Advertisement player system and device

Abstract

The invention relates to an advertising machine system and device. The advertising machine system comprises a facility layer, a data layer, a platform layer, a service layer and a user layer. According to the advertising machine system, the information, including facial expressions, retina data and eyeball movement data, of past people streams is collected through a built-in high-definition camera, the collected data is locally analyzed in real time through built-in edge computing equipment, a computing task does not need to be transmitted to a remote center server, and the response speed is increased; the data mining and analyzing module identifies the flow of people, whether the past flow of people watches the advertisement and the attention of the advertisement watching personnel to the advertisement, generates a label containing gender and age, interacts with the service data in the current application scene, and automatically generates a personalized marketing scheme and verbal skill to each person; the advertisement player provided by the invention is helpful for an advertiser to adjust advertisement contents and commodities according to information fed back by the advertisement player, and has huge value in digital marketing.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence advertising media, and in particular to an advertising machine system and device. Background Art

[0002] Traditional advertising machines are divided into a hardware layer and a platform management layer. The hardware layer is mainly used for playing advertisements; the platform management layer is used to monitor, maintain, and replace and place advertisements on all advertising machine hardware online; traditional advertising machines have relatively simple functions and can only perform simple advertising placement. They have no data capture capabilities, cannot evaluate the advertising playback effect, and cannot interact with business scenario data in specific venues, making it difficult to generate personalized marketing plans for specific business scenarios.

[0003] Currently, a small number of advertising machines have cameras attached to their bodies, which can capture some data. However, they are unable to associate the captured data with the advertising data of the advertising machine itself, and are even more unable to store data on a large scale. This makes it difficult to provide advertisers with rich advertising playback information, including the advertisers' judgment on the quality of the advertisements themselves and consumers' satisfaction with the products. As a result, advertisers are unable to adjust advertising content and improve products based on market feedback. Summary of the invention

[0004] In view of this, the present invention provides an effective solution to the problems in the prior art that the relevant traffic data of the advertising machine cannot be captured, the advertising effect cannot be evaluated through the collected data and the advertising effect cannot be fed back, and the advertising data cannot be interacted with the business data of the specific business scenario to provide personalized marketing strategies.

[0005] To achieve the above object, the present invention provides an advertising machine system, comprising: Facilities layer: servers, display screens, and network equipment; Data layer: includes collected traffic data, original advertising data, and business data for specific scenarios; Collect past crowd flow data, facial expressions, eye movement data, and retinal data when the advertisement is played through a high-definition camera, and send the collected past crowd flow data to the platform layer; Platform layer: background management module, data center module and data analysis and mining module; The data center module includes a traffic data storage center, an advertising data storage center, and a business data storage center; The data analysis and mining module uses edge computing devices to perform real-time analysis on the captured data, calculates the flow of people, whether they watch ads, the length of time they watch ads, the changes in facial expressions after watching ads, the age and gender of viewers, and the proportion of people who watch ads to the past flow of people, and sends all the data to the traffic data storage center for storage; The data analysis and mining module analyzes the viewers' attention to the currently playing advertisement, determines whether the attention reaches the preset value, and generates tags for the viewers' age, gender and corresponding advertisements whose attention reaches the preset value and sends them to the traffic data storage center; The collected data is mapped with the advertising data to evaluate the advertising effect, and then personalized marketing strategies are formulated based on the evaluation results, and the personalized marketing strategies are sent to the service layer; Service layer: The personalized marketing strategies received from the platform layer are pushed to the user layer by selecting relevant advertisements to achieve personalized reach; User layer: includes PC and mobile terminals.

[0006] Preferably, the rule for collecting the passing pedestrian flow data is: judging the distance between the passing pedestrians and the advertising machine, presetting a maximum distance threshold, based on the size of the advertising machine display screen and the distance from human eyes.

[0007] Preferably, the rule for generating the label is: through the collected face image, if the face direction and the plane angle of the advertising machine display screen are within 45 degrees and the eyes stay on the advertising machine display screen for more than 5 seconds, it is judged that the viewer's attention to the currently playing advertisement reaches the preset attention value.

[0008] Preferably, if the proportion of the number of people who watch the advertisement to the past flow of people is less than a preset threshold, it is determined that the delivery effect of the currently played advertisement is not good, and the content of the currently played advertisement is changed.

[0009] Preferably, the edge design device uses jetson tx2.

[0010] Preferably, evaluating the advertising effect includes: In the same application scenario, set two different versions of advertising content, A and B; Play two different versions of advertising content, A and B, respectively through the advertising machine backend management module at the same time; Based on the collected data, it is evaluated that versions A and B are more effective; The better performing version of the ad will automatically play.

[0011] Preferably, the data analysis and mining platform formulates personalized marketing strategies and words based on the collected data and merchant business data through a large language model.

[0012] Preferably, the background management module also includes hardware management and marketing management; the marketing management sets up a customized outbound calling system.

[0013] Compared with the prior art, the present invention has the following beneficial effects: The advertising machine provided by the present invention has a built-in high-definition camera and an edge reasoning device. The data collected by the high-definition camera is directly processed on the edge reasoning device without uploading the data to the remote central server, which reduces network consumption and speeds up data calculation and processing, and improves the response speed; it avoids system crashes caused by excessive calculation pressure on the remote central server; The built-in high-definition camera of the advertising machine provided by the present invention can not only monitor the flow of people passing by, but also capture the detailed expressions of people, including retinal data and eye movement data, so as to perform a more fine-grained analysis of the data and generate the attention paid by people passing by to the advertisement; The advertising machine provided by the present invention can evaluate the advertising effect through the collected data and automatically formulate a personalized marketing plan, thereby providing substantial support for digital marketing; The advertising machine provided by the present invention can perform AI analysis on the collected data and provide rich information to the advertiser, including the quality of the advertising design and the satisfaction of the product, so as to improve the content of the advertisement and change the placement of the advertising machine; The advertising machine provided by the present invention can interact with specific business scenario data, and give customers more portrait tags with the help of business data of specific scenarios, which is more conducive to product promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a structural block diagram of an advertising machine of the present invention; Figure 2 This is the structural block diagram of a traditional advertising machine. DETAILED DESCRIPTION

[0015] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0016] This embodiment provides the following technical solutions: An advertising machine system, comprising: Facilities layer: servers, display screens, and network equipment; Data layer: includes collected traffic data, original advertising data, and business data for specific scenarios; When the distance between the passing pedestrians and the advertising machine is less than the preset maximum distance threshold, the high-definition camera is used to collect the passing pedestrian flow data and the facial expressions, eye movement data and retinal data of the people, and the collected passing pedestrian flow data is sent to the platform layer; Platform layer: background management module, data center module and data analysis and mining module; The data center module includes a traffic data storage center, an advertising data storage center, and a business data storage center; The data analysis and mining module uses the edge computing device Jetson TX2 to analyze the captured data in real time, calculate the flow of people, whether they watch ads, the length of time they watch ads, the changes in their facial expressions after watching ads, the age and gender of the viewers, and the proportion of people who watch ads in the past flow of people, and send all the data to the traffic data storage center for storage; The data analysis and mining module analyzes the viewer's attention to the currently playing advertisement and determines whether the attention reaches the preset attention value. If the face direction and the plane angle of the advertising machine display screen are within 45 degrees and the eyes stay on the advertising machine display screen for more than 5 seconds, it is determined that the viewer's attention to the currently playing advertisement reaches the preset attention value. The age, gender and corresponding advertisement generation label of viewers whose attention reaches the preset attention value are sent to the traffic data storage center; The collected data is mapped with the advertising data to evaluate the advertising effect. If the proportion of people watching the advertisement to the past flow of people is less than the preset threshold, it is judged that the current advertising effect is not good, and the current advertising content is changed; In the same application scenario, set two different versions of advertising content, A and B; Play two different versions of advertising content, A and B, respectively through the advertising machine backend management module at the same time; Based on the collected data, it is evaluated that versions A and B are more effective; The better performing version of the ad will automatically play.

[0017] Then, according to the evaluation results, personalized marketing strategies are formulated. According to the collected data and merchant business data, personalized marketing strategies and words are formulated through the big language model, and the personalized marketing strategies are sent to the service layer. Service layer: The personalized marketing strategies received from the platform layer are pushed to the user layer by selecting relevant advertisements to achieve personalized reach; User layer: includes PC and mobile terminals.

[0018] In a specific scenario of a hospital, this embodiment provides an advertising machine device of the present invention, which has a built-in high-definition camera on a traditional advertising machine to monitor and capture relevant data of the advertising machine: collecting past traffic data and facial expressions, eye movement data and retinal data when playing advertisements, and can perform more fine-grained analysis of the data; The collected past traffic data is sent to the edge computing device jetson tx2 built into the advertising machine to perform AI model inference tasks. Inference calculations can be performed directly in the advertising machine without transmitting data to a remote server or storing video data. Data analysis and processing can be completed instantly. Compared with traditional cloud computing architecture, the use of edge computing device jetson tx2 improves response speed and reduces data transmission delay. In addition, edge computing device jetson tx2 helps reduce network burden and has flexibility and scalability. It can be customized and configured according to actual needs so that the advertising machine can adapt to different application scenarios.

[0019] In the waiting area of ​​the hospital outpatient department, the advertising machine infers the content that the patient may be interested in based on the patient's age and gender, and displays related advertisements; in the dermatology clinic, daily skin care and precautions after treatment are displayed; after the doctor in the clinic makes a diagnosis for the patient, the advertising machine in the passage area of ​​the exit room can collect the patient's relevant expressions and analyze and store them; the area for picking up reports in the physical examination center is the area where the patient's expression changes most obviously, so relevant content about common diseases and chronic diseases is displayed in a targeted manner; in the patient's family waiting area outside the operating room, advertising content and guidance related to postoperative care, rehabilitation training, etc. are played, and data such as the expressions of a large number of viewers can be obtained.

[0020] The advertising provider and the hospital have reached an agreement through in-depth cooperation. The hospital signs a letter of authorization with the patient when managing the patient's course of disease, allowing the hospital to recommend products that are beneficial to the patient's health and recovery under the premise of legality and compliance. In the pediatric department, the advertising machine plays advertisements for children's products, and in the geriatric department, the advertising machine plays advertisements for products for the elderly. The collected traffic data is interacted with the hospital's business data, and personalized marketing plans and scripts are generated through a large language model. Information is pushed to patients and their families through the contact information reserved in the hospital, greatly improving the transaction probability of the product.

[0021] Through a customized outbound calling system, we ensure that all stored and transmitted data is encrypted and has strict access control policies in real time, effectively preventing data leakage.

[0022] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An advertising machine system, characterized in that: include: Facilities layer: servers, display screens, and network equipment; Data layer: collects past crowd flow data, facial expressions, eye movement data, and retinal data when the advertisement is played through high-definition cameras, and sends the collected past crowd flow data to the platform layer; Platform layer: background management module, data center module and data analysis and mining module; The data center module includes a traffic data storage center, an advertising data storage center, and a business data storage center; The data analysis and mining module uses edge computing devices to perform real-time analysis on the captured data, calculates the flow of people, whether they watch ads, the length of time they watch ads, the changes in facial expressions after watching ads, the age and gender of viewers, and the proportion of people who watch ads to the past flow of people, and sends all the data to the traffic data storage center for storage; The data analysis and mining module analyzes the viewers' attention to the currently playing advertisement, determines whether the attention reaches the preset value, and generates tags for the viewers' age, gender and corresponding advertisements whose attention reaches the preset value and sends them to the traffic data storage center; The collected data is mapped with the advertising data to evaluate the advertising effect, and then personalized marketing strategies are formulated based on the evaluation results, and the personalized marketing strategies are sent to the service layer; Service layer: The personalized marketing strategies received from the platform layer are pushed to the user layer by selecting relevant advertisements to achieve personalized reach; User layer: includes PC and mobile terminals.

2. The advertising machine system according to claim 1, characterized in that: The rule for collecting the passing pedestrian flow data is: determine the distance between the passing pedestrians and the advertising machine, preset a maximum distance threshold, and take the size of the advertising machine display screen and the distance from the human eye as the standard.

3. An advertising machine system according to claim 1, characterized in that The rule for generating the label is: through the collected face image, if the face direction and the plane angle of the advertising machine display screen are within 45 degrees and the eyes stay on the advertising machine display screen for more than 5 seconds, it is judged that the viewer's attention to the currently playing advertisement has reached the preset attention value.

4. The advertising machine system according to claim 1, characterized in that: If the proportion of people who watch the advertisement to the past flow of people is less than a preset threshold, it is determined that the currently playing advertisement is not effective, and the currently playing advertisement content is replaced.

5. The advertising machine system according to claim 1, characterized in that: The edge design device uses jetsontx2.

6. The advertising machine system according to claim 1, characterized in that: Evaluating the effectiveness of advertising includes: In the same application scenario, set two different versions of advertising content, A and B; Play two different versions of advertising content, A and B, respectively through the advertising machine backend management module at the same time; Based on the collected data, it is evaluated that versions A and B are more effective; The better performing version of the ad will automatically play.

7. The advertising machine system according to claim 1, characterized in that: The data analysis and mining platform formulates personalized marketing strategies and words based on the collected data and merchant business data through a large language model.

8. The advertising machine system according to claim 1, characterized in that: The backend management module also includes hardware management and marketing management; marketing management sets up a customized outbound calling system.

9. An advertising machine device, characterized in that: It includes an advertising machine system as described in claims 1-7.

Images