CN109993589A - A kind of advertisement machine passenger flow data analysis method based on machine vision - Google Patents
A kind of advertisement machine passenger flow data analysis method based on machine vision Download PDFInfo
- Publication number
- CN109993589A CN109993589A CN201910305646.3A CN201910305646A CN109993589A CN 109993589 A CN109993589 A CN 109993589A CN 201910305646 A CN201910305646 A CN 201910305646A CN 109993589 A CN109993589 A CN 109993589A
- Authority
- CN
- China
- Prior art keywords
- data
- advertisement
- face
- content
- machine
- 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
- 238000000034 method Methods 0.000 title claims description 32
- 238000007405 data analysis Methods 0.000 title claims description 5
- 238000013473 artificial intelligence Methods 0.000 claims description 5
- 238000013480 data collection Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 abstract description 2
- 239000002699 waste material Substances 0.000 abstract description 2
- 230000000007 visual effect Effects 0.000 description 4
- 241001269238 Data Species 0.000 description 2
- 238000004458 analytical method 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
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- 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
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Finance (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention is to solve conventional Multi Media advertisement machine, can only be mechanical it is duplicate according to set content broadcasting advertisement content, advertisement putting business can not obtain the passenger flow data of advertisement machine, it can not learn Commercial Viewing Data, judge the effect of advertisement, also without normal direction specific crowd advertisement content the problem of, utilize Machine Vision Recognition Technology, the video data acquired by high-definition camera, the volume of the flow of passengers before advertisement machine can be perceived, watch the audience data of advertisement, and according to the marketing strategy set, relevant ad content is pushed to specific audience, pass through the above technology, traditional Multimedia Advertisement Machine is become into intelligent multimedia advertisement, improve the conversion ratio of advertisement, reduce the waste of resource.
Description
Technical field
The present invention relates under the basis of machine vision technique, the passenger flow data of Multimedia Advertisement Machine acquisition is subjected to intelligence
The method of energyization analysis, in addition to effective analysis data can be provided for product advertising, additionally it is possible to according to station before advertisement machine by
Many features, carry out the push of the advertising information of active, improve the conversion ratio of advertisement.
Background technique
Currently, Multimedia Advertisement Machine can be described as ubiquitous, elevator, market, bus station is seen everywhere in subway, though
The technology so played using multimedia video attracts passenger flow using lively content and sound, but wide based on tradition
The mode of announcement, set time play fixed content, as broadcasting ad content whether cause audient's note that when by
Crowd station also can only be the current ad content of mechanical broadcasting, lack data collection and analysis and perceive audient's before advertisement machine
The problem of function is distributed very wide although the quantity of advertisement machine is very much, also brings low efficiency simultaneously, the wasting of resources.
Summary of the invention
Multimedia Advertisement Machine major function is the stream of people's warp for having hundreds and thousands of ten thousand daily to huge audience broadcasting advertisement content
It crosses, in order to solve in Multimedia Advertisement Machine, the problem of can not acquiring and analyze passenger flow data, perceive audient, present invention design
The method of a set of passenger flow analysing based on machine vision technique and perception audient installs camera additional in Multimedia Advertisement Machine, will
These passenger flow datas collect, for statistical analysis using machine vision technique, and machine vision technique extraction also can be used
It stands the feature of the audient before advertisement machine, analyzes and determines its interested ad content, carry out the push of active, entire method stream
Journey is as follows:
1. the volume of the flow of passengers acquires
1.1) machine vision technique is used, identifies the quantity of the people occurred in video, and obtain everyone at a time
Position in video
1.2) direction of everyone movement over time, is calculated
1.3) when the position of people removal current video picture, then it is calculated as a passenger flow
1.4) by above data, the data point of available (such as: day, week, the moon, season, year etc.) passenger flow within cycle time
Cloth
2. watching the acquisition of advertisement passenger flow data
2.1) machine vision technique is used, identifies the face towards advertisement machine occurred in video
2.2) characteristic of the face, including age range, gender are extracted, if the human face data recorded for before
2.3) add up the duration that the face persistently occurs in video, the duration watched
2.4) content of currently playing advertisement, moment, advertisement total duration are recorded
2.5) according to above data, face duration and ad content, advertisement duration calculates the viewing number of advertisement
According to
3. ad content pushes
3.1) machine vision technique is used, identifies the audient towards advertisement machine occurred in video
3.2) characteristic of audient's face, including age range, gender are extracted, if the human face data recorded for before
3.3) label on audient's belongings or clothes is identified, as characteristic
3.4) according to collected age, gender and other feature data, the advertisement of related data will be met in ad system
Advertisement machine is pushed to play out
3.5) content of currently playing advertisement, moment, advertisement total duration, face duration are recorded
3.6) according to the propelling data of accumulation, the technology learnt by artificial intelligence machine continues to optimize push scheme
Beneficial effect can effectively collect volume of the flow of passengers data, advertisement by the technology of machine vision by above method
Data are watched, and realize ad content push, bring intelligentized ability for traditional Multimedia Advertisement Machine, are advertiser
Provide more valuable reference datas, to be the dispensing of advertisement, content design, precision marketing provide it is strong according to
According to reducing the waste of resource.
Detailed description of the invention
Fig. 1 volume of the flow of passengers collecting work process,
Fig. 2 watches advertisement passenger flow data collecting work process,
Fig. 3 ad content pushes workflow,
Advertisement machine passenger flow data analysis method of the Fig. 4 based on machine vision.
Specific embodiment
The scene of advertisement is played used here as an outdoor Multimedia Advertisement Machine to illustrate specific embodiment;
Multimedia Advertisement Machine 1, high-definition camera 1, by network access machine device visual services, implementation process is as follows:
1. the volume of the flow of passengers acquires
1.1) high-definition camera carries out real time video collection, and acquisition range is 3 meters of advertisement machine face range, and data are transmitted to machine
Visual services
1.2) by machine vision service, the human body occurred in video is identified
1.3) human body by each identification is marked, and records current location
1.4) it repeats to calculate its motion profile to marked human body 1.1) to 1.2) process, judges whether to enter or leave wide
Announcement machine range
1.5) when markd human body leaves advertisement machine range, a passenger flow data is recorded
2. watching the acquisition of advertisement passenger flow data
2.1) high-definition camera carries out real time video collection, and acquisition range is 3 meters of advertisement machine face range, and data are transmitted to machine
Device visual services
2.2) by machine vision service, the face of the face advertisement machine occurred in video is identified
2.3) by machine vision service, the feature of face is extracted, at the age, face is marked in gender data
2.4) it repeats 2.1) to the accumulative viewing duration data of marked face, and to record in currently playing advertisement to 2.2)
Hold
If 2.5) human face data is recorded in face database not in the face database of system by the human face data
2.6) after the face of label disappears, the duration of primary viewing advertisement is recorded
3. ad content pushes
3.1) high-definition camera carries out real time video collection, and acquisition range is 3 meters of advertisement machine face range, and data are transmitted to machine
Visual services
3.2) by machine vision service, the face of the face advertisement machine occurred in video is identified
3.3) by machine vision service, the feature of face is extracted, at the age, face is marked in gender data
3.4) by machine vision service, the label on audient's belongings or clothes is identified, as characteristic
If 3.5) human face data is recorded in face database not in the face database of system by the human face data
If 3.6) human face data has existed in the face database of system, the relevant data of face are taken out
3.7) data obtained according to 3.3), 3.4) and 3.6) should by system judgement by the ad content characteristic of system
The interested ad content of audient, and pushed.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Be familiar with the art be technical staff in the technical scope disclosed by the present invention, various equivalent modifications can be readily occurred in or replaced
It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection scope subject to.
Claims (4)
1. a kind of Multimedia Advertisement Machine passenger flow data analysis method based on artificial intelligence, which is characterized in that including passenger flow data
Collecting flowchart, Commercial Viewing Data collecting flowchart and ad content push process, in which:
The passenger flow data collecting flowchart, for handling passenger flow data collection process；
The Commercial Viewing Data collecting flowchart is used for Commercial Viewing Data collection process；
The ad content pushes process, pushes process for ad content.
2. passenger flow data collecting flowchart according to claim 1, characterized in that passenger flow data collecting flowchart specifically includes:
The video data of high-definition camera acquisition；
By artificial intelligence machine vision technique, the human body in video is identified；
Each human body is marked, and records position of human body data；
By again identifying that the video of subsequent period, the new position of marked human body is judged, it is effective whether calculating leaves advertisement machine
Region；
When labeled human body leaves, passenger flow data is recorded.
3. Commercial Viewing Data process flow according to claim 1, characterized in that Commercial Viewing Data process flow tool
Body includes:
The video data of high-definition camera acquisition；
By artificial intelligence machine vision technique, the face of face advertisement machine in video is identified；
Extract the characteristic of face, gender, age range data；
Record currently playing ad content
Add up duration existing for labeled face
After labeled face disappears, the data of advertisement viewing are recorded.
4. ad content according to claim 1 pushes process flow, characterized in that ad content pushes process flow tool
Body includes:
The video data of high-definition camera acquisition；
By artificial intelligence machine vision technique, the face of face advertisement machine in video is identified；
Extract the characteristic of face, gender, age range data, the other features number such as identification human body personal effects
According to；
The face characteristic is compared in existing face database, obtains the data of previous advertisement pushing
The ad data pushed according to the characteristic of current audience and in the past to it, by system-computed and to push its interested
Ad content.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910305646.3A CN109993589A (en) | 2019-04-16 | 2019-04-16 | A kind of advertisement machine passenger flow data analysis method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910305646.3A CN109993589A (en) | 2019-04-16 | 2019-04-16 | A kind of advertisement machine passenger flow data analysis method based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109993589A true CN109993589A (en) | 2019-07-09 |
Family
ID=67133892
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910305646.3A Pending CN109993589A (en) | 2019-04-16 | 2019-04-16 | A kind of advertisement machine passenger flow data analysis method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109993589A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110634035A (en) * | 2019-09-27 | 2019-12-31 | 广州南翼信息科技有限公司 | Face recognition's pop-up window advertising system |
| CN111784406A (en) * | 2020-07-10 | 2020-10-16 | 大连中维世纪科技有限公司 | Traditional advertisement big data quantitative analysis method based on face intelligent recognition |
| CN113159857A (en) * | 2021-04-30 | 2021-07-23 | 中国银行股份有限公司 | Advertisement putting method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129644A (en) * | 2011-03-08 | 2011-07-20 | 北京理工大学 | Intelligent advertising system having functions of audience characteristic perception and counting |
| CN106971317A (en) * | 2017-03-09 | 2017-07-21 | 杨伊迪 | The advertisement delivery effect evaluation analyzed based on recognition of face and big data and intelligently pushing decision-making technique |
| CN108109010A (en) * | 2017-12-26 | 2018-06-01 | 南京开为网络科技有限公司 | A kind of intelligence AR advertisement machines |
-
2019
- 2019-04-16 CN CN201910305646.3A patent/CN109993589A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129644A (en) * | 2011-03-08 | 2011-07-20 | 北京理工大学 | Intelligent advertising system having functions of audience characteristic perception and counting |
| CN106971317A (en) * | 2017-03-09 | 2017-07-21 | 杨伊迪 | The advertisement delivery effect evaluation analyzed based on recognition of face and big data and intelligently pushing decision-making technique |
| CN108109010A (en) * | 2017-12-26 | 2018-06-01 | 南京开为网络科技有限公司 | A kind of intelligence AR advertisement machines |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110634035A (en) * | 2019-09-27 | 2019-12-31 | 广州南翼信息科技有限公司 | Face recognition's pop-up window advertising system |
| CN110634035B (en) * | 2019-09-27 | 2023-09-05 | 广州南翼信息科技有限公司 | Face recognition popup advertisement system |
| CN111784406A (en) * | 2020-07-10 | 2020-10-16 | 大连中维世纪科技有限公司 | Traditional advertisement big data quantitative analysis method based on face intelligent recognition |
| CN113159857A (en) * | 2021-04-30 | 2021-07-23 | 中国银行股份有限公司 | Advertisement putting method and device |
| CN113159857B (en) * | 2021-04-30 | 2024-02-02 | 中国银行股份有限公司 | Advertisement putting method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108495153B (en) | Multimedia content pushing method, device and system | |
| KR101094119B1 (en) | Method and system for managing an interactive video display system | |
| CN109993589A (en) | A kind of advertisement machine passenger flow data analysis method based on machine vision | |
| CN102077580B (en) | Display control device, display control method | |
| CN106971317A (en) | The advertisement delivery effect evaluation analyzed based on recognition of face and big data and intelligently pushing decision-making technique | |
| CN102129644A (en) | Intelligent advertising system having functions of audience characteristic perception and counting | |
| US20120140069A1 (en) | Systems and methods for gathering viewership statistics and providing viewer-driven mass media content | |
| CN105975581A (en) | Media information display method, client and server | |
| CN101459806A (en) | System and method for video playing | |
| CN104112209A (en) | Audience statistical method of display terminal, and audience statistical system of display terminal | |
| CN102236860A (en) | Automatic advisement releasing system and method | |
| CN109543575B (en) | Method for feeding back excitation big data based on behavior track and dynamic multi-dimensional information and regional multi-dimensional detection feedback combined equipment | |
| CN108898410A (en) | The effect analysis method and device of medium are launched in a kind of advertisement | |
| CN108876454A (en) | The device and its statistical method of accurate statistics commercial audience situation | |
| CN107230106A (en) | A kind of advertisement broadcast method that feature is identified based on big data platform | |
| CN109102336A (en) | Robot advertisement sending method and its system based on image analysis | |
| CN109982141B (en) | Method for analyzing video image area and implanting advertisement by using AI technology | |
| CN110689367A (en) | Data acquisition method and device, computer device and storage medium | |
| CN114501081B (en) | Screen advertisement playing method and system | |
| CN113240466B (en) | Mobile media video data processing method and device based on big data depth analysis and storage medium | |
| JP2022542114A (en) | Data processing method, data processing apparatus, apparatus, computer readable storage medium, data processing apparatus and computer program | |
| CN114708018B (en) | Electronic screen advertisement intelligent charging management system based on data analysis | |
| CN109040841B (en) | Method and device for monitoring advertisement before cinema showing and computer readable storage medium | |
| CN114529352A (en) | Intelligent marketing promotion method and system based on big data analysis | |
| CN110942051A (en) | Indoor advertising screen watching time counting method |
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 |