CN112101979A - Advertisement pushing method and pushing system thereof - Google Patents
Advertisement pushing method and pushing system thereof Download PDFInfo
- Publication number
- CN112101979A CN112101979A CN202010742534.7A CN202010742534A CN112101979A CN 112101979 A CN112101979 A CN 112101979A CN 202010742534 A CN202010742534 A CN 202010742534A CN 112101979 A CN112101979 A CN 112101979A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- image data
- database
- face image
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an advertisement pushing method, which comprises the steps of establishing a face database and an advertisement database; acquiring images of pedestrians who must pass through a path to the advertising screen, and performing face recognition and pedestrian movement direction recognition; if the moving direction of the pedestrian is close to the advertising screen, reporting the recognized face image data, otherwise, giving up the acquisition of the pedestrian image; matching the reported face image data with a face database; forming a target advertisement corresponding to the reported face image data according to the matching result; and acquiring images of pedestrians in a first preset distance in front of the advertisement screen, and determining the advertisements played by the advertisement screen according to the postures of the pedestrians in front of the advertisement screen, the reported face image data, the face database matching result and the specified attributes of the advertisements in the advertisement database. The invention also discloses an advertisement pushing system. The invention can realize accurate advertisement putting, flexible putting setting, flexible advertisement putting setting, high-efficiency operation efficiency and benign operation environment.
Description
Technical Field
The invention relates to the field of information, in particular to an advertisement pushing method. The invention also relates to an advertisement pushing system.
Background
The advertisement, as the name implies, is an advertisement that informs the general public of the society of something. The meaning of advertisement is broadly and narrowly defined. Non-economic advertising refers to advertising that is not targeted for profit, such as government announcements, political parties, religions, education, culture, municipal administration, social group initiatives, statements, and the like. Economic advertising refers to advertising for profit purposes, typically commercial advertising, which is a means of disseminating information of goods or services to consumers or users through advertising media in a paid manner for the purpose of promoting the goods or providing the services. The commodity advertisement is the economic advertisement
With the rapid development of internet technology, the advertisement delivery form in the advertisement field also tends to be diversified. At present, a large number of advertisement screens (such as shopping malls and elevators) exist in the society, and the advertisement screens are used for playing multimedia materials to publicize products and attract customers to consume. When the current advertisement screen plays advertisements, a timing carousel mode is adopted in most cases, and whether audiences exist or not or whether the audiences like the advertisements or not is not concerned. This results in reduced advertising effectiveness desired by the advertising sponsors, and the audience is also affected by the lack of interest (dislike) in the advertising, which affects the user experience of the commercial property.
Disclosure of Invention
In this summary, a series of simplified form concepts are introduced that are simplifications of the prior art in this field, which will be described in further detail in the detailed description. This summary of the invention is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.
The invention aims to provide an advertisement pushing method for accurately delivering advertisements based on face recognition and internet technology.
The invention provides an advertisement push system for accurately delivering advertisements based on face recognition and internet technology.
In order to solve the technical problem, the advertisement push method provided by the invention comprises the following steps:
s1, establishing a face database and an advertisement database;
optionally, the face database is built based on the acquired face image data and/or imported third party existing data.
The collected face image data can be collected by field registration or long-term data collection;
exemplarily, a certain shop is taken as an example; the method comprises the following steps that Mr. O registered members simultaneously acquire face image data (which can be in a photo providing mode), and the face image data registered by Mr. O is simultaneously input into a face database;
the method comprises the steps of carrying out long-term data acquisition (the time is determined according to the system capacity, such as 100 days) on a certain elevator in a shopping mall, finding out face image data P, and enabling the occurrence frequency to be more than Q (the frequency is specified according to the actual situation, such as 10), establishing that the face image data P is Mr. O (the Mr. O is a code number and is not a real name), inputting the face image data P into a face database, and correspondingly specifying user information of the Mr. O, such as male, the age of 20-30, the height of 170 and 180CM in a shop, walking path preference (frequently riding a certain elevator), preference of entering the shop, residence time and the like, namely forming the face database of long-term repeated pedestrians through big data.
Third party existing data includes, but is not limited to, third party registered member data.
The face database at least comprises face image data and user information;
the user information comprises user inherent information and user behavior information; the user inherent information is information which is irrelevant to the user behavior and does not change along with the new behavior of the user, such as sex, age and height;
the user behavior information is a user behavior data set obtained by data collection, such as: the preference of a walking path, the historical time period of walking the path, the preference of entering a shop, the residence time of the shop, the residence time of playing a certain brand of advertisement facing an advertisement screen and the like.
The advertisement database at least comprises advertisement target crowd information and advertisement designated attributes;
the advertisement target crowd information can be specified according to the requirement of an advertisement putting party, such as a male with the age of 30-40.
The specified attributes of the advertisement can be set according to the actual conditions, including the specified playing time of the advertisement, the category of the advertisement, the price of the advertisement and the like.
For example, if the advertisement fee of the advertisement delivering party a is a ten thousand, the advertisement fee of the advertisement delivering party B is B ten thousand, and a is greater than B, the advertisement delivering party a delivers the advertisement with priority (specifying the playing time, the carousel frequency, the playing sequence, and the like).
S2, acquiring images of pedestrians who must pass through the advertisement screen, and performing face recognition and pedestrian movement direction recognition;
s3, if the moving direction of the pedestrian is close to the advertising screen, reporting the recognized face image data, otherwise, abandoning the image acquisition of the pedestrian;
s4, matching the reported face image data with a face database;
when the step S4 is implemented, if the reported face image data is successfully matched with a certain face image data in the face database, the reported face image data inherits the user information corresponding to the successfully matched face image data in the face database; and if the reported face image data fails to be matched with the face database, reporting that the matching fails.
S5, forming a target advertisement corresponding to the reported face image data according to the reported face image data and the matching result of the face database;
when step S5 is implemented, extracting advertisement target population information and advertisement designated attributes of the current advertisement in the advertisement database, and forming a target advertisement corresponding to the reported facial image data according to the advertisement target population information and the user information inherited by the reported facial image data;
and forming different alternative advertisement combinations according to the specified attributes of the advertisements or user customization.
S6, collecting images of pedestrians in a first preset distance in front of the advertisement screen, and determining the advertisements played by the advertisement screen according to the postures of the pedestrians in front of the advertisement screen, the reported face image data, the matching result of the face database and the specified attributes of the advertisements in the advertisement database.
When step S6 is implemented, if a pedestrian exists within a predetermined distance and faces an advertisement screen, requesting to play a target advertisement corresponding to the reported face image data; and if no pedestrian exists within the preset distance and/or the matching is failed to be received, requesting to play the alternative advertisement combination.
The invention provides an advertisement pushing system, which is realized based on face recognition and internet technology and comprises the following steps:
the camera is arranged on a necessary path leading to the advertisement screen, a second preset distance is arranged between the camera and the advertisement screen, and the camera is used for collecting images of pedestrians approaching the advertisement screen and transmitting the images to the processor; for the pedestrian moving away from the advertising screen, giving up collecting the pedestrian image; the camera on the necessary path leading to the advertising screen is selected, so that the scale of the system is favorably reduced, and the investment cost of the system is further reduced.
The second preset distance is selected according to actual conditions, and the distance between the camera and the advertising screen is kept between 10 meters and 50 meters as far as possible. Due to the fact that the pedestrians go at different traveling speeds, the pedestrians who pass through the camera first and then arrive at the advertising screen possibly exist, and therefore errors in advertisement playing can be caused. That is, the target advertisement that reaches the pedestrian on the advertisement screen first should be played, but the target advertisement that reaches the pedestrian on the camera first should be played. Therefore, the distance between the camera and the advertisement screen is not suitable to be too long, and the change of the sequence of the pedestrians reaching the advertisement screen is reduced as much as possible.
The advertisement screen is arranged at a designated position, including but not limited to an elevator hall and an entrance and exit, plays advertisements according to instructions of the processor, can acquire images of pedestrians within a first preset distance in front of the advertisement screen, and sends different playing requests to the processor according to postures of the pedestrians acquired by the images;
the first preset distance is usually 0.1 m to 3 m, and can be selected according to actual conditions. If the size of the advertisement screen is very large, for example 5 m by 5 m, the first preset distance may be increased.
The processor is internally provided with a face database and an advertisement database, and instructs the advertisement screen to play different advertisements according to the advertisement screen playing request, the matching result of the pedestrian image acquired by the camera and the face image data in the face database, and the specified attribute of the advertisements in the advertisement database; the processor may be a PC.
The face database at least comprises face image data and user information;
the advertisement database includes at least advertisement target population information and advertisement specifying attributes.
Optionally, the face database is built based on the acquired face image data and/or imported third party existing data.
The face database at least comprises face image data and user information;
the user information comprises user inherent information and user behavior information; the user inherent information is information which is irrelevant to the user behavior and can not be changed along with the new behavior of the user;
the user behavior information is a user behavior data set obtained through data collection.
The advertisement database at least comprises advertisement target crowd information and advertisement designated attributes;
the advertisement target crowd information can be specified according to the demand of an advertisement putting party.
The advertisement appointed attribute can be set according to the actual situation.
The collected face image data, the existing data imported into the third party, the user information, the advertisement target crowd information, the advertisement designated attribute relevant description and the example refer to the above description of the pushing method part, and are not repeated.
If the reported face image data is successfully matched with certain face image data in the face database, the processor controls the reported face image data to inherit the user information corresponding to the successfully matched face image data in the face database; and if the reported face image data fails to be matched with the face database, the processor records the matching failure.
Optionally, the advertisement delivery system is further improved, and the processor forms a target advertisement corresponding to the reported face image data according to the reported face image data and the matching result of the face database;
the correspondence here means that matching between the recognized face image data and the face database succeeds in inheriting the user information in the face database, and then whether the recognized face image data is the target population of the advertisement can be judged. For example, an advertising party A specifies that advertising target population information for advertisement C is 20-30 year old female. The user information inherited by the recognized face image data is as follows: plum, female, 25 years old. The plum blossom is the target population of the advertisement, and the target advertisement is played.
And after different alternative advertisement combinations are formed according to the specified attributes of the advertisements in the advertisement database, the advertisements or the alternative advertisement combinations played by the advertisement screen are determined according to the posture of a person before the advertisement screen, the reported face image data, the matching result of the face database and the specified attributes of the advertisements in the advertisement database.
Alternatively, alternative advertisement groupings may be custom formed by the user.
Optionally, the advertisement pushing system is further improved, and if the pedestrian gesture collected by the advertisement screen is oriented to the advertisement screen, a target advertisement corresponding to the pedestrian face image data is requested to be played;
and if the pedestrian does not exist in the first preset distance acquired by the advertisement screen and/or the matching result of the pedestrian image acquired by the camera and the face image data of the face database is failed, requesting to play the alternative advertisement combination. That is, the user-defined advertisement is played under the condition of failed matching or no person in front of the advertisement screen (the user refers to the operator of the push system)
Alternative advertisement combinations can be specified according to actual conditions; for example, according to the specified attributes of the advertisement, the advertisement fee of the advertisement delivering party A is a ten thousand, the advertisement fee of the advertisement delivering party B is B ten thousand, and a is more than B, the advertisement delivered by the advertisement delivering party A is added into the alternative advertisement combination. And under the condition of failed matching, the pedestrian is proved to have no prior data, so that the behavior preference of the pedestrian cannot be judged, and the advertisement of the high-investment putting party is promoted according to the specified attribute of the advertisement. The arrangement is beneficial to protecting the economic benefits of high-investment delivering parties, so that the advertisement of the delivering parties can obtain larger propaganda effect as far as possible. And also for the conversion of advertising (to customers) for new pedestrians (without prior data). The advertisement conversion rate is high, and an advertisement putting party is more willing to invest funds, so that the good operation of the advertisement push system is facilitated.
Optionally, the advertisement pushing system is further improved, the advertisement screen and the cameras on the paths leading to the advertisement screen within the preset range around the advertisement screen are combined to form an equipment group, and different advertisements are preset for different equipment groups.
The equipment groups are formed to be beneficial to system management, and different equipment groups are different from target customers, so that different preset advertisements are set for different equipment groups, the advertising effect of the advertisements is beneficial to optimization, and the advertisement conversion rate (converted into the customers) can be improved.
For example, most of the shopping mall is customers who go in and out, so that an equipment group can be formed, and the shopping mall is mainly pushed with the advertisement screen to advertise the commodities in the shopping mall. The rear mall door (such as staff passage) may be accessed by suppliers, staff in shops in the mall, and the like, and the rear mall door advertisement screen can be used for mainly pushing other product advertisements, such as living goods.
The invention can at least realize the following technical effects;
1. accurate advertisement putting is realized through face identification in combination with internet technology, is favorable to improving advertising effect and the advertisement conversion rate (turn into the customer) of advertisement putting side.
2. The flexible advertisement putting arrangement can put different advertisements to different target customers by forming the equipment group, and is beneficial to improving the propaganda effect and the advertisement conversion rate (converted into customers) of the advertisement putting party.
3. The efficient operating efficiency sets up the camera on the must pass through the route (predetermineeing the scope) that is close the advertising screen, shoots pedestrian's image and conveys the treater and carry out face identification and analysis and judgment before the pedestrian arrives the advertising screen, has reserved processing time for the treater, has improved system operating efficiency.
4. The invention can perform different management on different advertisement putting parties (such as invested funds and putting positions) in a benign operation environment, obtains high return after high investment and is beneficial to the benign operation of a system.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention, are incorporated in and constitute a part of this specification. The drawings are not necessarily to scale, however, and may not be intended to accurately reflect the precise structural or performance characteristics of any given embodiment, and should not be construed as limiting or restricting the scope of values or properties encompassed by exemplary embodiments in accordance with the invention. The invention will be described in further detail with reference to the following detailed description and accompanying drawings:
fig. 1 is a flow chart of an advertisement pushing method according to the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and technical effects of the present invention will be fully apparent to those skilled in the art from the disclosure in the specification. The invention is capable of other embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the general spirit of the invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict. The following exemplary embodiments of the present invention may be embodied in many different forms and should not be construed as limited to the specific embodiments set forth herein. It is to be understood that these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the technical solutions of these exemplary embodiments to those skilled in the art.
In a first embodiment, the present invention provides an advertisement push method, including the following steps:
s1, establishing a face database and an advertisement database;
the face database at least comprises face image data and user information;
the advertisement database at least comprises advertisement target crowd information and advertisement designated attributes;
s2, acquiring images of pedestrians who must pass through the advertisement screen, and performing face recognition and pedestrian movement direction recognition;
s3, if the moving direction of the pedestrian is close to the advertising screen, reporting the recognized face image data, otherwise, abandoning the image acquisition of the pedestrian;
s4, matching the reported face image data with a face database;
s5, forming a target advertisement corresponding to the reported face image data according to the reported face image data and the matching result of the face database;
s6, collecting images of pedestrians in a first preset distance in front of the advertisement screen, and determining the advertisements played by the advertisement screen according to the postures of the pedestrians in front of the advertisement screen, the reported face image data, the matching result of the face database and the specified attributes of the advertisements in the advertisement database.
The first embodiment of the invention can realize accurate advertisement delivery by combining the face recognition with the internet technology, is beneficial to improving the propaganda effect and the advertisement conversion rate (converted into customers) of the advertisement delivery party, can perform different management on different advertisement delivery parties (such as invested funds and delivery positions), obtains high return after high input, and is beneficial to the benign operation of the advertisement operator.
In a second embodiment, the present invention provides an advertisement push method, including the following steps:
s1, establishing a face database based on the collected face image data and/or the existing data imported into the third party; wherein the third party data adopts registered member data; the face database at least comprises face image data and user information;
the user information comprises user inherent information and user behavior information; the user inherent information is information which is irrelevant to the user behavior and does not change along with the new behavior of the user, such as sex, age and height;
the user behavior information is a user behavior data set obtained through data acquisition, such as the preference of a walking path, the preference of entering a shop, the residence time of the shop, the residence time of playing a certain brand of advertisement facing an advertisement screen, and the like.
The advertisement database at least comprises advertisement target crowd information and advertisement designated attributes;
the advertisement target crowd information can be specified according to the requirement of an advertisement putting party, such as a male with the age of 30-40.
The specified attributes of the advertisement can be set according to the actual conditions, including the specified playing time of the advertisement, the category of the advertisement, the price of the advertisement and the like.
For example, if the advertisement fee of the advertisement delivering party a is a ten thousand, the advertisement fee of the advertisement delivering party B is B ten thousand, and a is greater than B, the advertisement delivering party a delivers the advertisement with priority (specifying the playing time, the carousel frequency, the playing sequence, and the like).
S2, acquiring images of pedestrians who must pass through the advertisement screen, and performing face recognition and pedestrian movement direction recognition;
s3, if the moving direction of the pedestrian is close to the advertising screen, reporting the recognized face image data, otherwise, abandoning the image acquisition of the pedestrian;
s4, matching the reported face image data with the face database, and if the reported face image data is successfully matched with the face image data in the face database, reporting the face image data to inherit the user information corresponding to the successfully matched face image data in the face database; if the reported face image data fails to be matched with the face database, reporting matching failure;
s5, extracting advertisement target crowd information and advertisement designated attributes of the current advertisement in the advertisement database, and forming a target advertisement corresponding to the reported facial image data according to the advertisement target crowd information and the user information inherited by the reported facial image data;
and forming different alternative advertisement combinations according to the specified attributes of the advertisements or user customization;
s6, collecting images of pedestrians in front of the advertisement screen, and playing a target advertisement corresponding to the reported face image data if the pedestrians exist in a preset distance and face the advertisement screen; and if no pedestrian exists within the preset distance and/or the matching is failed to be received, playing the alternative advertisement combination.
In a third embodiment, the present invention provides an advertisement delivery system, which is implemented based on face recognition and internet technology, and includes:
the camera is arranged on a necessary path leading to the advertisement screen, a second preset distance is arranged between the camera and the advertisement screen, and the camera is used for collecting images of pedestrians approaching the advertisement screen and transmitting the images to the processor; for the pedestrian moving away from the advertising screen, giving up collecting the pedestrian image;
here, the pedestrian image transmitted to the processor by the camera can be selected from two options:
the first is to use a camera to execute face recognition, and the pedestrian image transmitted to the processor is face image data; the method adopts distributed recognition calculation, reduces the operation pressure of the processor, and can improve the operation efficiency of the system.
The second is that the camera directly transmits the image to the processor, and the processor executes the face recognition; the advantage of this approach is that the cost of the system can be reduced. For example, a camera of an existing security monitoring system may be utilized for transmitting a captured image of a pedestrian. And performing face recognition, matching and other calculations on the processor.
The two modes have no essential difference under the general design idea of the invention, and the main difference lies in the requirement on the processing capacity of the camera;
the preset distance is selected according to the actual situation, the preset distance is suggested to be relatively long when the complex path (branch exists), and the preset distance is suggested to be relatively short when the simple path (branch does not exist in the single path);
the advertisement screen is arranged at a designated position, plays advertisements according to instructions of the processor, can acquire images of pedestrians in a first preset distance in front of the advertisement screen, and sends different playing requests to the processor according to postures of the pedestrians acquired by the images;
the processor is internally provided with a face database and an advertisement database, and instructs the advertisement screen to play different advertisements according to the advertisement screen playing request, the matching result of the pedestrian image acquired by the camera and the face image data of the face database, and the specified attributes of the advertisements in the advertisement database; the processor may be a PC.
The third embodiment of the invention can realize accurate advertisement delivery by combining face recognition with internet technology, different target customers deliver different advertisements, which is beneficial to improving the propaganda effect and the advertisement conversion rate (converted into customers) of an advertisement delivery party, and can perform different management on different advertisement delivery parties (such as invested funds and delivery positions), a camera is arranged on a necessary path (preset range) close to an advertisement screen, a pedestrian image is shot before the pedestrian reaches the advertisement screen, and is transmitted to a processor for face recognition and analysis judgment, the processing time is reserved for the processor, the system operation efficiency is improved, high return is obtained by high input, and the benign operation of the advertisement delivery party is facilitated.
In a fourth embodiment, the present invention provides an advertisement delivery system, which is implemented based on face recognition and internet technologies, and includes:
the camera is arranged on a necessary path leading to the advertisement screen, a second preset distance is arranged between the camera and the advertisement screen, and the camera is used for collecting images of pedestrians approaching the advertisement screen and transmitting the images to the processor;
the camera can utilize the camera of the existing security monitoring system, and can also be provided with a special camera; correspondingly, for the descriptions of different working modes of the camera and the processor, reference is made to the corresponding description of the third embodiment, and further description is omitted here.
The advertisement screen is arranged at a designated position, plays advertisements according to instructions of the processor, can acquire images of pedestrians in a first preset distance in front of the advertisement screen, and sends different playing requests to the processor according to postures of the pedestrians acquired by the images;
correspondingly, the number of the advertisement screens in the system can be multiple, and the number of the cameras can also be multiple. The advertisement screen and the cameras on the path which are necessary to pass through the advertisement screen in the preset range around the advertisement screen are combined to form an equipment group, and different advertisements are preset for different equipment groups. The equipment groups are formed to be beneficial to system management, and different equipment groups are different from target customers, so that different preset advertisements are set for different equipment groups, the advertising effect of the advertisements is beneficial to optimization, and the advertisement conversion rate (converted into the customers) can be improved.
For example, most of the shopping malls are customers who enter and exit from the front door, so that an equipment group can be formed, and the advertisement screen mainly pushes the commodity advertisement in the shopping malls. The entrance and exit of the back door of the store (such as staff passage) can be the suppliers, staff in the store, and the like, and other product advertisements, such as daily necessities, can be pushed mainly. The main design idea of the example is to select the played advertisement according to the pedestrian passing by the channel, and to specifically promote the content that the pedestrian may be interested in.
As another example, a person entering from a different entrance in a store may enter a different area of the store. If a market enters from the entrance X and the area of the entrance X is a jewelry area, an advertisement screen arranged at the entrance X plays an advertisement of an advertisement putting party in the jewelry area of the market. If a user enters a market from an entrance Y and the area of the entrance Y is a makeup area, an advertisement screen arranged at the entrance Y plays an advertisement of an advertisement putting party in the makeup area of the market. The main design idea of the example is that the advertisement is selected to be played according to the commercial tenant in the subsequent area of the channel, the pedestrian entering from the area is likely to be interested in the commodity in the area, and the advertisement investment of the commercial tenant in the area can directly form customer conversion in the area, so that the pedestrian can directly find the commodity conveniently.
The processor is internally provided with a face database and an advertisement database, and instructs the advertisement screen to play different advertisements according to the advertisement screen playing request, the matching result of the pedestrian image acquired by the camera and the face image data of the face database, and the specified attributes of the advertisements in the advertisement database; the processor may be a PC.
The face database is built based on the collected face image data and/or the existing data imported into the third party. Third party data, such as registered member data.
The face database at least comprises face image data and user information;
the user information comprises user inherent information and user behavior information; the user inherent information is information which is irrelevant to the user behavior and does not change along with the new behavior of the user, such as sex, age and height;
the user behavior information is a user behavior data set obtained through data acquisition, such as the preference of a walking path, the preference of entering a shop, the residence time of the shop, the residence time of playing a certain brand of advertisement facing an advertisement screen, and the like.
The advertisement database at least comprises advertisement target crowd information and advertisement designated attributes;
the advertisement target crowd information can be specified according to the requirement of an advertisement putting party, such as a male with the age of 30-40.
The specified attributes of the advertisement can be set according to the actual conditions, including the specified playing time of the advertisement, the category of the advertisement, the price of the advertisement and the like.
For example, if the advertisement fee of the advertisement delivering party a is a ten thousand, the advertisement fee of the advertisement delivering party B is B ten thousand, and a is greater than B, the advertisement delivering party a delivers the advertisement with priority (specifying the playing time, the carousel frequency, the playing sequence, and the like).
When the processor instructs the advertisement screen to play different advertisements: if the pedestrian gesture collected by the advertising screen is oriented to the advertising screen, requesting to play a target advertisement corresponding to the pedestrian face image data; the correspondence here means that matching between the recognized face image data and the face database succeeds in inheriting the user information in the face database, and then whether the recognized face image data is the target population of the advertisement can be judged. For example, an advertising party A specifies that advertising target population information for advertisement C is 20-30 year old female. The user information inherited by the recognized face image data is as follows: plum, female, 25 years old. The plum blossom is the target population of the advertisement, and the target advertisement is played.
And if the pedestrian does not exist in the first preset distance acquired by the advertisement screen and/or the matching result of the pedestrian image acquired by the camera and the face image data of the face database is failed, requesting to play the alternative advertisement combination.
As described above, under the general design idea of the present invention, one way is to perform face recognition on a pedestrian image collected by a camera by a processor, match the recognized face image data with a face database, and if the matching is successful, the recognized face image data inherits the user information corresponding to the successfully matched face image data in the face image database; if the matching fails, marking the matching result as failure;
extracting advertisement target crowd information and advertisement designated attributes of the current advertisement in an advertisement database, and forming a target advertisement corresponding to the reported facial image data according to the advertisement target crowd information and user information inherited by the reported facial image data;
and forming different alternative advertisement combinations according to the specified attributes of the advertisements or user customization.
For example, according to the specified attributes of the advertisement, the advertisement fee of the advertisement delivering party A is a ten thousand, the advertisement fee of the advertisement delivering party B is B ten thousand, and a is more than B, the advertisement delivered by the advertisement delivering party A is added into the alternative advertisement combination. And under the condition of failed matching, the pedestrian is proved to have no prior data, so that the behavior preference of the pedestrian cannot be judged, and the advertisement of the high-investment putting party is promoted according to the specified attribute of the advertisement. The arrangement is beneficial to protecting the economic benefits of high-investment delivering parties, so that the advertisement of the delivering parties can obtain larger propaganda effect as far as possible. And also for the conversion of advertising (to customers) for new pedestrians (without prior data). The advertisement conversion rate is high, and an advertisement putting party is more willing to invest funds, so that the good operation of the advertisement push system is facilitated.
It should be further noted that the processor instructs the advertisement playing according to the pedestrian face image data sent by the camera, and when there are a plurality of pedestrians, the advertisement playing sequence on the advertisement screen is determined according to the receiving sequence of the pedestrian face image data. And optionally setting whether the formed advertisement playing sequence can be changed by recognizing the pedestrian posture by the advertisement screen.
For example, pedestrian M, male, 25 years old; pedestrian N, female, 45 years old; the advertisements are identified after passing through the camera in sequence, and the sequence of the advertisements reaching the advertisement screen is not changed, so that the advertisements instructed by the processor can be played according to the identification sequence.
It is also possible that the pedestrian M suddenly accelerates, the pedestrian N temporarily stops moving (stays on the phone); in this case, the priority of the request for the advertisement screen can be selectively set to be higher. The pedestrian M arrives before the advertisement screen first, and the advertisement screen recognizes that the posture thereof is facing the advertisement screen, it may request to preferentially play the advertisement of the pedestrian M as the target person. And (5) subsequent playing, namely, serving as the advertisement of the target person for the pedestrian N. The pedestrian posture recognition priority of the advertisement screen is improved, and the accuracy of playing advertisements on the advertisement screen is further improved.
Unless otherwise defined, all terms (including 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. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The present invention has been described in detail with reference to the specific embodiments and examples, but these are not intended to limit the present invention. Many variations and modifications may be made by one of ordinary skill in the art without departing from the principles of the present invention, which should also be considered as within the scope of the present invention.
Claims (16)
1. An advertisement pushing method is characterized by comprising the following steps:
s1, establishing a face database and an advertisement database;
the face database at least comprises face image data and user information;
the advertisement database at least comprises advertisement target crowd information and advertisement designated attributes;
s2, acquiring images of pedestrians who must pass through the advertisement screen, and performing face recognition and pedestrian movement direction recognition;
s3, if the moving direction of the pedestrian is close to the advertising screen, reporting the recognized face image data, otherwise, abandoning the image acquisition of the pedestrian;
s4, matching the reported face image data with a face database;
s5, forming a target advertisement corresponding to the reported face image data according to the reported face image data and the matching result of the face database;
s6, collecting images of pedestrians in a first preset distance in front of the advertisement screen, and determining the advertisements played by the advertisement screen according to the postures of the pedestrians in front of the advertisement screen, the reported face image data, the matching result of the face database and the specified attributes of the advertisements in the advertisement database.
2. The advertisement push method according to claim 1, characterized in that:
the user information comprises user inherent information and user behavior information;
the user inherent information is information which is irrelevant to the user behavior and can not be changed along with the new behavior of the user;
the user behavior information is a user behavior data set obtained through data collection.
3. The advertisement push method according to claim 1, characterized in that:
the advertisement designation attributes include a designated playing time of the advertisement, a category to which the advertisement belongs, and an advertisement price.
4. The advertisement push method according to claim 1, characterized in that: the face database is built based on the collected face image data and/or the existing data imported into the third party.
5. The advertisement push method according to claim 1, characterized in that: when the step S4 is implemented, if the reported face image data is successfully matched with a certain face image data in the face database, the reported face image data inherits the user information corresponding to the successfully matched face image data in the face database; and if the reported face image data fails to be matched with the face database, reporting that the matching fails.
6. The advertisement push method according to claim 1, characterized in that: when step S5 is implemented, extracting advertisement target crowd information and advertisement designated attributes of the current advertisement in the advertisement database, and forming a target advertisement corresponding to the reported facial image data according to the advertisement target crowd information and the user information inherited by the reported facial image data;
and forming different alternative advertisement combinations according to the specified attributes of the advertisements or user customization.
7. The advertisement push method according to claim 6, characterized in that: when the step S6 is executed, if a pedestrian exists within the predetermined distance and faces the advertisement screen, requesting to play a target advertisement corresponding to the reported face image data; and if no pedestrian exists within the preset distance and/or the matching is failed to be received, requesting to play the alternative advertisement combination.
8. An advertisement push system, comprising:
the camera is arranged on a necessary path leading to the advertisement screen, a second preset distance is arranged between the camera and the advertisement screen, and the camera is used for collecting images of pedestrians approaching the advertisement screen and transmitting the images to the processor;
the advertisement screen is arranged at a designated position, plays advertisements according to instructions of the processor, can acquire images of pedestrians in a first preset distance in front of the advertisement screen, and sends different playing requests to the processor according to postures of the pedestrians acquired by the images;
the processor is internally provided with a face database and an advertisement database, and instructs the advertisement screen to play different advertisements according to the advertisement screen playing request, the matching result of the pedestrian image acquired by the camera and the face image data in the face database, and the specified attribute of the advertisements in the advertisement database;
the face database at least comprises face image data and user information;
the advertisement database includes at least advertisement target population information and advertisement specifying attributes.
9. The advertisement push system according to claim 8, characterized in that:
the user information comprises user inherent information and user behavior information;
the user inherent information is information which is irrelevant to the user behavior and can not be changed along with the new behavior of the user;
the user behavior information is a user behavior data set obtained through data collection.
10. The advertisement push system according to claim 8, characterized in that:
the advertisement designation attributes include a designated playing time of the advertisement, a category to which the advertisement belongs, and an advertisement price.
11. The advertisement push system according to claim 8, characterized in that: the face database is built based on the collected face image data and/or the existing data imported into the third party.
12. The advertisement push system according to claim 8, characterized in that: if the reported face image data is successfully matched with certain face image data in the face database, the processor controls the reported face image data to inherit the user information corresponding to the successfully matched face image data in the face database; and if the reported face image data fails to be matched with the face database, the processor records the matching failure.
13. The advertisement push system according to claim 8, characterized in that: the processor forms a target advertisement corresponding to the reported face image data according to the reported face image data and the matching result of the face database;
and after different alternative advertisement combinations are formed according to the specified attributes of the advertisements in the advertisement database, the advertisements or the alternative advertisement combinations played by the advertisement screen are determined according to the posture of a person before the advertisement screen, the reported face image data, the matching result of the face database and the specified attributes of the advertisements in the advertisement database.
14. The advertisement push system according to claim 13, characterized in that: alternative advertisement combinations are custom formed by the user.
15. The advertisement push system according to claim 12, characterized in that: if the pedestrian gesture collected by the advertising screen is oriented to the advertising screen, requesting to play a target advertisement corresponding to the pedestrian face image data;
and if the pedestrian does not exist in the first preset distance acquired by the advertisement screen and/or the matching result of the pedestrian image acquired by the camera and the face image data of the face database is failed, requesting to play the alternative advertisement combination.
16. The advertisement push system according to claim 8, characterized in that: the advertisement screen and the cameras on the path which are necessary to pass through the advertisement screen in the preset range around the advertisement screen are combined to form an equipment group, and different advertisements are preset for different equipment groups.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010742534.7A CN112101979A (en) | 2020-07-29 | 2020-07-29 | Advertisement pushing method and pushing system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010742534.7A CN112101979A (en) | 2020-07-29 | 2020-07-29 | Advertisement pushing method and pushing system thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112101979A true CN112101979A (en) | 2020-12-18 |
Family
ID=73749541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010742534.7A Pending CN112101979A (en) | 2020-07-29 | 2020-07-29 | Advertisement pushing method and pushing system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112101979A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112767019A (en) * | 2021-01-12 | 2021-05-07 | 珠海亿智电子科技有限公司 | Advertisement putting method, device, equipment and storage medium |
| CN115580754A (en) * | 2022-12-06 | 2023-01-06 | 成都智元汇信息技术股份有限公司 | Subway public space content on-demand method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106296264A (en) * | 2016-07-28 | 2017-01-04 | 河海大学常州校区 | A kind of pushing intelligent advertisements system based on recognition of face |
| CN109523325A (en) * | 2018-11-29 | 2019-03-26 | 成都睿码科技有限责任公司 | A kind of targetedly self-regulation advertisement delivery system based on recognition of face |
| CN109934625A (en) * | 2019-03-01 | 2019-06-25 | 统云信息科技有限公司 | A kind of artificial intelligence display screen advertisement dynamic throwing system and method |
| CN110889719A (en) * | 2019-11-19 | 2020-03-17 | 珠海亿智电子科技有限公司 | Advertisement pushing system and method based on user consumption characteristics |
| CN111242683A (en) * | 2020-01-10 | 2020-06-05 | 深圳市胜博恩科技有限公司 | Method and device for self-service delivery of advertisement content, storage medium and computer equipment |
| CN111428662A (en) * | 2020-03-30 | 2020-07-17 | 齐鲁工业大学 | Advertisement playing change method and system based on crowd attributes |
-
2020
- 2020-07-29 CN CN202010742534.7A patent/CN112101979A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106296264A (en) * | 2016-07-28 | 2017-01-04 | 河海大学常州校区 | A kind of pushing intelligent advertisements system based on recognition of face |
| CN109523325A (en) * | 2018-11-29 | 2019-03-26 | 成都睿码科技有限责任公司 | A kind of targetedly self-regulation advertisement delivery system based on recognition of face |
| CN109934625A (en) * | 2019-03-01 | 2019-06-25 | 统云信息科技有限公司 | A kind of artificial intelligence display screen advertisement dynamic throwing system and method |
| CN110889719A (en) * | 2019-11-19 | 2020-03-17 | 珠海亿智电子科技有限公司 | Advertisement pushing system and method based on user consumption characteristics |
| CN111242683A (en) * | 2020-01-10 | 2020-06-05 | 深圳市胜博恩科技有限公司 | Method and device for self-service delivery of advertisement content, storage medium and computer equipment |
| CN111428662A (en) * | 2020-03-30 | 2020-07-17 | 齐鲁工业大学 | Advertisement playing change method and system based on crowd attributes |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112767019A (en) * | 2021-01-12 | 2021-05-07 | 珠海亿智电子科技有限公司 | Advertisement putting method, device, equipment and storage medium |
| CN115580754A (en) * | 2022-12-06 | 2023-01-06 | 成都智元汇信息技术股份有限公司 | Subway public space content on-demand method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019149005A1 (en) | Offline interactive advertisement system | |
| JP6138930B2 (en) | Method and apparatus for selecting advertisements for display on a digital sign | |
| JP4125634B2 (en) | Customer information collection management method and system | |
| US8660895B1 (en) | Method and system for rating of out-of-home digital media network based on automatic measurement | |
| US9000928B2 (en) | System and method for communicating information | |
| WO2020134231A1 (en) | Information pushing method and device, and information display system | |
| CN110415065A (en) | User data collection system and information-pushing method | |
| CN106355442A (en) | Online precise advertising method and system based on big data driving | |
| US11636510B2 (en) | Systems, methods and programmed products for dynamically tracking delivery and performance of digital advertisements in electronic digital displays | |
| CN105450778B (en) | Information transmission system | |
| CN106971317A (en) | The advertisement delivery effect evaluation analyzed based on recognition of face and big data and intelligently pushing decision-making technique | |
| WO2021031600A1 (en) | Data collection method and apparatus, computer device, and storage medium | |
| CN107103485B (en) | Automatic advertisement recommendation method and system according to cinema visitor information | |
| KR101348142B1 (en) | The method for providing the customized marketing contens for the customers classified as individuals or groups by using face recognition technology and the system thereof | |
| JP5002441B2 (en) | Marketing data analysis method, marketing data analysis system, data analysis server device, and program | |
| CN109543575B (en) | Method for feeding back excitation big data based on behavior track and dynamic multi-dimensional information and regional multi-dimensional detection feedback combined equipment | |
| CN108876430B (en) | Advertisement pushing method based on crowd characteristics, electronic equipment and storage medium | |
| CN112101979A (en) | Advertisement pushing method and pushing system thereof | |
| KR20210050742A (en) | Smart exhibition management system and method | |
| CN111125288A (en) | Area deployment method, device and storage medium | |
| CN106204146A (en) | A kind of Internet advertising put-on method, device | |
| Yu et al. | AI-based targeted advertising system | |
| CN110889719A (en) | Advertisement pushing system and method based on user consumption characteristics | |
| JP2012252613A (en) | Customer behavior tracking type video distribution system | |
| CN114169952A (en) | Commodity recommendation method, server, shopping cart and shopping system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |