CN115034817A - Advertisement recommendation method and device based on big data - Google Patents

Abstract

The invention relates to the technical field of advertisement screen cutting, and relates to an advertisement recommendation method and device based on big data. The method includes: acquiring the information of persons in the current elevator; confirming the information of the households in the elevator through a preset building household relationship table; When it stops, when people are moving in and out, predict the distribution of people in the elevator after people enter and leave, and switch the content of the LCD advertising screen when people are flowing; switch according to the screen in the elevator that is paying attention to the LCD advertising screen. The playing audio of the LCD advertising screen. By means of the present invention, by prioritizing objects and dividing the screen according to the families of most people in the elevator, the economical utilization of the LCD advertising screen is improved, and the audio signal of the LCD advertising screen can be obtained in combination with the face recognition of the LCD advertising screen. Make the elevator LCD advertising screen more intelligent.

Description

A method and device for advertising recommendation based on big data

【Technical field】

The invention relates to the technical field of advertisement screen cutting, and relates to an advertisement recommendation method and device based on big data.

【Background technique】

At present, with the development of society and the penetration of advertising into people's lives, advertising has become an auxiliary driving force for people's consumption, especially elevator advertising has become the main place for advertising in recent years, but the split-screen processing design of LCD advertising screen is still perfect. And there is room for improvement. Through the maturity of face recognition technology, it is possible to determine the consumption demand information and trend classification of people based on the analysis of specific character information, and to target and screen advertising information to improve the efficiency of advertising in elevators.

[Content of the invention]

The purpose of the present invention is to solve the above-mentioned problems, and propose a method and device for recommending advertisements based on big data.

The technical solution is as follows:

A method for recommending advertisements based on big data, comprising:

Get the information of people in the current elevator;

Confirm the family information in the elevator through the preset building resident relationship table;

Determine the current number of households in the elevator, and split the screen according to the number of households;

When the elevator stops on a certain floor and people flow in and out, predict the distribution of people in the elevator after people enter and leave, and switch the content of the LCD advertising screen when people flow;

The playing audio of the liquid crystal advertisement screen is switched according to the attention situation of the image of the liquid crystal advertisement screen in the elevator.

Preferably, the obtaining of the current personnel information in the elevator includes: the personnel information includes the personnel identity, the number of passengers in the elevator, the current elevator carrying weight and the target floor that the elevator personnel want to go to;

Preferably, the method for acquiring the number of passengers in the elevator and the target floor that the people in the elevator want to go to and the identity of the personnel includes: installing cameras (1, 2, 3, 4) in the elevator at the four upper corners of the elevator, to detect Collect the face information of the people in the elevator; transmit the collected face information to the data processing center;

A database is established in the data processing center, and the building resident information, including the face images of the household members and the information of the floor where they live, are entered into the database;

Using face recognition technology, identify the face information collected by the cameras (1, 2, 3, 4), analyze the face information, and determine the number of passengers in the elevator and the places where the people in the elevator want to go. the target floor and the identity of the persons mentioned;

The identity of the person is the person's name id;

The identification of the floor to which the people in the elevator go is provided by the building occupant information, and the floor to which the people in the elevator go is determined through the living floor of each person in the building occupants.

Preferably, the determining the current number of households in the elevator, and performing advertisement split screen according to the number of households, including:

Using the method of step s13, the cameras (1, 2, 3, 4) in the elevator are used to identify the people in the elevator, analyze the family information in the elevator, and take the number of family members in the elevator captured by the camera as the priority object. Sorting, the family with the most members in the elevator is the first priority object, the second priority object is the second priority object, and there are 4 priority objects in total; the first priority object plays advertisements on a single LCD advertising screen (10), and the second priority object is displayed on the LCD advertising screen. A half screen of the screen (11) plays advertisements, and the third priority object and the fourth priority object play advertisements on a quarter screen of the liquid crystal advertising screen (11).

Preferably, when the elevator stops on a certain floor and people flow in and out, predict the distribution of people in the elevator after the people come in and out, and switch the content of the LCD advertising screen when the people flow, including: An elevator door camera (15) is installed on the top of the elevator door (14), which is connected to the data processing center, and the data processing center uses the face recognition technology to identify the personnel waiting for the elevator; according to the method of step s12, confirm the current The target floor to which the people in the elevator are going; when the elevator opens the door, the data processing center analyzes and selects the information of the people waiting outside the elevator door (14) and the people in the elevator who have not yet reached the destination floor, and rewrites the information in combination with the methods of steps s21-s22. The advertisements corresponding to the family hobbies included in the family information in the elevator are acquired, and the terminal device sends the advertisements to the LCD advertisement screens (10, 11) in the elevator through wireless communication, and performs split-screen advertisement playback according to the priority rule in step s21.

Preferably, switching the playing audio of the LCD advertising screen according to the attention situation of the LCD advertising screen in the elevator, including: arranging a camera in the LCD advertising screen (10, 11), and combining the eye movement attention point recognition technology to detect Attention is paid to the picture of the LCD advertising screen (10, 11) in the elevator;

The playing sound of the liquid crystal advertisement screen (10, 11) is switched according to the attention situation.

Preferably, switching the playing sound of the LCD advertising screen (10, 11) according to the attention situation includes: respectively installing a LCD advertising screen camera (12, 13) above the LCD advertising screen (10, 11) in the elevator ), connected with the data processing center, for acquiring images and performing face recognition; the initial state of the LCD advertising screen (10, 11) is that the audio has no signal output; when the LCD advertising screen camera (12, 13) captures the When there is a human face, the following information is acquired according to the method of step s41, and the split-screen advertisement with the largest number of followers is obtained, and the liquid crystal advertisement screen (10, 11) plays the advertisement audio of the split-screen advertisement with the most number of followers.

The beneficial effects of the present invention are: by combining the face recognition technology with the personnel information database of the data processing center, the identity information of the elevator personnel can be confirmed simply and efficiently, and the advertisement type requirements of the personnel in the elevator can be accurately identified through the hobby information of the family information database. , can achieve targeted output of advertisements to the crowd, through priority object sorting, split screen according to the family of most people in the elevator, improve the economical use of LCD advertising screen, combined with face recognition of LCD advertising screen, to obtain The audio signal of the LCD advertising screen makes the elevator LCD advertising screen more intelligent.

【Description of drawings】

1 is a schematic flowchart of a method and device for advertising recommendation based on big data in the implementation of the invention;

2 is a schematic diagram of the internal layout of an elevator according to a method and device for advertising recommendation based on big data in the implementation of the invention;

3 is a schematic diagram of the external layout of an elevator according to a method and device for advertising recommendation based on big data in the implementation of the invention;

4 is a schematic diagram of a method and apparatus for recommending advertisements based on big data in the implementation of the invention;

Among them, 1, 2, 3, 4. Camera in elevator; 5. Infrared thermal sensor; 6, 7, 8, 9. Pressure sensor; 10, 11. LCD advertising screen; 12, 13. LCD advertising screen camera; 14. Elevator door; 15. Camera outside the elevator door; 16. Display screen in the outer hall; 17. Side wall of the elevator door.

【Detailed ways】

In order to make the technical problems solved by the present invention, the technical solutions adopted and the technical effects achieved more clearly, the technical solutions of the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings. Obviously, the described embodiments are only the present invention. some examples, but not all examples. Based on the embodiments of the present invention, the embodiments obtained by those skilled in the art without creative work all belong to the protection scope of the present invention.

S1: Obtain personnel information in the elevator through face recognition technology, pressure sensors (6, 7, 8, 9), and infrared thermal imaging technology. The personnel information includes personnel identity, the number of passengers in the elevator, the current elevator weight and The target floor that people in the elevator want to go to.

S11: The current method for obtaining the bearing weight of the elevator, including: evenly installing four pressure sensors (6, 7, 8, 9) on the floor in the elevator, the purpose is to measure the bearing weight in the elevator, because the floor area of the elevator is too large , in order to improve the accuracy of the measurement and reduce the measurement error, 4 are installed, and the values measured by the 4 pressure sensors (6, 7, 8, 9) are sent back to the data processing center.

S12: The method for obtaining the number of passengers in the elevator, the target floor to which each person goes, and the identity of the person, including: installing cameras (1, 2, 3, and 4) in the elevator at the four upper corners of the elevator, and monitoring the inside of the elevator. Collect the face information of the personnel; transmit the collected face information to the data processing center;

A database is established in the data processing center, and the building resident information, including the face images of the household members and the information of the floor where they live, are entered into the database;

Using face recognition technology, identify the face information collected by the cameras (1, 2, 3, 4), analyze the face information, and determine the number of passengers in the elevator and the places where the people in the elevator want to go. the target floor and the identity of the persons mentioned;

The identity of the person is the person's name id;

Identifying the floor that the people in the elevator want to go to is provided by the building occupant information. The floor that the people in the elevator want to go to is determined through the living floor of each person in the building occupants.

In order to deal with emergencies, such as strangers and residents going to other floors, for further accurate information, when the face recognized by the camera disappears, it is determined that the person finally goes to the floor, and the data processing center synchronizes the arrival information of the elevator personnel to the Terminal monitoring. At the same time, in order to identify the number of people more accurately, an infrared thermal sensor (5) is installed in the elevator to identify the heat map of the temperature range of the human body. It was only confirmed that people had left the elevator.

An outer hall display screen (16) is installed on the side wall (17) of the elevator entrance to display the number of passengers in the elevator and the current elevator weight data analyzed by the data processing center. The data processing center then transmits the analyzed identity information of the elevator personnel to the terminal monitoring, and the monitoring screen of the terminal monitoring can display the identity information of the passengers and the target floor they want to go to.

S13: Confirm the family information in the elevator through the preset building resident relationship table;

A building resident relationship table is established in the data processing center, and various information of the building resident is entered, including household members of the resident, family relationship of the identity of the person, face image, the floor where they live, and the family's hobbies. The identity of the person is obtained through the face recognition method in step s12, and the family information in the elevator is obtained in combination with the building resident relationship table. living floor, and the family's hobbies.

s2: Determine the current number of households in the elevator, and split the advertisement screen according to the number of households.

s21: Each of the two elevator doors (14) in the elevator is equipped with an advertising LCD screen for advertising;

Through the method of step s13, the cameras (1, 2, 3, 4) in the elevator are used to identify the people in the elevator, and the information is transmitted to the data processing center. The number of family members in the elevator is currently prioritized, and the family with the most members in the elevator is the first priority object, followed by the second priority object, and so on for a total of 4 priority objects. The first priority object uses a single LCD advertising screen (10) to display advertisements, the second priority object uses half-screen advertisements of the LCD advertising screen (11), and the third priority object and the fourth priority object display advertisements on quarters of the LCD advertising screen (11). One screen plays an advertisement.

s22: The data processing center sends the identified family hobbies and hobbies included in the elevator family information to the terminal device, and the terminal device establishes an advertisement database to match advertisements corresponding to the family hobbies and hobbies included in the elevator family information. The terminal device sends the advertisement to the liquid crystal advertisement screen (10, 11) in the elevator through wireless communication, and performs split-screen advertisement playback according to the priority rule in step s21.

s3: When the elevator stops on a certain floor and people flow in and out, predict the distribution of people in the elevator after people come in and out, and switch the content of the LCD advertising screen (10, 11) when people flow.

An elevator door camera (15) is installed above the elevator door (14), which is connected to the data processing center, and the data processing center uses face recognition technology to identify persons waiting for the elevator. According to the method of step s12, the target floor to which the people in the elevator are currently going is confirmed. When the elevator opens, the data processing center analyzes and filters the information of the people waiting outside the elevator door (14) and the people in the elevator who have not yet reached the destination floor, and re-acquires the families included in the family information in the elevator in combination with the methods of steps s21-s22. For advertisements corresponding to interests and hobbies, the terminal device sends the advertisements to the LCD advertisement screens (10, 11) in the elevator through wireless communication, and performs split-screen advertisement playback according to the priority rule in step s21.

The technical effect of this step is that the re-update of the split-screen advertisement is completed before the flow of people is completed, which improves the user experience.

s4: Switch the playing sound of the liquid crystal advertisement screen (10, 11) according to the attention situation of the image of the liquid crystal advertisement screen (10, 11) in the elevator.

s41: Set up cameras in the LCD advertising screens (10, 11), and combine the eye movement attention point recognition technology to detect the attention of the LCD advertising screen (10, 11) in the elevator, for example, through face recognition technology. The faces of the characters, only those facing the LCD advertising screen (10, 11) can recognize the human face, and it is possible to pay attention to the LCD advertising screen (10, 11). (10, 11) The picture gets attention, and the attention includes the number of people who follow each display screen of the LCD advertising screen (10, 11) and the split-screen advertisement therein;

Switching the playing sound of the LCD advertising screen (10, 11) according to the attention situation, specifically includes: respectively installing a LCD advertising screen camera (12, 13) above the elevator LCD advertising screen (10, 11), and the data The processing centers are connected to acquire images and perform face recognition. The initial state of the LCD advertising screen (10, 11) is that no audio signal is output. When the liquid crystal advertising screen cameras (12, 13) capture the human face, the following information is acquired according to the method of step s41, and the split-screen advertisement with the most attention is obtained, and the data processing center sends a signal to the terminal device, and the terminal device will wirelessly The communication sends a signal to the liquid crystal advertisement screens (10, 11), and the liquid crystal advertisement screens (10, 11) play the advertisement audio of the split-screen advertisement with the largest number of people.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention in any form. Although the present invention has been disclosed above with preferred embodiments, it is not intended to limit the present invention. Within the scope of the technical solution of the present invention, personnel can make some changes or modifications to equivalent examples of equivalent changes by using the above-mentioned technical content, but any content that does not depart from the technical solution of the present invention, according to the present invention. Any simple modifications, equivalent changes and modifications made to the above embodiments in the technical essence still fall within the scope of the solution of the present invention.

The above disclosures are only preferred embodiments of the invention, and of course, the scope of the rights of the present invention cannot be limited by this. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims (8)

1. A method for recommending advertisements based on big data, comprising: Get the information of people in the current elevator; Confirm the family information in the elevator through the preset building resident relationship table; Determine the current number of households in the elevator, and split the screen according to the number of households; When the elevator stops on a certain floor and people flow in and out, predict the distribution of people in the elevator after people enter and leave, and switch the content of the LCD advertising screen when people flow; The playing audio of the liquid crystal advertisement screen is switched according to the attention situation of the image of the liquid crystal advertisement screen in the elevator. 2 . The method for recommending advertisements based on big data according to claim 1 , wherein the obtaining the personnel information in the current elevator comprises: the personnel information includes personnel identities, the number of passengers in the elevator, the current elevator The carrying weight and the destination floor the person in the elevator wants to go to. 3. a kind of advertisement recommendation method based on big data according to claim 2 is characterized in that: the acquisition method of the target floor and personnel identity that the elevator is in the number of passengers and personnel in the elevator want to go, comprising: in the elevator The elevator cameras (1, 2, 3, 4) are installed in the 4 upper corners of the elevator to collect the face information of the people in the elevator; the collected face information is transmitted to the data processing center; A database is established in the data processing center, and the building resident information, including the face images of the household members and the information of the floor where they live, are entered into the database; Using face recognition technology, identify the face information collected by the cameras (1, 2, 3, 4), analyze the face information, and determine the number of passengers in the elevator and the places where the people in the elevator want to go. the target floor and the identity of the persons mentioned; The identity of the person is the person's name id; The identification of the floor to which the people in the elevator go is provided by the building occupant information, and the floor to which the people in the elevator go is determined through the living floor of each person in the building occupants. 4. The method for recommending advertisements based on big data according to claim 1, wherein the determining the number of households in the elevator at present, and performing advertisement split screen according to the number of households, comprising: Through the method of step s13, face recognition technology and elevator cameras (1, 2, 3, 4) are used to identify people in the elevator, analyze the family information in the elevator, and prioritize the number of family members in the elevator currently captured by the camera. The objects are sorted. The family with the most members in the elevator is the first priority object, and the second priority object is the second priority object. There are 4 priority objects in total; A half screen of the advertising screen (11) plays advertisements, and the third priority object and the fourth priority object play advertisements on a quarter screen of the liquid crystal advertising screen (11). 5. a kind of advertisement recommendation method based on big data according to claim 1, is characterized in that: When the elevator stops on a certain floor and people flow in and out, predict the distribution of people in the elevator after the people come in and out, and switch the content of the LCD advertising screen when people flow, including: in the elevator door ( 14) An elevator door camera (15) is installed on the top of the mouth, connected to the data processing center, and the data processing center uses face recognition technology to identify the personnel waiting for the elevator; According to the method of step s12, confirm the current elevator in the elevator. The target floor to which the person is going; when the elevator opens the door, the data processing center analyzes and selects the information of the people waiting outside the elevator door (14) and the people in the elevator who have not yet reached the destination floor, and re-acquires the information in combination with the methods of steps s21-s22. For the advertisements corresponding to family interests and hobbies included in the family information in the elevator, the terminal device sends the advertisements to the LCD advertisement screens (10, 11) in the elevator through wireless communication, and performs split-screen advertisement playback according to the priority rule in step s21. 6. a kind of advertisement recommendation method based on big data according to claim 1, is characterized in that: described switching the playing audio of described liquid crystal advertisement screen according to the picture of being concerned about liquid crystal advertisement screen in the elevator is paid attention to, comprising: A camera is arranged in the LCD advertising screen (10, 11), combined with eye movement attention point recognition technology, to detect the attention status of the image of the LCD advertising screen (10, 11) in the elevator; The playing sound of the liquid crystal advertisement screen (10, 11) is switched according to the attention situation. 7. The method for recommending advertisements based on big data according to claim 6, characterized in that: switching the playing sound of the liquid crystal advertisement screens (10, 11) according to the attention situation comprises: A liquid crystal advertising screen camera (12, 13) is respectively installed above the liquid crystal advertising screen (10, 11), which is connected to the data processing center and used for acquiring images and performing face recognition; the liquid crystal advertising screen (10, 11) The initial state is that there is no audio signal output; when the LCD advertising screen cameras (12, 13) capture the human face, the attention situation is obtained according to the method of step s41, and the split-screen advertisement with the most attention is obtained, the LCD advertisement Screens (10, 11) play the advertisement audio of the split-screen advertisement with the most bets. 8. A kind of advertisement recommendation device based on big data for realizing the described method of any claim 1-7, it is characterized in that: camera (1,2,3,4) is set in elevator, pressure sensor (6) , 7, 8, 9), LCD advertising screens (10, 11), cameras outside the elevator door and display screens in the outer hall are set outside the elevator.

Images