micro-expression of the target person and a length of attention to the first advertisement information.

8. A data collection device for advertisement delivery, the device comprising:

9. A computer device, characterized by: the computer arrangement comprises a processor for implementing the data acquisition method for advertisement push of any of claims 1-7 when executing a computer program stored in a memory.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program, when executed by a processor, implements a data collection method for advertisement push as claimed in any one of claims 1-7.