CN112163880A - Intelligent advertisement putting method and system based on image processing - Google Patents
Intelligent advertisement putting method and system based on image processing Download PDFInfo
- Publication number
- CN112163880A CN112163880A CN202011004373.8A CN202011004373A CN112163880A CN 112163880 A CN112163880 A CN 112163880A CN 202011004373 A CN202011004373 A CN 202011004373A CN 112163880 A CN112163880 A CN 112163880A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- customer
- image processing
- module
- characteristic
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000005516 engineering process Methods 0.000 claims abstract description 10
- 238000002716 delivery method Methods 0.000 claims abstract description 5
- 210000005252 bulbus oculi Anatomy 0.000 claims description 23
- 230000014509 gene expression Effects 0.000 claims description 16
- 210000001508 eye Anatomy 0.000 claims description 8
- 239000011521 glass Substances 0.000 claims description 6
- 210000004709 eyebrow Anatomy 0.000 claims description 4
- 210000001747 pupil Anatomy 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 239000002699 waste material Substances 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 8
- 230000009286 beneficial effect Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 4
- 102100036790 Tubulin beta-3 chain Human genes 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000001815 facial effect Effects 0.000 description 3
- 230000004397 blinking Effects 0.000 description 2
- 230000019771 cognition Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 230000004424 eye movement Effects 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 230000002458 infectious effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000004043 responsiveness Effects 0.000 description 1
- 238000007493 shaping process Methods 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
- G06Q30/0276—Advertisement creation
-
- 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
- G06Q30/0242—Determining effectiveness of advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent advertisement putting method based on image processing, which comprises the following steps: s1, adding a customer characteristic label which is matched with the characteristic attribute of the customer for the advertisement file; s2, acquiring customer image information, and identifying the characteristic attribute of the customer based on an image processing technology; s3, placing an advertisement file having a customer characteristic tag that matches the customer characteristic attribute determined in step S2. The intelligent advertisement delivery method based on image processing judges the characteristic attribute of the client and delivers and displays the advertisement content suitable for the client, so that the advertisement delivery is better and more accurate, the utilization rate of the advertisement file is improved, and the resource waste caused by non-differential delivery is avoided. The invention also discloses an intelligent advertisement delivery system based on image processing.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to an intelligent advertisement putting method and system based on image processing.
Background
Today, the market competition is increasingly intense and the products are highly homogeneous, the brands are increasingly becoming important competitive means for merchants, and the advertisements are powerful means and methods for forming brand images. The advertisement has significant contribution to improving the memory of consumers to brands, shaping brand personalities and increasing product values, and more enterprises popularize products and services per se through the advertisement. The existing advertisement putting mode is five-flower eight-door, the online and offline advertisement quality is good and uneven, and the ideal output can be brought by high advertisement putting. Common advertisement carriers include public transport advertisements, elevator advertisements, roof advertisements, television advertisements and the like, and the advertisement display modes are high in cost, poor in pertinence and not durable in propaganda effect. The goal of advertising is to maintain the ability to convey brand information to the potential target consumer audience population without memory fading. However, the advertisement information covering the ground has no value guidance, and the irrelevant advertisement push can make customers tired and bored, so that the advertisement playing is automatically shielded, the attention level of audiences is reduced, and the advertisement attention time is shortened.
The traditional advertisement putting mode mainly adopts a single advertisement machine, the updating period of the mode is long, the advertisement cost is high, a customer feels tired when watching the same advertisement for a long time, the same advertisement information can generate uneven advertisement effect for different customers, and the maximum benefit of the maximum advertisement cannot be achieved.
The existing mature accurate advertisement delivery technology is to acquire information of a user such as name, address, telephone, browsing record, purchasing record and the like through browsing record of the user on the network, establish a user interest map according to analysis of the cognition degree and the responsiveness of the user to advertisements, and push proper advertisement information to the user according to the map. Such push methods can cause panic to users who suspect that personal privacy is revealed and the protection of personal information is violated.
Disclosure of Invention
The invention provides an intelligent advertisement putting method based on image processing, aiming at solving the problems in the prior art.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
an intelligent advertisement putting method based on image processing comprises the following steps:
s1, adding a customer characteristic label which is matched with the characteristic attribute of the customer for the advertisement file;
s2, acquiring customer image information, and identifying the characteristic attribute of the customer based on an image processing technology;
s3, placing an advertisement file having a customer characteristic tag that matches the customer characteristic attribute determined in step S2.
Compared with the prior art, the invention has the following technical effects:
the characteristic attributes of the clients are judged firstly, and the advertisement content suitable for the clients is pushed and displayed to the clients, so that the advertisement delivery is better and accurate, the utilization rate of the advertisement file is improved, and resource waste caused by non-differential delivery is avoided.
On the basis of the technical scheme, the invention can be further improved as follows.
Preferably, the customer characteristic attribute comprises at least one of: gender, age, height, body type, skin color, whether or not to wear glasses.
The method has the advantages that the external expression characteristics of the customer are the internal favorite expressions, the customer preferences are presumed by identifying the external expression characteristics of the customer, and the advertisement putting accuracy is improved.
Preferably, the step S3 further includes the following sub-steps:
s3-1, acquiring image information of a customer, and identifying the micro-expression of the customer based on an image processing technology;
s3-2, calculating the interest value Q of the customer to the current advertisement according to the micro expression of the customer;
and S3-3, if the interest value Q of the customer to the currently played advertisement is lower than a set threshold, switching to the next advertisement file, otherwise, continuously playing the current advertisement file.
The beneficial effect of adopting the further scheme is that: the micro expression of the client can reveal the internal state of the client, and the attitude of the client to the current advertisement playing information can be judged by acquiring the micro expression of the client, so that the advertisement putting strategy is determined, the advertisement putting strategy is different from person to person, and the advertisement putting accuracy is improved.
Preferably, the identifying of the micro-expression of the customer means acquiring at least one of the following features: the time t that the customer's gaze stays on the advertisement information, and the frequency f of watching the advertisement1Blinking frequency f during viewing of the advertisement2Moving speed v of eyeball, pupil expansion degree e, eyebrow shape s, and angular arc of mouthAnd r is measured.
The further scheme has the beneficial effects that the expression details can represent the expression of the customer, and the more the expression details are obtained, the more accurate the expression of the customer is determined.
Preferably, the interest value Q ═ w of the customer in the currently played advertisement1×t+w2×f1+w3×f2+w4×v+w5×e+w6×s+w7X r, wherein w1~w7Are weight coefficients.
The beneficial effect of adopting the further scheme is that the micro-expression of the customer is quantized, and the control is convenient.
The invention also discloses an intelligent advertisement delivery system based on image processing, which comprises an advertisement delivery module, a camera module and a control module, wherein the advertisement delivery module and the camera module are sequentially and electrically connected with the control module;
the camera module is used for acquiring image information of a customer, extracting features of the image information and acquiring characteristic attributes of the customer;
the control module sends an instruction for delivering advertisement information matched with the characteristic attribute of the customer to the advertisement delivery module according to the characteristic attribute of the customer acquired by the camera module;
and the advertisement putting module puts and displays specific advertisement information according to the instruction of the control module.
Compared with the prior art, the method has the following beneficial effects
Preferably, the camera module further comprises an eyeball tracking module electrically connected with the control module and used for tracking the sight line attention point of the customer.
The beneficial effect who adopts above-mentioned further scheme is that can discern customer's characteristic through this system to according to customer's characteristic directional propelling movement advertising information, the precision is high.
Preferably, the customer characteristic attribute comprises at least one of: gender, age, height, body type, skin color, whether or not to wear glasses.
The method has the advantages that the external expression characteristics of the customer are the internal favorite expressions, the customer preferences are presumed by identifying the external expression characteristics of the customer, and the advertisement putting accuracy is improved.
Preferably, the function of collecting advertisement cold and hot areas is as follows:
SS1 capturing several visual points A of the customer's eyes on the advertisement by using the eyeball tracking modulei;
SS2, recording the sight of the customer at sight point AiTime t of treatmentAi;
SS3, recording time tAiBlink frequency of the customer;
SS4 counts the attention data of N customers on the same advertisement to form the distribution data of the cold and hot areas of the advertisement.
The beneficial effect of adopting the further scheme is that the natural reaction of the customer when looking over the advertisement information can be obtained, and the natural reaction is used for evaluating the quality of the advertisement file, so that the targeted modification of the advertisement file is facilitated.
Preferably, the step SS 3' is further included between the step SS3 and the step SS 4: recording the sight of the customer at a plurality of sight points AiThe line of movement and the gaze transfer speed.
The method has the advantage that the eye movement speed can be increased by one parameter to evaluate the preference degree of the customers for the advertisement information.
Drawings
FIG. 1 is a schematic flow chart of a smart advertisement delivery method based on image processing according to the present invention;
FIG. 2 is a flowchart of the image processing-based smart advertisement delivery method step S3 sub-step of the present invention;
fig. 3 is a block diagram of the image processing-based smart advertisement delivery system of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
The external customer screen of the double-screen cash register at the cash register of the shopping mall can be used as an advertisement carrier, advertisement information is displayed for customers coming to the store in a targeted manner, and potential consumers of products are mined. In the embodiment, three playing modes are provided, a camera device above a display screen captures customer images at any time, when clear customer images are obtained, the idle state of the current cash register can be judged, if the cash register is in the idle state, specific advertisement information can be displayed according to the attribute characteristics of customers, and the display mode of the advertisements is switched to full-screen display; when the cash register is in a non-idle state, characteristic advertisement information is displayed according to the attribute characteristics of the customer, and the display mode of the advertisement is switched to half-screen display. When the camera device above the display screen can not capture the image of the customer, the display screen randomly displays the advertisement information and displays the advertisement information in a full screen mode. The method of the invention is adopted in the double-screen cash register, so that the double-screen cash register can purposefully push advertisements to the client in the time period when the client waits for payment.
Please refer to fig. 1 and fig. 2, which are schematic structural diagrams illustrating an intelligent advertisement delivery method based on image processing according to the present invention. The intelligent advertisement putting method based on image processing comprises the following steps:
s1, adding a customer characteristic label which is matched with the characteristic attribute of the customer for the advertisement file;
s2, acquiring customer image information, and identifying the characteristic attribute of the customer based on an image processing technology; the characteristic attributes of the customers comprise sex, age, height, body type, skin color, whether wearing glasses and the like,
s3, putting an advertisement file with the customer characteristic label matched with the customer characteristic attribute determined in the step S2; further comprising:
s3-1, acquiring image information of a customer, and identifying the micro-expression of the customer based on an image processing technology; the identifying of the micro expression of the customer means acquiring at least one of the following characteristics: the time t that the customer's gaze stays on the advertisement information, and the frequency f of watching the advertisement1Blinking frequency f during viewing of the advertisement2Moving speed v of eyeballs, pupil expansion degree e, eyebrow shape s and mouth angle radian r;
s3-2, according to the micro-meter of the customerCalculating the interest value Q of the customer to the current advertisement; wherein Q ═ w1×t+w2×f1+w3×f2+w4×v+w5×e+w6×s+w7X r, wherein w1~w7The weight coefficient is a value range of 0-1;
and S3-3, if the interest value Q of the customer to the currently played advertisement is lower than a set threshold, switching to the next advertisement file, otherwise, continuously playing the current advertisement file.
As shown in fig. 3, an intelligent advertisement delivery system based on image processing includes an advertisement delivery module 1, a camera module 2 and a control module 3, wherein the advertisement delivery module and the camera module are sequentially and electrically connected to the control module;
the camera module 2 is used for acquiring image information of a customer, extracting features of the image information and acquiring characteristic attributes of the customer; the characteristic attributes of the customers comprise sex, age, height, body type, skin color, whether glasses are worn or not and the like. The camera module 2 comprises an eyeball tracking module 2.1 for tracking the eyeball movement of the customer.
The control module sends an instruction for delivering advertisement information matched with the characteristic attribute of the customer to the advertisement delivery module according to the characteristic attribute of the customer acquired by the camera module;
and the advertisement putting module puts and displays specific advertisement information according to the instruction of the control module.
The advertisement display time is automatically regulated and controlled according to the micro-expression change of the customer, if the eye spirit of the customer is concentrated in an advertisement area, the current advertisement is displayed for more seconds, and if the eye spirit of the customer is dispersed and dissociated, the advertisement is switched, so that the trouble that the customer is disturbed by uninteresting advertisement content is avoided.
(1) Utilize infrared camera (corresponding camera module) to catch the face image when customer watches the advertisement, eyeball tracking module tracks the motion of customer's eyeball, transmits the information that obtains for control module, and control module draws the characteristic of face region based on the face detection algorithm of degree of depth study: blink frequency f2Pupil dilation e, eyebrow shape s, mouth angle curvature r, etc.
(2) Amplifying the extracted features, and utilizing convolution to take values of the depth features.
(3) Each customer image may contain multiple mental states, combined with the weight w of each featureiAnd comparing the facial feature score with a threshold value in a sample expression information table prepared in advance, calculating the facial feature score of the customer, and converting the facial feature score into the interest value Q of the customer for the current advertisement.
(4) The control module controls the advertisement putting module to adjust the display time of the advertisement according to the interest value Q of the current played advertisement by the customer, and automatically regulates and controls the content switching of the advertisement.
The system has the functions of collecting advertisement cold and hot areas:
an excellent advertisement is very shocky and infectious, so that people can notice the advertisement to be equal to half of the product promotion, and whether the advertisement can attract the attention of consumers is a success or failure factor. The evaluation of advertising effectiveness typically expands from two aspects: firstly, whether expected marketing effect can be brought after advertisement display is carried out or not is judged, and the mode needs to observe the change situation of product sales before and after advertisement putting for a period of time; secondly, through the perception of the advertisement audience to the advertisement effect, the physiological and psychological changes of the advertisement audience when focusing on the advertisement need to be known, and the reaction mode of the audience when focusing on the advertisement is determined.
The invention is based on the length of the stay time, the watching frequency, the blinking frequency and the eyeball moving speed of the advertisement audiences focusing on the advertisement information, which are used as the objective evaluation for determining the preference of the audiences to the specific type of advertisements, and comprises the following steps:
SS1 capturing several visual points A of the customer's eyes on the advertisement by using the eyeball tracking modulei;
SS2, recording the sight of the customer at sight point AiTime t of treatmentAi;
SS3, recording time tAiBlink frequency of the customer;
SS 3' for recording the sight of customers at a plurality of sight points AiThe line of movement and the gaze transfer speed;
SS4 counts the attention data of N customers on the same advertisement to form the distribution data of the cold and hot areas of the advertisement.
Specifically, in order to determine the advertisement area concerned by the line of sight of the advertisement audience, whether the line of sight point of the customer falls on the external customer screen of the cash register is judged based on the infrared eye tracking technology:
(1) an infrared wide-angle camera device is arranged on an external customer screen of the cash register, so that eyeball movement information of customers can be captured in a wider area;
(2) acquiring an eyeball attention area through an infrared camera light source, and recording the time point of attention; for example, real estate advertisement is divided into a picture area and a character area, the eye dwell time of the two areas is calculated respectively, and the longer dwell time indicates that the content is difficult to understand or the customers are interested in;
(3) the moving speed of the eyeball can indicate the interest degree of the customer in the advertisement content, and the specific content is as follows:
the infrared eyeball tracking technology can capture a screen area concerned by eyeballs, and when the eyeballs concern the point A, the time t is recordedAWhen the eyeball focuses on point B, the time t is recordedBAccording to the angle of the infrared light source-eyeball-A point and the angle of the infrared light source-eyeball-B point, the relative displacement from A to B is calculated, and the relative displacement is divided by the time to obtain the eyeball moving speed.
(4) The blink frequency can also reflect the attention degree of the audience to the advertisement information on the side, and the lower the blink frequency indicates that the attention degree of the audience to the information is higher.
(5) And determining the hot area and the cold area of the advertisement information according to the length of the stay time, the watching frequency, the blinking frequency and the eyeball moving speed of the audience on the advertisement information.
(6) The hot and cold regions of the advertisement are provided to the advertiser as a data reference for ad tuning and optimization.
In addition, the system is combined with an intelligent camera at the entrance of a store, and can be used for evaluating the advertisement putting effect:
the advertisement attention rate is a main index examined when the advertisement propagation effect is evaluated, and reflects how many audiences really contact the advertisement and form cognition and memory on the advertisement. The advertisement attention rate is a basic index for measuring the recognition and memory of the advertisement by the audience, is an indicator for effectively reaching the advertisement and is a final measurement standard for the advertisement propagation effect.
(1) Calculating the advertisement attention rate of the store-entering customers: the in-store camera counts the number of in-store customers, and the infrared eyeball device counts the number of customers in the focus advertisement area of the checkout customer;
(2) calculating the advertisement attention rate of the checkout customer: the cashier foreground camera counts the number of the clients waiting for payment and queuing, and the infrared eyeball device counts the number of the clients paying for payment in the advertisement region;
(3) calculating customer attention rates for the advertisements;
(4) calculating the focus hot zone of the advertisement: the areas with the greatest length of time of attention of all customers who pay attention to the advertisement are calculated, and then the maximum lengths of time of the areas are added and divided by the number of the attention customers.
(5) After 14 days of advertisement putting, the sales and sales change of the advertisement putting product before and after advertisement putting are concerned.
(6) After 14 days of advertising, the sales and sales variation of the product and the related products are compared.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. An intelligent advertisement putting method based on image processing is characterized by comprising the following steps:
s1, adding a customer characteristic label which is matched with the characteristic attribute of the customer for the advertisement file;
s2, acquiring customer image information, and identifying the characteristic attribute of the customer based on an image processing technology;
s3, placing an advertisement file having a customer characteristic tag that matches the customer characteristic attribute determined in step S2.
2. The image-processing-based smart advertisement delivery method according to claim 1, wherein the customer characteristic attribute includes at least one of: gender, age, height, body type, skin color, whether or not to wear glasses.
3. The intelligent advertising method based on image processing according to claim 1 or 2, wherein the step S3 further comprises the following sub-steps:
s3-1, acquiring image information of a customer, and identifying the micro-expression of the customer based on an image processing technology;
s3-2, calculating the interest value Q of the customer to the current advertisement according to the micro expression of the customer;
and S3-3, if the interest value Q of the customer to the currently played advertisement is lower than a set threshold, switching to the next advertisement file, otherwise, continuously playing the current advertisement file.
4. The method for intelligent advertisement delivery based on image processing as claimed in claim 3, wherein the identifying of the micro-expression of the customer means obtaining at least one of the following features: the time t that the customer's gaze stays on the advertisement information, and the frequency f of watching the advertisement1Blinking frequency f during viewing of the advertisement2The moving speed v of the eyeball, the pupil expansion degree e, the eyebrow shape s and the mouth angle radian r.
5. The method of claim 4, wherein the interest value Q of the customer in the currently played advertisement is w1×t+w2×f1+w3×f2+w4×v+w5×e+w6×s+w7X r, wherein w1~w7Are weight coefficients.
6. An intelligent advertisement delivery system based on image processing is characterized by comprising an advertisement delivery module, a camera module and a control module, wherein the advertisement delivery module and the camera module are sequentially and electrically connected with the control module;
the camera module is used for acquiring image information of a customer, extracting features of the image information and acquiring characteristic attributes of the customer;
the control module sends an instruction for delivering advertisement information matched with the characteristic attribute of the customer to the advertisement delivery module according to the characteristic attribute of the customer acquired by the camera module;
and the advertisement putting module puts and displays specific advertisement information according to the instruction of the control module.
7. The image processing-based smart advertisement delivery system according to claim 6, wherein the camera module comprises an eye tracking module electrically connected to the control module for tracking a line of sight point of interest of the customer.
8. The image processing-based smart advertisement delivery system of claim 7, wherein the customer characteristic attributes comprise at least one of: gender, age, height, body type, skin color, whether or not to wear glasses.
9. The intelligent image-processing-based advertisement delivery system according to claim 7, having a function of collecting advertisement hot and cold areas:
SS1 capturing several visual points A of the customer's eyes on the advertisement by using the eyeball tracking modulei;
SS2, recording the sight of the customer at sight point AiTime t of treatmentAi;
SS3, recording time tAiBlink frequency of the customer;
SS4 counts the attention data of N customers on the same advertisement to form the distribution data of the cold and hot areas of the advertisement.
10. The intelligent image-processing-based advertising system according to claim 9, wherein between steps SS3 and SS4, further comprising steps SS 3': recording the sight of the customer at a plurality of sight points AiBetween the two roadsLine and gaze translation speed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011004373.8A CN112163880A (en) | 2020-09-22 | 2020-09-22 | Intelligent advertisement putting method and system based on image processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011004373.8A CN112163880A (en) | 2020-09-22 | 2020-09-22 | Intelligent advertisement putting method and system based on image processing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112163880A true CN112163880A (en) | 2021-01-01 |
Family
ID=73862649
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011004373.8A Pending CN112163880A (en) | 2020-09-22 | 2020-09-22 | Intelligent advertisement putting method and system based on image processing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112163880A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113531322A (en) * | 2021-07-12 | 2021-10-22 | 银川翔通公交传媒有限公司 | Intelligent bus-mounted advertisement management system and device based on cloud platform |
CN113919859A (en) * | 2021-08-25 | 2022-01-11 | 读书郎教育科技有限公司 | Model machine display method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103999032A (en) * | 2011-12-12 | 2014-08-20 | 英特尔公司 | Interestingness scoring of areas of interest included in a display element |
CN106682946A (en) * | 2016-12-30 | 2017-05-17 | 北京七鑫易维信息技术有限公司 | Advertisement content analysis method and device |
US20170278130A1 (en) * | 2016-03-28 | 2017-09-28 | Le Holdings (Beijing) Co., Ltd. | Method and Electronic Device for Matching Advertisement Data |
CN109740466A (en) * | 2018-12-24 | 2019-05-10 | 中国科学院苏州纳米技术与纳米仿生研究所 | Acquisition methods, the computer readable storage medium of advertisement serving policy |
-
2020
- 2020-09-22 CN CN202011004373.8A patent/CN112163880A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103999032A (en) * | 2011-12-12 | 2014-08-20 | 英特尔公司 | Interestingness scoring of areas of interest included in a display element |
US20170278130A1 (en) * | 2016-03-28 | 2017-09-28 | Le Holdings (Beijing) Co., Ltd. | Method and Electronic Device for Matching Advertisement Data |
CN106682946A (en) * | 2016-12-30 | 2017-05-17 | 北京七鑫易维信息技术有限公司 | Advertisement content analysis method and device |
CN109740466A (en) * | 2018-12-24 | 2019-05-10 | 中国科学院苏州纳米技术与纳米仿生研究所 | Acquisition methods, the computer readable storage medium of advertisement serving policy |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113531322A (en) * | 2021-07-12 | 2021-10-22 | 银川翔通公交传媒有限公司 | Intelligent bus-mounted advertisement management system and device based on cloud platform |
CN113919859A (en) * | 2021-08-25 | 2022-01-11 | 读书郎教育科技有限公司 | Model machine display method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109740466B (en) | Method for acquiring advertisement putting strategy and computer readable storage medium | |
CN105339969B (en) | Linked advertisements | |
WO2019149005A1 (en) | Offline interactive advertisement system | |
US8670183B2 (en) | Augmented view of advertisements | |
KR101271483B1 (en) | Smart digital signage using customer recognition technologies | |
US9747497B1 (en) | Method and system for rating in-store media elements | |
JP6267861B2 (en) | Usage measurement techniques and systems for interactive advertising | |
JP6123140B2 (en) | Digital advertising system | |
US20120140069A1 (en) | Systems and methods for gathering viewership statistics and providing viewer-driven mass media content | |
US20200320576A1 (en) | Targeted Advertising Based On Demographic Features Extracted From Persons | |
TW201810128A (en) | Engagement value processing system and engagement value processing device | |
CN108876430B (en) | Advertisement pushing method based on crowd characteristics, electronic equipment and storage medium | |
JP2004227158A (en) | Information providing device and information providing method | |
US20220067792A1 (en) | System and method for generating visual content associated with tailored advertisements in a mixed reality environment | |
US20220066537A1 (en) | System and method for identifying tailored advertisements based on detected features in a mixed reality environment | |
CN107146096A (en) | Intelligent video advertisement display method and device | |
EP2158781A2 (en) | System and method for selecting a message to play from a playlist | |
JP6498900B2 (en) | Advertisement evaluation system, advertisement evaluation method | |
KR20150000026A (en) | Smart mobile digital signage using customer recognition technologies and control method thereof | |
CN112163880A (en) | Intelligent advertisement putting method and system based on image processing | |
CN110889719A (en) | Advertisement pushing system and method based on user consumption characteristics | |
EP2136329A2 (en) | Comprehensive computer implemented system and method for adapting the content of digital signage displays | |
CN110969480A (en) | Multimedia backpack advertising information playing control method and device | |
US20190279233A1 (en) | Real-World Analytics Monitor | |
US20230409112A1 (en) | System and method for determining user interactions with visual content presented in a mixed reality environment |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210101 |
|
RJ01 | Rejection of invention patent application after publication |