CN109087133A - A kind of behavior guidance analysis system and its working method based on context aware - Google Patents
A kind of behavior guidance analysis system and its working method based on context aware Download PDFInfo
- Publication number
- CN109087133A CN109087133A CN201810818856.8A CN201810818856A CN109087133A CN 109087133 A CN109087133 A CN 109087133A CN 201810818856 A CN201810818856 A CN 201810818856A CN 109087133 A CN109087133 A CN 109087133A
- Authority
- CN
- China
- Prior art keywords
- data
- face
- current region
- current
- product
- 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
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
- G06Q30/0282—Rating or review of business operators or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/013—Eye tracking input arrangements
-
- 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
- G06V40/172—Classification, e.g. identification
Abstract
The invention discloses a kind of behavior guidance analysis system and its working method based on context aware.Behavior guidance analysis system in the present invention includes data acquisition unit, data processing unit, data evaluation unit and data storage cell.Working method in the present invention obtains stream of people's data and current face's characteristic, eye movement data and face characteristic data first；Then output just handles data；Then the level distribution situation and push for exporting and saving the product of current region are suggested.The present invention is applied in wisdom shopping scene, by the data analysis to user, product and resource advantage, on-line off-line data resource has been effectively integrated, has constructed precision marketing for businessman, it allows product precisely to cover validated user, and quickly understands project, to-be-experienced product convenient for user.
Description
Technical field
The invention belongs to consumption data analysis technical fields, and in particular to a kind of behavior guidance based on context aware point
Analysis system and its working method.
Background technique
O2O (Online To Offline) mode of today of internet increasingly prosperity, on-line off-line fusion will do shopping
Process becomes more simplified and convenient, this is a kind of greatly strike for traditional Chun Xianxia shops；People's gradually selection line
The reason of upper shopping is mainly that can quickly search out oneself desired commodity, in contrast, existing Xian Xia shops distribution system
System has a single function, and can only guarantee consuming when secondary for consumer, can not learn other propensities to consume of consumer, and cannot be fine
The personal considerations according to consumption quotient provide personalized service, not can increase consumer for the viscosity of Xian Xia shops, it is intelligent
Degree is low, cannot accurately obtain the propensity to consume of most consumers, only uniformity quality is sold；It is above-mentioned to cause
The reason of user experience of Xian Xia shops gradually decreases is mainly that can not obtain the consumer behavior guiding of consumer in time and disappear
Context aware of the expense person in process of consumption causes, and being badly in need of a kind of technology at present can solve the above problem.
Summary of the invention
In order to solve the above problems existing in the present technology, it is an object of that present invention to provide a kind of based on context aware
Behavior guidance analysis system and its working method.
The technical scheme adopted by the invention is as follows:
A kind of behavior guidance analysis system based on context aware, comprising:
Data acquisition unit is also used for acquiring the face feature data and eye movement data of the human body of current region
In stream of people's data of acquisition current region；
Data processing unit, for obtain data acquisition unit acquisition data after carry out recognition of face, face alignment,
Facial Expression Analysis, the analysis of sight focus and motion trail analysis；
Data evaluation unit, for carrying out the assessment of product attention rate, consumption after obtaining the data that data processing unit exports
Capability evaluation and consumption habit assessment, the level distribution situation and push for being also used to export the product of current region are suggested.
Data storage cell, for establishing demographic data library and regional database；Demographic data library is with each personnel for 1
A storage cell, for storing face feature, consuming capacity, consumption habit and the consumption number of times of current persons；Regional database
With each region for 1 storage cell, for storing the sales situation, stream of people's data, product level distribution situation of current region
And push is suggested；
Data processing unit, data evaluation unit and the data storage cell is all set in Cloud Server；It is described
Data processing unit and data acquisition unit wireless communication connect.
Preferably, the data acquisition unit includes the correlation type photoelectric sensor being arranged in current region, swashs
Photoscanner, temperature sensor and camera；The laser scanner for scan the three-D profile of personnel in current region,
Position and motion state, output can be converted to the range information of polar form；The camera is for realizing current region
The acquisition of the face characteristic data of interior personnel, and the data for matching laser scanner output do the state description of each personnel；Institute
The temperature sensor stated is used to detect the record of the shell temperature of personnel and physiological characteristic in current region, and sweeps in conjunction with laser
Retouch the behavior act and physiological status of personnel in current region in the data judging space of instrument and camera output.
Preferably, the correlation type photoelectric sensor is 2, it is respectively arranged at the outlet of current region and works as
The entrance of forefoot area；The camera includes the entrance of 2 groups of outlets for being set to current region and current region, and 2 groups of stream of peoples
The shooting direction for counting camera is opposite；Each correlation type photoelectric sensor triggers corresponding stream of people's statistics when optical path is blocked
Camera is taken pictures and identifies face number to get stream of people's data of the entrance of the outlet or current region of current region are arrived, together
Shi Renliu counts camera and obtains current face's characteristic.
Preferably, the camera further includes the eye movement camera for being set to the product periphery of current region；It is described
Eye movement camera be used to detect the eye movement of active user, obtain eye movement data.
Preferably, the camera further includes multiple track cameras for being set to current region top；Each track phase
Machine carries out the acquisition of the face characteristic data within the scope of current shooting.
The working method of the above-mentioned behavior guidance analysis system based on context aware, comprising the following steps:
S1. stream of people's data and current face's characteristic in current region entrance and its exit are obtained；
S2. the eye movement data of the personnel on current region product periphery is obtained；
S3. the face characteristic data of the personnel in current region are obtained；
S4. by stream of people's data, current face's characteristic, eye movement data and the face characteristic number in step S1-S3
It analyzes, and is exported just according to recognition of face, face alignment, facial Expression Analysis, the analysis of sight focus and motion profile point is carried out
Handle data；
S5. the first processing data in obtaining step S4 carry out the assessment of product attention rate, consuming capacity assessment and consumption and practise
Used assessment, establishes or improves demographic data library and regional database, then exports and save the level point of the product of current region
Cloth situation and push are suggested.
Preferably, in step S1, the specific steps are as follows:
S101. after the light receiving device of correlation type optical sensor detects that optical path is blocked, a switch control signal is exported,
It triggers 2 groups of stream of peoples and counts camera；
The S102.2 group stream of people counts camera and runs simultaneously, and in real time identifies the image of shooting, obtains stream of people's number
According to, and the image of shooting is subjected to pretreatment and generates current face's characteristic；
S103. stream of people's data of identification and current face's characteristic are uploaded to data processing unit.
Preferably, the analysis of sight focus is carried out by eye movement data, by current in the step S4
Face characteristic data and face characteristic data carry out recognition of face, face alignment and facial Expression Analysis, pass through current face spy
It levies data and face characteristic data and auxiliary data carries out motion trail analysis；The auxiliary data includes laser scanner
The range information that can be exchanged into polar form of output further includes the behavior act of each personnel of temperature sensor output
And physiological status.
Preferably, when carrying out recognition of face, carrying out face inspection to the face characteristic data of acquisition first in step S4
It surveys；Specific step is as follows for the Face datection:
S401. the input picture containing face characteristic data is pre-processed, to obtain the first light of input picture
Image and pretreatment image are compensated, the pretreatment image includes area of skin color and non-area of skin color；
S402. edge detection process is carried out to pretreatment image, obtains the length of edge inspection area and edge inspection area
Angle value, width value and length-width ratio, and round area to be tested is obtained according to the length value, width value and length-width ratio；
S403. area of skin color extension process is carried out to the pretreatment image in round area to be tested coverage area, obtained
First facial contour；
S404. in round area to be tested coverage area the first light compensation image carry out light compensation deals and
Face Detection obtains the second facial contour；
S405. merge the first facial contour and the second facial contour to get to facial image needed for Face datection.
Preferably, demographic data library includes multiple individual databases in step S5；Each individual database includes
Gender, age, consumption number of times, consuming capacity and the consumption habit of current persons further includes unique user identifier；Described
User identifier and the face picture of current persons correspond；Regional database includes place, area and the product of current region
Level distribution situation, further include the push suggestion for current region；The level distribution situation of the product passes through unit
The product attention rate of each product obtains in time or unit flow of the people；The product attention rate passes through unit time or list
The sight focus of current production obtains in the flow of the people of position；The push is suggested that the product including current region is furnished and is suggested
And product purchasing suggestion.
The invention has the benefit that
It is practised by product attention rate, consuming capacity and consumption that all data that current region acquires obtains consumption personnel
It is used, it realizes the integration of on-line off-line data resource, and provide accurately data service based on big data analysis, is decision data
It provides effective twelve Earthly Branches to hold, greatly improves the precision marketing that interactive experience and shopping experience carry out displaying convenient for the later period and push away
It send and services, construct precision marketing for offline businesses and effectively data supporting is provided；Intelligence degree of the present invention is high, Neng Gouti
For comprehensive analysis, it can suggest that adjustment is current according to the level distribution situation of product and push in time convenient for offline businesses
The product placement and buying situation in region；The present invention is analyzed by the data to user, product and resource advantage, is effectively integrated
On-line off-line data resource constructs precision marketing for businessman, allows product precisely to cover validated user, and quick convenient for user
Understand the project of current businessman, experience the product in current scene, substantially increase user experience, is Xian Xia shops mutual
The networking epoch provide new reform analysis, are suitable for promoting the use of.
Specific embodiment
Further explaination is done to the present invention combined with specific embodiments below.
Embodiment 1:
The behavior guidance analysis system based on context aware that the present embodiment provides a kind of, including data acquisition unit, data
Processing unit, data evaluation unit and data storage cell.
Data acquisition unit is also used for acquiring the face feature data and eye movement data of the human body of current region
In stream of people's data of acquisition current region.In the present embodiment, data acquisition unit includes the correlation type being arranged in current region
Photoelectric sensor, laser scanner, temperature sensor and camera；Laser scanner is for scanning three of personnel in current region
Profile, position and motion state are tieed up, output can be converted to the range information of polar form；Camera is for realizing working as proparea
The acquisition of the face characteristic data of personnel in domain, and the data for matching laser scanner output do the state description of each personnel；
Temperature sensor is used to detect the record of the shell temperature of personnel and physiological characteristic in current region, and combining laser scanning instrument
And in the data judging space of camera output in current region personnel behavior act and physiological status.
In the present embodiment, correlation type photoelectric sensor is 2, is respectively arranged at the outlet of current region and works as proparea
The entrance in domain；Camera includes the entrance of 2 groups of outlets for being set to current region and current region, and 2 groups of stream of peoples count camera
Shooting direction is opposite；Each correlation type photoelectric sensor triggers corresponding stream of people's statistics camera and claps when optical path is blocked
According to and identify face number to get to current region outlet or current region entrance stream of people's data, while the stream of people count
Camera obtains current face's characteristic；By taking inlet as an example, when inlet has personnel by blocking correlation type photoelectric sensing
When the optical path of device, shooting direction is towards in current region and counting camera towards 2 groups of stream of peoples outside current region and be triggered simultaneously
And take pictures, if current persons are into shop, shooting direction is towards outside current region and being located at 1 group of stream of people of inlet inside and unite
Meter camera takes the positive face of personnel, is then calculated by human face five-sense-organ identification and identifies that the stream of people can be obtained in the number of face
Data, wherein only need to identify that eye, nose, any organ in mouth judge that current persons face in current region, i.e., into
Shop personnel add 1；If current persons are shops out, shooting direction is towards in current region and another 1 group of people for being located on the outside of entrance
Stream statistics camera takes the positive face of current persons, and judgement and calculating process are similarly as above.
In the present embodiment, camera further includes the eye movement camera for being set to the product periphery of current region；Eye movement
Camera is used to detect the eye movement of active user, obtains eye movement data.
In the present embodiment, camera further includes multiple track cameras for being set to current region top；Each track camera is equal
Carry out the acquisition of the face characteristic data within the scope of current shooting.
Data processing unit, for obtain data acquisition unit acquisition data after carry out recognition of face, face alignment,
Facial Expression Analysis, the analysis of sight focus and motion trail analysis.
Data evaluation unit, for carrying out the assessment of product attention rate, consumption after obtaining the data that data processing unit exports
Capability evaluation and consumption habit assessment, the level distribution situation and push for being also used to export the product of current region are suggested.
Data storage cell, for establishing demographic data library and regional database；Demographic data library is with each personnel for 1
A storage cell, for storing face feature, consuming capacity, consumption habit and the consumption number of times of current persons；Regional database
With each region for 1 storage cell, for storing the sales situation, stream of people's data, product level distribution situation of current region
And push is suggested.
Data processing unit, data evaluation unit and data storage cell are all set in Cloud Server；Data processing list
Member is connected with data acquisition unit wireless communication.
The working method of the above-mentioned behavior guidance analysis system based on context aware, comprising the following steps:
S1. stream of people's data and current face's characteristic in current region entrance and its exit are obtained；
In the present embodiment, in step S1, the specific steps are as follows:
S101. after the light receiving device of correlation type optical sensor detects that optical path is blocked, a switch control signal is exported,
It triggers 2 groups of stream of peoples and counts camera；
The S102.2 group stream of people counts camera and runs simultaneously, and in real time identifies the image of shooting, obtains stream of people's number
According to, and the image of shooting is subjected to pretreatment and generates current face's characteristic；
S103. stream of people's data of identification and current face's characteristic are uploaded to data processing unit.
S2. the eye movement data of the personnel on current region product periphery is obtained；
S3. the face characteristic data of the personnel in current region are obtained；
S4. by stream of people's data, current face's characteristic, eye movement data and the face characteristic number in step S1-S3
It analyzes, and is exported just according to recognition of face, face alignment, facial Expression Analysis, the analysis of sight focus and motion profile point is carried out
Handle data；
In the present embodiment, in step S4, the analysis of sight focus is carried out by eye movement data, passes through current face
Characteristic and face characteristic data carry out recognition of face, face alignment and facial Expression Analysis, pass through current face's characteristic
According to and face characteristic data and auxiliary data carry out motion trail analysis；Auxiliary data includes turning for laser scanner output
It is changed to the range information of polar form, further includes the behavior act and physiological status of each personnel of temperature sensor output.
In the present embodiment, in step S4, when carrying out recognition of face, face is carried out to the face characteristic data of acquisition first
Detection；Specific step is as follows for Face datection:
S401. the input picture containing face characteristic data is pre-processed, to obtain the first light of input picture
Image and pretreatment image are compensated, pretreatment image includes area of skin color and non-area of skin color；
S402. edge detection process is carried out to pretreatment image, obtains the length of edge inspection area and edge inspection area
Angle value, width value and length-width ratio, and round area to be tested is obtained according to length value, width value and length-width ratio；In this step,
Edge detection process is carried out to pretreatment image, obtains edge inspection area；Then obtain edge inspection area length value,
Width value and length-width ratio choose edge inspection area of the length-width ratio in default value section as initial profile region；
Then using the center in initial profile region as the center of circle, round area to be tested is obtained, wherein the diameter of round area to be tested
It is 1.1 to 1.5 times of the maximum value among the length value and width value in initial profile region.
S403. area of skin color extension process is carried out to the pretreatment image in round area to be tested coverage area, obtained
First facial contour；In this step, it is uniformly arranged luminous point in the pretreatment image in round area to be tested coverage area,
Then round area to be tested is divided into several fan-shaped regions, then moves luminous point step by step in fan-shaped region, detection light
Point is every to move whether the pixel to move a step is located at area of skin color, and the pixel adjacent with the pixel of area of skin color is located at is labeled as
Area of skin color in round area to be tested coverage area is finally fitted by area of skin color using smoothed curve, forms institute
State the first facial contour.
S404. in round area to be tested coverage area the first light compensation image carry out light compensation deals and
Face Detection obtains the second facial contour；In this step, the first light in round area to be tested coverage area is compensated
Image carries out light compensation deals, obtains the second light and compensates image, then carries out colour of skin inspection to the second light compensation image
It surveys, obtains Face Detection image, wherein Face Detection image includes area of skin color and non-area of skin color, then will be round to be checked
The area of skin color surveyed in area coverage is fitted using smoothed curve, eventually forms second facial contour.
S405. merge the first facial contour and the second facial contour to get to facial image needed for Face datection；This
In step, the first human face region of the first facial contour encirclement and the second face area of the second facial contour encirclement are obtained respectively
Then domain obtains facial image in the union of the first human face region and the second human face region institute coverage area.
It can effectively avoid making due to blocking by the facial image that the method for detecting human face of step S401-S405 obtains
At shade caused by during the detection colour of skin human face data loss, improve the accuracy rate and detection speed of Face datection
Degree.
S5. the first processing data in obtaining step S4 carry out the assessment of product attention rate, consuming capacity assessment and consumption and practise
Used assessment, establishes or improves demographic data library and regional database, then exports and save the level point of the product of current region
Cloth situation and push are suggested.
In the present embodiment, in step S5, demographic data library includes multiple individual databases.
Each individual database includes gender, age, consumption number of times, consuming capacity and the consumption habit of current persons,
It further include unique user identifier；User identifier and the face picture of current persons correspond；The age of current persons can be with
It is obtained according to the data containing face characteristic, specifically can refer to that application No. is CN201610857697.3, entitled based on convolution
The prior art of the facial image age estimation method of neural network, details are not described herein again.
Regional database includes the level distribution situation in the place of current region, area and product, further includes for current
The push suggestion in region；The level distribution situation of product is closed by the product of each product in unit time or unit flow of the people
Note degree obtains；Product attention rate is obtained by the sight focus of current production in unit time or unit flow of the people；Push is built
View includes the suggestion of product ornaments and product purchasing suggestion of current region.
The present invention is not limited to above-mentioned optional embodiment, anyone can obtain other under the inspiration of the present invention
Various forms of products.Above-mentioned specific embodiment should not be understood the limitation of pairs of protection scope of the present invention, guarantor of the invention
Shield range should be subject to be defined in claims, and specification can be used for interpreting the claims.
Claims (10)
1. a kind of behavior guidance analysis system based on context aware, it is characterised in that: include:
Data acquisition unit is also used to adopt for acquiring the face feature data and eye movement data of the human body of current region
Collect stream of people's data of current region；
Data processing unit, for carrying out recognition of face, face alignment, face table after obtaining the data that data acquisition unit acquires
Mutual affection analysis, the analysis of sight focus and motion trail analysis；
Data evaluation unit, for carrying out the assessment of product attention rate, consuming capacity after obtaining the data that data processing unit exports
Assessment and consumption habit assessment, the level distribution situation and push for being also used to export the product of current region are suggested.
Data storage cell, for establishing demographic data library and regional database；Demographic data library is 1 storage with each personnel
Unit, for storing face feature, consuming capacity, consumption habit and the consumption number of times of current persons；Regional database is with each
Region is 1 storage cell, for storing sales situation, stream of people's data, product level distribution situation and the push of current region
It is recommended that；
Data processing unit, data evaluation unit and the data storage cell is all set in Cloud Server；The number
It is connected according to processing unit and data acquisition unit wireless communication.
2. the behavior guidance analysis system according to claim 1 based on context aware, it is characterised in that: the data
Acquisition unit includes correlation type photoelectric sensor, laser scanner, temperature sensor and the camera being arranged in current region；Institute
For scanning the three-D profile of personnel, position and motion state in current region, output can be converted to the laser scanner stated
The range information of polar form；The camera for realizing the face characteristic data of personnel in current region acquisition, and
The state that the data of matching laser scanner output are each personnel is described；The temperature sensor is for detecting current region
The shell temperature of interior personnel and the record of physiological characteristic, and work as in the data judging space of combining laser scanning instrument and camera output
The behavior act and physiological status of personnel in forefoot area.
3. the behavior guidance analysis system according to claim 2 based on context aware, it is characterised in that: described to penetrating
Type photoelectric sensor is 2, is respectively arranged at the outlet of current region and the entrance of current region；The camera includes 2
Group is set to the outlet of current region and the entrance of current region, and the shooting direction that 2 groups of stream of peoples count camera is opposite；It is each right
Emitting photoelectric sensor triggers corresponding stream of people's statistics camera and takes pictures and identify face number, i.e., when optical path is blocked
Stream of people's data of the outlet of current region or the entrance of current region are obtained, while the stream of people counts camera and obtains current face's feature
Data.
4. the behavior guidance analysis system according to claim 3 based on context aware, it is characterised in that: the camera
It further include the eye movement camera for being set to the product periphery of current region；The eye movement camera is for detecting current use
The eye movement at family obtains eye movement data.
5. the behavior guidance analysis system according to claim 4 based on context aware, it is characterised in that: the camera
It further include multiple track cameras for being set to current region top；Each track camera carries out the face within the scope of current shooting
The acquisition of characteristic.
6. the working method of the behavior guidance analysis system according to any one of claims 1 to 5 based on context aware, special
Sign is: the following steps are included:
S1. stream of people's data and current face's characteristic in current region entrance and its exit are obtained；
S2. the eye movement data of the personnel on current region product periphery is obtained；
S3. the face characteristic data of the personnel in current region are obtained；
S4. by stream of people's data, current face's characteristic, eye movement data and the face characteristic data in step S1-S3 into
Row recognition of face, face alignment, facial Expression Analysis, the analysis of sight focus and motion profile point analysis, and export just processing
Data；
S5. the first processing data in obtaining step S4 carry out the assessment of product attention rate, consuming capacity assessment and consumption habit and comment
Estimate, establish or improve demographic data library and regional database, then exports and save the level distribution feelings of the product of current region
Condition and push are suggested.
7. the working method of the behavior guidance analysis system according to claim 6 based on context aware, it is characterised in that:
In step S1, the specific steps are as follows:
S101. after the light receiving device of correlation type optical sensor detects that optical path is blocked, a switch control signal, triggering 2 are exported
The group stream of people counts camera；
The S102.2 group stream of people counts camera and runs simultaneously, and in real time identifies the image of shooting, obtains stream of people's data, and will
The image of shooting carries out pretreatment and generates current face's characteristic；
S103. stream of people's data of identification and current face's characteristic are uploaded to data processing unit.
8. the working method of the behavior guidance analysis system according to claim 6 based on context aware, it is characterised in that:
In the step S4, the analysis of sight focus is carried out by eye movement data, passes through current face's characteristic and face
Characteristic carries out recognition of face, face alignment and facial Expression Analysis, passes through current face's characteristic and face characteristic number
According to and auxiliary data carry out motion trail analysis；The auxiliary data include laser scanner output can be exchanged into polar coordinates
The range information of form further includes the behavior act and physiological status of each personnel of temperature sensor output.
9. the working method of the behavior guidance analysis system according to claim 6 based on context aware, it is characterised in that:
In step S4, when carrying out recognition of face, Face datection is carried out to the face characteristic data of acquisition first；The Face datection
Specific step is as follows:
S401. the input picture containing face characteristic data is pre-processed, to obtain the first light compensation of input picture
Image and pretreatment image, the pretreatment image include area of skin color and non-area of skin color；
S402. edge detection process is carried out to pretreatment image, obtain edge inspection area and edge inspection area length value,
Width value and length-width ratio, and round area to be tested is obtained according to the length value, width value and length-width ratio；
S403. area of skin color extension process is carried out to the pretreatment image in round area to be tested coverage area, obtains first
Facial contour；
S404. light compensation deals are carried out to the first light compensation image in round area to be tested coverage area and the colour of skin is examined
It surveys, obtains the second facial contour；
S405. merge the first facial contour and the second facial contour to get to facial image needed for Face datection.
10. the working method of the behavior guidance analysis system according to claim 6 based on context aware, feature exist
In: in step S5, demographic data library includes multiple individual databases；Each individual database include current persons gender,
Age, consumption number of times, consuming capacity and consumption habit further include unique user identifier；The user identifier and work as forefathers
The face picture of member corresponds；Regional database includes the level distribution situation in the place of current region, area and product, also
Including the push suggestion for current region；The level distribution situation of the product passed through in unit time or unit flow of the people
The product attention rate of each product obtains；The product attention rate passes through current production in unit time or unit flow of the people
Sight focus obtains；The suggestion of product ornaments and product purchasing suggestion including current region are suggested in the push.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810818856.8A CN109087133A (en) | 2018-07-24 | 2018-07-24 | A kind of behavior guidance analysis system and its working method based on context aware |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810818856.8A CN109087133A (en) | 2018-07-24 | 2018-07-24 | A kind of behavior guidance analysis system and its working method based on context aware |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109087133A true CN109087133A (en) | 2018-12-25 |
Family
ID=64838388
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810818856.8A Pending CN109087133A (en) | 2018-07-24 | 2018-07-24 | A kind of behavior guidance analysis system and its working method based on context aware |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109087133A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112857357A (en) * | 2021-01-11 | 2021-05-28 | 李高云 | Trajectory movement analysis system based on data visualization |
| CN113506132A (en) * | 2021-07-06 | 2021-10-15 | 树蛙信息科技(南京)有限公司 | Method and device for determining offline attention degree |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201033908A (en) * | 2009-03-12 | 2010-09-16 | Micro Star Int Co Ltd | System and method for counting people flow |
| KR20120108306A (en) * | 2011-03-23 | 2012-10-05 | (주)큐앤솔브 | Method and system for face recongnition based advertisment |
| CN106934650A (en) * | 2016-11-28 | 2017-07-07 | 深圳网猫科技有限公司 | A kind of advertisement machine business diagnosis method and device |
| CN107016321A (en) * | 2016-01-28 | 2017-08-04 | 青岛海尔智能技术研发有限公司 | Commercial cabinet personnel flow detection statistical method |
| CN107301578A (en) * | 2016-04-15 | 2017-10-27 | 上海新飞凡电子商务有限公司 | Obtain and recognize the method and its device of customer information |
| CN107451861A (en) * | 2017-07-27 | 2017-12-08 | 中兴软创科技股份有限公司 | A kind of method of user's online feature recognition under big data |
| CN107463608A (en) * | 2017-06-20 | 2017-12-12 | 上海汇尔通信息技术有限公司 | A kind of information-pushing method and system based on recognition of face |
| CN107958390A (en) * | 2017-11-30 | 2018-04-24 | 重庆云邮天下信息技术有限公司 | A kind of unattended shop consumer consumption behavior analysis method and system |
| CN108280368A (en) * | 2018-01-22 | 2018-07-13 | 北京腾云天下科技有限公司 | On a kind of line under data and line data correlating method and computing device |
| US10460330B1 (en) * | 2018-08-09 | 2019-10-29 | Capital One Services, Llc | Intelligent face identification |
-
2018
- 2018-07-24 CN CN201810818856.8A patent/CN109087133A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201033908A (en) * | 2009-03-12 | 2010-09-16 | Micro Star Int Co Ltd | System and method for counting people flow |
| KR20120108306A (en) * | 2011-03-23 | 2012-10-05 | (주)큐앤솔브 | Method and system for face recongnition based advertisment |
| CN107016321A (en) * | 2016-01-28 | 2017-08-04 | 青岛海尔智能技术研发有限公司 | Commercial cabinet personnel flow detection statistical method |
| CN107301578A (en) * | 2016-04-15 | 2017-10-27 | 上海新飞凡电子商务有限公司 | Obtain and recognize the method and its device of customer information |
| CN106934650A (en) * | 2016-11-28 | 2017-07-07 | 深圳网猫科技有限公司 | A kind of advertisement machine business diagnosis method and device |
| CN107463608A (en) * | 2017-06-20 | 2017-12-12 | 上海汇尔通信息技术有限公司 | A kind of information-pushing method and system based on recognition of face |
| CN107451861A (en) * | 2017-07-27 | 2017-12-08 | 中兴软创科技股份有限公司 | A kind of method of user's online feature recognition under big data |
| CN107958390A (en) * | 2017-11-30 | 2018-04-24 | 重庆云邮天下信息技术有限公司 | A kind of unattended shop consumer consumption behavior analysis method and system |
| CN108280368A (en) * | 2018-01-22 | 2018-07-13 | 北京腾云天下科技有限公司 | On a kind of line under data and line data correlating method and computing device |
| US10460330B1 (en) * | 2018-08-09 | 2019-10-29 | Capital One Services, Llc | Intelligent face identification |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112857357A (en) * | 2021-01-11 | 2021-05-28 | 李高云 | Trajectory movement analysis system based on data visualization |
| CN112857357B (en) * | 2021-01-11 | 2022-05-17 | 北京卓信智恒数据科技股份有限公司 | Trajectory movement analysis system based on data visualization |
| CN113506132A (en) * | 2021-07-06 | 2021-10-15 | 树蛙信息科技(南京)有限公司 | Method and device for determining offline attention degree |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101140533B1 (en) | Method and system for recommending a product based upon skin color estimated from an image | |
| KR102266361B1 (en) | Devices, systems and methods of virtualizing a mirror | |
| CN108960937B (en) | Advertisement sending method of the application based on eye movement tracer technique of AR intelligent glasses | |
| US20220031068A1 (en) | Clothing registration device and clothing recommendation device, and online system comprising same | |
| US7522768B2 (en) | Capture and systematic use of expert color analysis | |
| US8908928B1 (en) | Body modeling and garment fitting using an electronic device | |
| CN108921051A (en) | Pedestrian's Attribute Recognition network and technology based on Recognition with Recurrent Neural Network attention model | |
| US20190362134A1 (en) | Makeup evaluation system and operating method thereof | |
| CN105662348A (en) | Novel skin detection system based on smart phone and auxiliary product selection system | |
| JP2006142005A (en) | Skin condition diagnostic system and beauty counseling system | |
| KR20190082048A (en) | Method and device to recommend customer item based on visual information | |
| CN109087133A (en) | A kind of behavior guidance analysis system and its working method based on context aware | |
| JP7082216B2 (en) | Impact measurement methods and devices using social networks | |
| CN109614925A (en) | Dress ornament attribute recognition approach and device, electronic equipment, storage medium | |
| CN108596730A (en) | Processing method, device and the smart machine of dress ornament information | |
| CN108363964A (en) | A kind of pretreated wrinkle of skin appraisal procedure and system | |
| CN109829940A (en) | A kind of method and system of the measurement garment dimension based on machine vision | |
| CN110503457A (en) | Analysis method and device, storage medium, the computer equipment of user satisfaction | |
| KR20160095792A (en) | Skin Analysis Services system and method using a skin analyzer | |
| Modi et al. | Real-time camera-based eye gaze tracking using convolutional neural network: a case study on social media website | |
| CN108851833A (en) | Smart pier glass and its training method based on machine learning training algorithm | |
| Huang et al. | A cloud-based intelligent skin and scalp analysis system | |
| KR20200107488A (en) | Virtual makeup composition processing method | |
| CN110321782A (en) | A kind of system detecting characteristics of human body's signal | |
| CN110279406A (en) | A kind of touchless pulse frequency measurement method and device based on camera |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181225 |