CN113177808A - Advertisement recommendation system and method based on visual algorithm - Google Patents
Advertisement recommendation system and method based on visual algorithm Download PDFInfo
- Publication number
- CN113177808A CN113177808A CN202110560530.1A CN202110560530A CN113177808A CN 113177808 A CN113177808 A CN 113177808A CN 202110560530 A CN202110560530 A CN 202110560530A CN 113177808 A CN113177808 A CN 113177808A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- terminal
- data processing
- person
- information
- 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
- 230000000007 visual effect Effects 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 title claims description 16
- 238000004891 communication Methods 0.000 claims abstract description 4
- 238000001514 detection method Methods 0.000 claims description 24
- 239000013598 vector Substances 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 4
- 230000036541 health Effects 0.000 claims description 3
- 239000004973 liquid crystal related substance Substances 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004297 night vision Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- 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
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/436—Interfacing a local distribution network, e.g. communicating with another STB or one or more peripheral devices inside the home
- H04N21/4363—Adapting the video or multiplex stream to a specific local network, e.g. a IEEE 1394 or Bluetooth® network
- H04N21/43637—Adapting the video or multiplex stream to a specific local network, e.g. a IEEE 1394 or Bluetooth® network involving a wireless protocol, e.g. Bluetooth, RF or wireless LAN [IEEE 802.11]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/81—Monomedia components thereof
- H04N21/812—Monomedia components thereof involving advertisement data
Abstract
The invention discloses an advertisement recommendation system based on a visual algorithm, which comprises: the data processing terminal is connected with the advertisement uploading terminal through a network, the advertisement putting terminal is connected with the data processing terminal through a network connection device, the people information collecting terminal is connected with the advertisement putting terminal in a communication mode, the people information collecting terminal uploads collected people information to the data processing terminal through the advertisement putting terminal, the data processing terminal can store and analyze the advertisements uploaded by the advertisement uploading terminal, the people information collected by the information collecting terminal and uploaded by a user through mobile phone application program registration, and the data processing terminal sends the people information and matched advertisements to the advertisement putting terminal to be stored and played. When the network connection equipment normally operates, the people information can be collected through the people information collection terminal and uploaded to the data processing terminal to be analyzed, and then advertisements matched with the people information are launched, and when the network connection equipment cannot normally operate, the advertisements can be automatically played by the advertisement launching terminal.
Description
The technical field is as follows:
the invention relates to the field of advertisement recommendation, in particular to an advertisement recommendation system and method based on a visual algorithm.
Background art:
the purpose of the advertisement is to draw attention, call people's demand for the commodity, guide the customer to know the commodity in the process of invisibility, and induce consumption behavior.
Typically, television advertisements are produced by specialized advertising companies and then purchased for airtime to a television station. The television becomes an important part in daily life of people due to strong transmission and influence of the television, and is an important way for people to know information and enjoy entertainment. However, the traditional television advertisement has the disadvantages of low targeting, high cost, short service cycle, difficulty in estimating the distribution amount, waste of a large part of the traditional television advertisement, incapability of enabling required people to know, low economic return rate and difficulty in achieving the expected effect.
The outdoor or indoor plane printing advertisement shows the product information through static pictures and characters, the expression form is single, and the impact force on customers is weaker than that of television advertisement; compared with television advertisement, the method has the advantages of relatively low manufacturing cost, low target of delivery and short service cycle.
Above two kinds of traditional schemes, it is not strong to have the target nature of putting, and life cycle is short, is difficult to accomplish to put in the advertisement to different crowds.
Disclosure of Invention
The invention provides an advertisement recommendation system based on a visual algorithm, which aims to enable advertisements to be delivered to different crowds when the advertisements are delivered and solve the problems that the advertisement delivery is blindness and the economic return rate caused by the advertisements in the prior art is low, and comprises the following schemes:
a visual algorithm based advertisement recommendation system, the system comprising: the system comprises a data processing terminal connected with an advertisement uploading terminal through a network, an advertisement putting terminal connected with the data processing terminal through a network connection device, and a human information collecting terminal in communication connection with the advertisement putting terminal, wherein the human information collecting terminal uploads collected human information to the data processing terminal through the advertisement putting terminal, the data processing terminal can store and analyze the advertisement uploaded by the advertisement uploading terminal, the human information collected by the information collecting terminal and uploaded by a user through a mobile phone application program, the data processing terminal sends the human information and matched advertisements to the advertisement putting terminal for storage and playing, under the condition that the network connection device cannot normally operate, the human information collecting terminal sends the collected human information to the advertisement putting terminal to activate a Bluetooth detection module arranged in the advertisement putting terminal, and the Bluetooth detection module starts to detect a Bluetooth MAC address of the mobile phone when the network connection device cannot normally operate, and matching the detected mobile phone Bluetooth MAC address with a mobile phone Bluetooth MAC address stored in the advertisement putting terminal, wherein the matching is successful, and the advertisement putting terminal plays the advertisement matched with the person information corresponding to the mobile phone MAC address.
Furthermore, the advertisement uploading terminal is a cloud service manager capable of storing video, audio, text and image data, and the cloud service manager can monitor the working state of the advertisement delivery terminal.
Further, the information of the people registered by the user through the mobile phone application program comprises a mobile phone number, a license plate number, a vehicle type, a vehicle insurance, a gender, an age, a height, a weight, a looks, a dress, an income, an occupation, a culture level, a health condition, an interest and an authorized mobile phone Bluetooth MAC address of the user.
Further, the network connection mode is a 4G or WiFi mode wireless connection mode.
Furthermore, the data processing terminal is a comprehensive cloud computing platform capable of storing advertisements and analyst information, and the network connection device is a gateway, a wireless AP or a wireless router.
Further, the wireless AP or the wireless router is connected with a repeater.
Further, the information collected by the information collecting terminal of the person comprises sex, age, height, weight, appearance and dressing of the person, the comprehensive cloud computing platform analyzes the person information through an image recognition algorithm, the image recognition algorithm is a face detection algorithm, and the face detection algorithm is detection based on a skin color model, detection based on edge characteristics and a statistical theory method.
Further, the comprehensive cloud computing platform can determine the specific position of the advertisement delivery terminal through the ID address of the advertisement delivery terminal electrically connected with the human information acquisition terminal, so that the advertisement is sent to the advertisement delivery terminal, the advertisement delivery terminal is an advertisement machine capable of displaying videos, audios, pictures and characters, and the advertisement machine is an LED or a liquid crystal multimedia display screen.
Further, the mobile phone application program is one or more of an app, an applet, a wechat public number and an H5 webpage.
Specifically, the invention provides an advertisement recommendation method based on a visual algorithm, which comprises the following steps:
a user registers the information of the user through a mobile phone application program;
the advertisement uploading terminal uploads the recorded advertisement to the data processing terminal;
the data processing terminal analyzes and matches the human information and the advertisements and then sends the human information and the matched advertisements to the advertisement putting terminal through the network connection equipment;
when the network connection equipment operates normally, the human information acquisition terminal uploads the acquired human information to the data processing terminal through the network connection equipment, and the data processing terminal analyzes the human information to find out advertisements matched with the human information characteristics and sends the advertisements to the advertisement delivery terminal connected with the network connection equipment through a network for playing;
when the network connection equipment can not normally operate, the advertisement delivery terminal receives the personal information transmitted by the personal information acquisition terminal electrically connected with the advertisement delivery terminal, then the Bluetooth detection module arranged in the advertisement delivery terminal is started, and when the mobile phone Bluetooth MAC address detected by the Bluetooth detection module is the same as the mobile phone Bluetooth MAC address stored in the advertisement delivery terminal, the advertisement delivery terminal automatically plays the advertisement matched with the mobile phone user.
Further, the numberAccording to the processing terminal, the gender, age, height, weight, appearance and dressing characteristics of the person are extracted through an image recognition algorithm for advertisement matching, and the matching algorithm for transmitting the matched advertisement to the advertisement putting terminal for playing specifically comprises the following steps: p is a radical ofjN-dimensional feature vector of advertisement or person, n is number of labels, each dimension in the vector represents a label tiAt pjWeight w (i, j), number of tags n, and tag t in (1)iThe label weights w (i, j) are customized by the advertiser,
then p can be substitutedjIs represented by pjIf P (1, j), w (2, j)1And P2The feature labels of the advertisement and the person are respectively, and the feature vectors of the advertisement and the person are respectively V (p)1) And V (p)2) The matching degree between the advertisement and the person is Sim (p)1，p2)，
Sim(p1，p2) The larger the numerical value is, the higher the matching degree between the advertisement and the person is, the advertisement with the highest matching degree is preferentially recommended and issued to the data source advertisement delivery terminal, the camera takes pictures regularly and uploads the pictures, the cloud platform continues to analyze the behavior of the person, and the labels are extracted for the behavior (the behavior labels are mainly interested and not interested, if the person is i, the advertisement is j, pijFor the behavior tag, if the camera shoots people to directly view the advertisement delivery terminal, pij1, the advertisement is interested in the person, if the camera does not shoot the person directly watching the advertisement delivery terminal, pij0, representing that the person is not interested in the advertisement), and recording the information in the database, and after the person leaves the person information acquisition terminal and collects the person information area, the advertisement delivery terminal counts down for 15 seconds to enter a dormant state, and the advertisement delivery process is completed once.
The invention has the beneficial effects that: 1. when the network connection equipment normally operates, the human information acquisition terminal can acquire human information and upload the human information to the data processing terminal through the advertisement putting terminal, and the advertisement putting terminal analyzes the human information and sends advertisements matched with the human information to the advertisement putting terminal for playing; 2. when the network connection equipment cannot normally run, the data processing terminal sends the person information and the matched advertisement to the advertisement putting terminal for storage, and at the moment, the Bluetooth detector arranged in the advertisement putting terminal finds the advertisement matched with the person information of the registered Bluetooth MAC address of the mobile phone by scanning the Bluetooth MAC address of the mobile phone, and directly puts the advertisement.
Drawings
In order to more clearly illustrate the technical solution in the present embodiment, the following will briefly describe the embodiments or drawings required to be used in the prior art, and obviously, the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of a visual algorithm-based advertisement recommendation system;
FIG. 2 is a schematic diagram of an operation structure of an advertisement recommendation system based on a visual algorithm when a network is disconnected;
FIG. 3 is a flowchart illustrating normal operation of a network connection device in an advertisement recommendation method based on a visual algorithm;
FIG. 4 is a flowchart of a method for recommending advertisements based on a visual algorithm when a network is disconnected.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1: a visual algorithm based advertisement recommendation system, the system comprising: the data processing terminal is connected with the advertisement uploading terminal through a network, the advertisement putting terminal is connected with the data processing terminal through a network connection device, the people information collecting terminal is connected with the advertisement putting terminal in a communication mode, the people information collecting terminal uploads collected people information to the data processing terminal through the advertisement putting terminal, the data processing terminal can store and analyze the advertisements uploaded by the advertisement uploading terminal, the people information collected by the information collecting terminal and uploaded by a user through mobile phone application program registration, and the data processing terminal sends the people information and matched advertisements to the advertisement putting terminal to be stored and played.
The advertisement uploading terminal is a cloud service manager capable of storing video, audio, text and image data, and the cloud service manager can monitor the working state of the advertisement putting terminal.
The information of the user registered by the mobile phone application program comprises a mobile phone number, a license plate number, a vehicle type, a vehicle insurance, a sex, an age, a height, a weight, a looks, a dress, an income, an occupation, a culture level, a health condition, an interest and an authorized mobile phone Bluetooth MAC address of the user.
As shown in fig. 2: the advertisement putting terminal is internally provided with a Bluetooth detection module which is used for detecting a mobile phone Bluetooth MAC address authorized by a user when the network connection equipment cannot normally operate.
Under the condition that the network connection equipment cannot normally operate, the human information acquisition terminal transmits acquired human information to the advertisement delivery terminal, a Bluetooth detection module arranged in the advertisement delivery terminal is activated, started and started, the detected mobile phone Bluetooth MAC address is matched with a mobile phone Bluetooth MAC address stored in the advertisement delivery terminal, the matching is successful, and the advertisement delivery terminal plays an advertisement matched with the human information corresponding to the mobile phone MAC address.
When no person is in the person information collecting range of the person information collecting terminal, a standby instruction is sent to the advertisement putting terminal, the screen of the advertisement putting terminal is closed to be in a standby low-power-consumption state, when a person is in the person, a starting instruction is sent to the advertisement putting terminal, and the advertisement putting terminal is started to play advertisements.
The human information acquisition terminal is a camera with more than 300 ten thousand pixels, and the camera has the functions of automatic exposure, automatic balance, automatic light stripe elimination, automatic black level calibration, automatic band-pass filtering, infrared camera shooting and night vision.
The network connection mode is a 4G or WiFi mode wireless connection mode.
The data processing terminal is a comprehensive cloud computing platform capable of storing advertisements and analyst information, and the network connection equipment is a gateway, a wireless AP or a wireless router.
The wireless AP or the wireless router is connected with the repeater.
The information collected by the information collecting terminal comprises sex, age, height, weight, appearance and dressing of a person, the comprehensive cloud computing platform analyzes the person information through an image recognition algorithm, the image recognition algorithm is a face detection algorithm, and the face detection algorithm is detection based on a skin color model, detection based on edge characteristics and a statistical theory method.
The data processing terminal extracts the sex, age, height, weight, looks and dressing characteristics of a person through an image recognition algorithm to match advertisements, and the matching algorithm for transmitting the matched advertisements to the advertisement delivery terminal to be played specifically comprises pjN-dimensional feature vector of advertisement or person, n is number of labels, each dimension in the vector represents a label tiAt pjWeight w (i, j), number of tags n, and tag t in (1)iThe label weights w (i, j) are customized by the advertiser,
then p can be substitutedjIs represented by pjIf P (1, j), w (2, j)1And P2The feature labels of the advertisement and the person are respectively, and the feature vectors of the advertisement and the person are respectively V (p)1) And V (p)2) The matching degree between the advertisement and the person is Sim (p)1，p2)，
Sim(p1，p2) The larger the numerical value is, the higher the matching degree between the advertisement and the person is, the advertisement with the highest matching degree is preferentially recommended and issued to the data source advertisement delivery terminal, the camera shoots regularly and uploads the advertisement during the period, and the cloud platform continues to analyze the personBehavior of (2) extracting tags for its behavior (behavior tags are mainly interesting and disintergent, if man is i, advertisement is j, pijFor the behavior tag, if the camera shoots people to directly view the advertisement delivery terminal, pij1, the advertisement is interested in the person, if the camera does not shoot the person directly watching the advertisement delivery terminal, pij0, representing that the person is not interested in the advertisement), and recording the information in the database, and after the person leaves the person information acquisition terminal and collects the person information area, the advertisement delivery terminal counts down for 15 seconds to enter a dormant state, and the advertisement delivery process is completed once.
The comprehensive cloud computing platform can determine the specific position of the advertisement delivery terminal through the ID address of the advertisement delivery terminal electrically connected with the human information acquisition terminal, so that the advertisement is sent to the advertisement delivery terminal, the advertisement delivery terminal is an advertisement player capable of displaying videos, audios, pictures and characters, and the advertisement player is an LED or liquid crystal multimedia display screen.
The mobile phone application program is one or more of an app, an applet, a WeChat public number and an H5 webpage.
As shown in fig. 3 and 4: the working principle of the invention is as follows:
a user registers the information of the user through a mobile phone application program;
the advertisement uploading terminal uploads the recorded advertisement to the data processing terminal;
the data processing terminal analyzes and matches the human information and the advertisements and then sends the human information and the matched advertisements to the advertisement putting terminal through the network connection equipment;
when the network connection equipment operates normally, the human information acquisition terminal uploads the acquired human information to the data processing terminal through the network connection equipment, and the data processing terminal analyzes the human information to find out advertisements matched with the human information characteristics and sends the advertisements to the advertisement delivery terminal connected with the network connection equipment through a network for playing;
when the network connection equipment can not normally operate, the advertisement delivery terminal receives the personal information transmitted by the personal information acquisition terminal electrically connected with the advertisement delivery terminal, then the Bluetooth detection module arranged in the advertisement delivery terminal is started, and when the mobile phone Bluetooth MAC address detected by the Bluetooth detection module is the same as the mobile phone Bluetooth MAC address stored in the advertisement delivery terminal, the advertisement delivery terminal automatically plays the advertisement matched with the mobile phone user.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (11)
1. An advertisement recommendation system based on a visual algorithm, the system comprising: the system comprises a data processing terminal connected with an advertisement uploading terminal through a network, an advertisement putting terminal connected with the data processing terminal through a network connection device, and a human information collecting terminal in communication connection with the advertisement putting terminal, wherein the human information collecting terminal uploads collected human information to the data processing terminal through the advertisement putting terminal, the data processing terminal can store and analyze the advertisement uploaded by the advertisement uploading terminal, the human information collected by the information collecting terminal and uploaded by a user through a mobile phone application program, the data processing terminal sends the human information and matched advertisements to the advertisement putting terminal for storage and playing, under the condition that the network connection device cannot normally operate, the human information collecting terminal sends the collected human information to the advertisement putting terminal to activate a Bluetooth detection module arranged in the advertisement putting terminal, and the Bluetooth detection module starts to detect a Bluetooth MAC address of the mobile phone when the network connection device cannot normally operate, and matching the detected mobile phone Bluetooth MAC address with a mobile phone Bluetooth MAC address stored in the advertisement putting terminal, wherein the matching is successful, and the advertisement putting terminal plays the advertisement matched with the person information corresponding to the mobile phone MAC address.
2. The advertisement recommendation system based on the visual algorithm is characterized in that the advertisement uploading terminal is a cloud service manager capable of storing video, audio, text and image data, and the cloud service manager can monitor the working state of the advertisement delivery terminal.
3. The advertisement recommendation system based on visual algorithm as claimed in claim 1, wherein the people information registered by the user through the mobile phone application program comprises mobile phone number, license plate number, vehicle type, vehicle insurance, gender, age, height, weight, appearance, dressing, income, occupation, culture level, health condition, hobbies and user authorized mobile phone Bluetooth MAC address.
4. A visual algorithm based advertisement recommendation system according to claim 1, characterized in that: the network connection mode is a 4G or WiFi mode wireless connection mode.
5. A visual algorithm based advertisement recommendation system according to claim 1, characterized in that: the data processing terminal is a comprehensive cloud computing platform capable of storing advertisements and analyst information, and the network connection equipment is a gateway, a wireless AP or a wireless router.
6. A visual algorithm based advertisement recommendation system according to claim 5, characterized in that: the wireless AP or the wireless router is connected with the repeater.
7. A visual algorithm based advertisement recommendation system according to claim 5, characterized in that: the information collected by the human information collecting terminal comprises sex, age, height, weight, appearance and dressing of a human, the comprehensive cloud computing platform analyzes human information through an image recognition algorithm, the image recognition algorithm is a human face detection algorithm, and the human face detection algorithm is detection based on a skin color model, detection based on edge characteristics and a statistical theory method.
8. A visual algorithm based advertisement recommendation system according to claim 7, characterized in that: the comprehensive cloud computing platform can determine the specific position of the advertisement delivery terminal through the ID address of the advertisement delivery terminal electrically connected with the human information acquisition terminal, so that the advertisement is sent to the advertisement delivery terminal, the advertisement delivery terminal is an advertisement player capable of displaying videos, audios, pictures and characters, and the advertisement player is an LED or liquid crystal multimedia display screen.
9. A visual algorithm based advertisement recommendation system according to any one of claims 1 to 8, characterized in that: the mobile phone application program is one or more of an app, an applet, a WeChat public number and an H5 webpage.
10. An advertisement recommendation method based on a visual algorithm is characterized by comprising the following steps:
s1: a user registers the information of the user through a mobile phone application program;
s2: the advertisement uploading terminal uploads the recorded advertisement to the data processing terminal;
s3: the data processing terminal analyzes and matches the human information and the advertisements and then sends the human information and the matched advertisements to the advertisement putting terminal through the network connection equipment;
s4: when the network connection equipment operates normally, the human information acquisition terminal uploads the acquired human information to the data processing terminal through the network connection equipment, and the data processing terminal analyzes the human information to find out advertisements matched with the human information characteristics and sends the advertisements to the advertisement delivery terminal connected with the network connection equipment through a network for playing;
s5: when the network connection equipment can not normally operate, the advertisement delivery terminal receives the personal information transmitted by the personal information acquisition terminal electrically connected with the advertisement delivery terminal, then the Bluetooth detection module arranged in the advertisement delivery terminal is started, and when the mobile phone Bluetooth MAC address detected by the Bluetooth detection module is the same as the mobile phone Bluetooth MAC address stored in the advertisement delivery terminal, the advertisement delivery terminal automatically plays the advertisement matched with the mobile phone user.
11. A visual algorithm based advertisement recommendation method according to claim 10, characterized in that: the data processing terminal recognizes through the imageThe matching algorithm for extracting gender, age, height, weight, looks and dressing characteristics of people by using the discrimination algorithm to match advertisements and transmitting the matched advertisements to the advertisement putting terminal to be played specifically comprises the following steps of pjN-dimensional feature vector of advertisement or person, n is number of labels, each dimension in the vector represents a label tiAt pjWeight w (i, j), number of tags n, and tag t in (1)iThe label weights w (i, j) are customized by the advertiser,
then p can be substitutedjIs represented by pjIf P (1, j), w (2, j)1And P2The feature labels of the advertisement and the person are respectively, and the feature vectors of the advertisement and the person are respectively V (p)1) And V (p)2) The matching degree between the advertisement and the person is Sim (p)1，p2)，
Sim(p1，p2) The larger the numerical value is, the higher the matching degree between the advertisement and the person is, the advertisement with the highest matching degree is preferentially recommended and issued to the data source advertisement delivery terminal, the camera takes pictures regularly and uploads the pictures, the cloud platform continues to analyze the behavior of the person, and the labels are extracted for the behavior (the behavior labels are mainly interested and not interested, if the person is i, the advertisement is j, pijFor the behavior tag, if the camera shoots people to directly view the advertisement delivery terminal, pij1, the advertisement is interested in the person, if the camera does not shoot the person directly watching the advertisement delivery terminal, pij0, representing that the person is not interested in the advertisement), and recording the information in the database, and after the person leaves the person information acquisition terminal and collects the person information area, the advertisement delivery terminal counts down for 15 seconds to enter a dormant state, and the advertisement delivery process is completed once.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110560530.1A CN113177808A (en) | 2021-05-21 | 2021-05-21 | Advertisement recommendation system and method based on visual algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110560530.1A CN113177808A (en) | 2021-05-21 | 2021-05-21 | Advertisement recommendation system and method based on visual algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113177808A true CN113177808A (en) | 2021-07-27 |
Family
ID=76929625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110560530.1A Pending CN113177808A (en) | 2021-05-21 | 2021-05-21 | Advertisement recommendation system and method based on visual algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113177808A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160063558A1 (en) * | 2013-04-02 | 2016-03-03 | Gwon Young KIM | Short distance user recognition system, and method for providing information using same |
| CN106408323A (en) * | 2016-08-29 | 2017-02-15 | 山东易牌网络科技有限公司 | Electronic advertisement management system and method |
| CN108011946A (en) * | 2017-11-30 | 2018-05-08 | 浙江小屏信息技术有限公司 | Intelligently pushing method and device based on bluetooth |
| CN108805629A (en) * | 2018-06-20 | 2018-11-13 | 深圳市玛威尔显控科技有限公司 | It is a kind of that surrounding population information content playback method is identified using WiFi probes based on big data |
| CN109033172A (en) * | 2018-06-21 | 2018-12-18 | 西安理工大学 | A kind of image search method of deep learning and approximate target positioning |
| 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 |
| CN110263603A (en) * | 2018-05-14 | 2019-09-20 | 桂林远望智能通信科技有限公司 | Face identification method and device based on center loss and residual error visual simulation network |
| CN110413096A (en) * | 2019-08-02 | 2019-11-05 | 梁彩连 | A kind of advertisement intelligent display system based on big data |
| EP3748564A1 (en) * | 2018-01-30 | 2020-12-09 | Malogic Holdings Limited | Offline interactive advertisement system |
-
2021
- 2021-05-21 CN CN202110560530.1A patent/CN113177808A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160063558A1 (en) * | 2013-04-02 | 2016-03-03 | Gwon Young KIM | Short distance user recognition system, and method for providing information using same |
| CN106408323A (en) * | 2016-08-29 | 2017-02-15 | 山东易牌网络科技有限公司 | Electronic advertisement management system and method |
| CN108011946A (en) * | 2017-11-30 | 2018-05-08 | 浙江小屏信息技术有限公司 | Intelligently pushing method and device based on bluetooth |
| EP3748564A1 (en) * | 2018-01-30 | 2020-12-09 | Malogic Holdings Limited | Offline interactive advertisement system |
| CN110263603A (en) * | 2018-05-14 | 2019-09-20 | 桂林远望智能通信科技有限公司 | Face identification method and device based on center loss and residual error visual simulation network |
| CN108805629A (en) * | 2018-06-20 | 2018-11-13 | 深圳市玛威尔显控科技有限公司 | It is a kind of that surrounding population information content playback method is identified using WiFi probes based on big data |
| CN109033172A (en) * | 2018-06-21 | 2018-12-18 | 西安理工大学 | A kind of image search method of deep learning and approximate target positioning |
| 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 |
| CN110413096A (en) * | 2019-08-02 | 2019-11-05 | 梁彩连 | A kind of advertisement intelligent display system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108234591B (en) | Content data recommendation method and device based on identity authentication device and storage medium | |
| US10592929B2 (en) | Systems and methods for delivering content | |
| US7921036B1 (en) | Method and system for dynamically targeting content based on automatic demographics and behavior analysis | |
| WO2019149005A1 (en) | Offline interactive advertisement system | |
| CN104598869A (en) | Intelligent advertisement pushing method based on human face recognition device | |
| CN107705432A (en) | A kind of system of automatic vending machine, the method for information displaying and information displaying | |
| US20100253778A1 (en) | Media displaying system and method | |
| CN106557937B (en) | Advertisement pushing method and device | |
| US20120140069A1 (en) | Systems and methods for gathering viewership statistics and providing viewer-driven mass media content | |
| US20150088637A1 (en) | Information processing system, information processing method, and non-transitory computer readable storage medium | |
| CN104575339A (en) | Media information pushing method based on face detection interface | |
| CN108495153B (en) | Multimedia content pushing method, device and system | |
| US20200320576A1 (en) | Targeted Advertising Based On Demographic Features Extracted From Persons | |
| CN108898443B (en) | Data acquisition and processing method applied to unmanned vending house system | |
| JP6498900B2 (en) | Advertisement evaluation system, advertisement evaluation method | |
| CN104112209A (en) | Audience statistical method of display terminal, and audience statistical system of display terminal | |
| CN113674037A (en) | Data acquisition and recommendation method based on shopping behaviors | |
| CN110889719A (en) | Advertisement pushing system and method based on user consumption characteristics | |
| CN110942321A (en) | Advertisement accurate delivery method and system based on face recognition | |
| CN110969480A (en) | Multimedia backpack advertising information playing control method and device | |
| US20130018735A1 (en) | System and Method for interaction specific advertising media distribution | |
| CN111724199A (en) | Intelligent community advertisement accurate delivery method and device based on pedestrian active perception | |
| CN113850627A (en) | Elevator advertisement display method and device and electronic equipment | |
| CN109767262B (en) | Three-dimensional facial expression recognition scoring evaluation method for advertising screen | |
| CN112163880A (en) | Intelligent advertisement putting method and system based on image processing |
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 |