CN110458140A - Site satisfaction evaluation method and apparatus based on Expression Recognition - Google Patents
Site satisfaction evaluation method and apparatus based on Expression Recognition Download PDFInfo
- Publication number
- CN110458140A CN110458140A CN201910767413.5A CN201910767413A CN110458140A CN 110458140 A CN110458140 A CN 110458140A CN 201910767413 A CN201910767413 A CN 201910767413A CN 110458140 A CN110458140 A CN 110458140A
- Authority
- CN
- China
- Prior art keywords
- expression recognition
- site
- model
- client
- image
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
Site satisfaction evaluation method and apparatus provided by the invention based on Expression Recognition, the human face photo of two time points when entering site by obtaining client and at the end of transacting business, facial expression recognition processing is carried out respectively, obtain facial expression recognition result of the client when entering site and at the end of transacting business, based on the facial expression recognition result and its situation of change, determine the satisfaction evaluation value that the client services site, satisfaction evaluation value can be obtained in the case where client is noninductive, operation without client, realize noninductive evaluation, improve customer experience.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of site satisfaction evaluation methods based on Expression Recognition
And device.
Background technique
Satisfaction is a kind of psychological condition, refers to subjective assessment of the people to one section of Relationship Quality.It is the demand of client
Pleasant feeling after being satisfied is client to acquired reality after the expectation in advance of product or service and actual use product or service
The relativeness of impression.If measuring this psychological condition with number, this number is just called satisfaction, and customer satisfaction is visitor
The primary condition of family loyalty.By evaluating customer satisfaction, service organization can be helped to improve service quality.
Currently, such as financial institution (such as bank, securities broker company, insurance company), customer service mechanism (customer service of such as manufacturer),
The mode that the service organizations such as administrative body, government (such as tax hall) carry out satisfaction evaluation mainly completes industry in client
After business prompt client select on satisfaction selection device accordingly evaluate (as it is very satisfied, satisfied, be unsatisfied with etc. it is several
A grade), satisfaction information acquisition is completed, still, this satisfaction evaluation mode needs client to play an active part in, increases visitor
The burden at family is experienced not good enough.
Summary of the invention
For the problems of the prior art, the present invention provide a kind of site satisfaction evaluation method based on Expression Recognition,
Device, electronic equipment and computer readable storage medium can at least be partially solved problems of the prior art.
To achieve the goals above, the present invention adopts the following technical scheme:
In a first aspect, providing a kind of site satisfaction evaluation method based on Expression Recognition, comprising:
It obtains facial image when each client enters site and is stored in database；
Obtain facial image at the end of the business handling of a client；
Facial image carries out images match and obtains the client entering site in the database at the end of according to the business handling
When facial image；
Facial image at the end of facial image when entering site of the client and the business handling is inputted into pre- instruction respectively
Experienced Expression Recognition model obtain the client enter site when facial expression recognition result and business handling at the end of
Facial expression recognition result；
According to the client enter site when facial expression recognition result and business handling at the end of human face expression
Satisfaction of the recognition result evaluation client to site.
Further, further includes:
Respectively to this enter site when facial image and the business handling at the end of facial image pre-process.
Further, this respectively to this enter site when facial image and the business handling at the end of facial image carry out
Pretreatment, comprising:
Using OpenCv respectively to this enter site when facial image and the business handling at the end of facial image carry out
It cuts, sharpen, overturning processing, facial image and multiple treated business handlings when obtaining multiple treated to enter site
At the end of facial image；
Remold multiple respectively using difference arithmetic treated when entering site facial image and multiple treated industry
Facial image obtains facial image when entering site and multiple remodelings after multiple remodelings of pre-set dimension at the end of business is handled
Facial image at the end of business handling afterwards.
Further, the Expression Recognition model of the pre-training is convolutional neural networks model.
Further, further includes:
Construct convolutional neural networks model；
The convolutional neural networks model is trained to obtain the expression of the pre-training using the image pattern of known label
Identification model；
Wherein, in the image pattern of the known label, each image pattern includes an image and a label, the mark
Label indicate the corresponding expression of the image.
Further, which is trained to obtain this pre- to the convolutional neural networks model
Trained Expression Recognition model, comprising:
Image in each image pattern is inputted into the convolutional neural networks model and obtains Expression Recognition result；
Expression Recognition result label corresponding with the image is compared；
The parameter that convolutional neural networks model is adjusted according to comparison result, obtains the Expression Recognition model of the pre-training.
Further, further includes:
The Expression Recognition model of the pre-training is tested using the test sample of known label, and by the defeated of the model
It is used as test result out；
Based on the test result and the corresponding known label of the test sample, judge that the Expression Recognition model of the pre-training is
It is no to meet preset requirement；
If so, using "current" model as the object module for being used for Expression Recognition；
If it is not, then being optimized to "current" model and/or re-starting model training using updated training sample set.
Second aspect provides a kind of site satisfaction evaluation device based on Expression Recognition, comprising:
Facial image obtains module when into site, obtains facial image when each client enters site and is stored in database
In；
Facial image obtains module at the end of business handling, obtains facial image at the end of the business handling of a client；
Images match module, according to the business handling at the end of facial image carry out images match in the database and be somebody's turn to do
Facial image when client enters site；
Expression Recognition module, by this enter site when facial image and the business handling at the end of facial image difference it is defeated
The Expression Recognition model for entering pre-training obtains facial expression recognition result and business handling knot of the client when entering site
Facial expression recognition result when beam；
Satisfaction evaluation module, according to facial expression recognition result and business handling knot of the client when entering site
The satisfaction of facial expression recognition evaluation of result client when beam to business service.
Further, further includes:
Preprocessing module, respectively to this enter site when facial image and the business handling at the end of facial image carry out
Pretreatment.
Further, which includes:
Image processing unit, using OpenCv respectively to this enter site when facial image and the business handling at the end of
Facial image cut, sharpened, overturning processing, facial image and multiple processing when obtaining multiple treated to enter site
Facial image at the end of business handling afterwards；
Image remolds unit, remolds multiple respectively using difference arithmetic treated when entering site facial image and more
Facial image obtains facial image when entering site after multiple remodelings of pre-set dimension at the end of business handling that treated
And facial image at the end of the business handling after multiple remodelings.
Further, the Expression Recognition model of the pre-training is convolutional neural networks model.
Further, further includes:
Model construction module constructs convolutional neural networks model；
Model training module is trained this to the convolutional neural networks model using the image pattern of known label
The Expression Recognition model of pre-training；
Wherein, in the image pattern of the known label, each image pattern includes an image and a label, the mark
Label indicate the corresponding expression of the image.
Further, which includes:
Image in each image pattern is inputted the convolutional neural networks model and obtains Expression Recognition by Expression Recognition unit
As a result；
Expression Recognition result label corresponding with the image is compared by comparing unit；
Parameter adjustment unit adjusts the parameter of convolutional neural networks model according to comparison result, obtains the table of the pre-training
Feelings identification model.
Further, further includes:
Model measurement module tests the Expression Recognition model of the pre-training using the test sample of known label,
And using the output of the model as test result；
Model judgment module is based on the test result and the corresponding known label of the test sample, judges the pre-training
Whether Expression Recognition model meets preset requirement；
Model output module, if the Expression Recognition model of pre-training meets preset requirement, using "current" model as being used for
The object module of Expression Recognition；
Model adjusts module, if the Expression Recognition model of pre-training does not meet preset requirement, carries out to "current" model excellent
Change and/or re-starts model training using updated training sample set.
The third aspect, provides a kind of electronic equipment, including memory, processor and storage on a memory and can handled
The computer program run on device, the processor realize that the above-mentioned site satisfaction based on Expression Recognition is commented when executing the program
The step of valence method.
Fourth aspect provides a kind of computer readable storage medium, is stored thereon with computer program, the computer program
The step of above-mentioned site satisfaction evaluation method based on Expression Recognition is realized when being executed by processor.
Site satisfaction evaluation method and apparatus provided by the invention based on Expression Recognition, this method comprises: obtaining each
It facial image and is stored in database when client enters site；Obtain facial image at the end of the business handling of a client；According to
Facial image carries out images match in the database and obtains facial image when the client enters site at the end of the business handling；It will
The client into site when facial image and the business handling at the end of facial image input the expression of pre-training respectively and know
Human face expression at the end of other model obtains facial expression recognition result and business handling of the client when entering site is known
Other result；According to the client enter site when facial expression recognition result and business handling at the end of human face expression know
Satisfaction of the other evaluation of result client to site.Wherein, when entering site by obtaining client and two at the end of transacting business
The human face photo of a time point carries out facial expression recognition processing respectively, and obtaining client terminates when entering site with transacting business
When facial expression recognition as a result, be based on the facial expression recognition result and its situation of change, determine the client to site
The satisfaction evaluation value of service can obtain satisfaction evaluation value in the case where client is noninductive, without the operation of client, realize
Noninductive evaluation, improves customer experience.
For above and other objects, features and advantages of the invention can be clearer and more comprehensible, preferred embodiment is cited below particularly,
And cooperate institute's accompanying drawings, it is described in detail below.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the application
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.In the accompanying drawings:
Fig. 1 is the system architecture for implementing the site satisfaction evaluation method provided in an embodiment of the present invention based on Expression Recognition
Schematic diagram；
Fig. 2 is the flow diagram one of site satisfaction evaluation method of the embodiment of the present invention based on Expression Recognition；
Fig. 3 is the flow diagram two of site satisfaction evaluation method of the embodiment of the present invention based on Expression Recognition；
Fig. 4 shows the step S10 and step of site satisfaction evaluation method of the embodiment of the present invention based on Expression Recognition
S20；
Fig. 5 is the structural block diagram one of the site satisfaction evaluation device based on Expression Recognition in the embodiment of the present invention；
Fig. 6 is the structural block diagram two of the site satisfaction evaluation device based on Expression Recognition in the embodiment of the present invention；
Fig. 7 is the structure chart of electronic equipment of the embodiment of the present invention.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
The embodiment of the application a part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
Member's every other embodiment obtained without making creative work, all should belong to the model of the application protection
It encloses.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
It should be noted that term " includes " and " tool in the description and claims of this application and above-mentioned attached drawing
Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing a series of steps or units
Process, method, system, product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include without clear
Other step or units listing to Chu or intrinsic for these process, methods, product or equipment.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Currently, such as financial institution (such as bank, securities broker company, insurance company), customer service mechanism (customer service of such as manufacturer),
The mode that the service organizations such as administrative body, government (such as tax hall) carry out satisfaction evaluation mainly completes industry in client
After business prompt client select on satisfaction selection device accordingly evaluate (as it is very satisfied, satisfied, be unsatisfied with etc. it is several
A grade), satisfaction information acquisition is completed, still, this satisfaction evaluation mode needs client to play an active part in, increases visitor
The burden at family is experienced not good enough.
At least partly to solve the above-mentioned technical problems in the prior art, the embodiment of the present invention provides a kind of based on table
Feelings identification site satisfaction evaluation method, apparatus, electronic equipment and computer readable storage medium, by obtain client into
The human face photo of two time points when point of presence and at the end of transacting business, carries out facial expression recognition processing respectively, obtains client
Facial expression recognition when entering site and at the end of transacting business is as a result, be based on the facial expression recognition result and its change
Change situation, determines the satisfaction evaluation value that the client services site, satisfaction can be obtained in the case where client is noninductive
Evaluation of estimate realizes noninductive evaluation without the operation of client, improves site to the customer experience of site satisfaction evaluation, and can
To custom-configure by the collection to service organization's business handling information and to satisfaction evaluation, flexibly obtain various full
Meaning degree evaluation of estimate, to improve the respective services quality of service organization.
Fig. 1 is the system architecture for implementing the site satisfaction evaluation method provided in an embodiment of the present invention based on Expression Recognition
Schematic diagram.As shown in Figure 1, the Service Process Server can be imaged at least one cabinet face camera and at least one gate
Head communication connection, for client when entering site, gate camera acquires the facial image of client, and is stored in database, this field
Technical staff is it is understood that the database may be provided in processing server, or is arranged in other servers, other
Server and processing server communicate to connect, and client is in service organization's transacting business, by business personnel (or teller or service
Personnel) Service Process Server (such as computer, laptop, smart phone, the tablet computer and portable wearable that use
Equipment etc.) at Installation cabinet face camera, acquire the human face photo of client, and the human face photo of acquisition is sent to business processing clothes
Be engaged in device, Service Process Server can receive the human face photo of client online, online or offline to the human face photo of client into
Row pretreatment, obtains facial image at the end of the business handling of a client；Facial image is in number at the end of according to the business handling
The facial image when client enters site is obtained according to images match is carried out in library；By the client enter site when facial image with
And the Expression Recognition model that facial image inputs pre-training respectively at the end of the business handling obtains the client when entering site
Facial expression recognition result and business handling at the end of facial expression recognition result；According to the client when entering site
Facial expression recognition result and business handling at the end of satisfaction to site of the facial expression recognition evaluation of result client
Degree.
Fig. 2 is the flow diagram one of site satisfaction evaluation method of the embodiment of the present invention based on Expression Recognition.Such as Fig. 2
Shown, the site satisfaction evaluation method based on Expression Recognition of being somebody's turn to do may include the following contents:
Step S100: it obtains facial image when each client enters site and is stored in database；
Specifically, image is acquired according to preset interval by being mounted on the gate camera at site gate, and by face figure
As in deposit database.
It is worth noting that since gate camera is according to preset interval acquisition image, so, it, can for same user
The image that multiple clients enter gate can be acquired, at the image storing data library for acquiring gate camera, can be passed through
Image recognition processing technology comes out the duplicate optical sieving comprising same client, by one or the clarity that the time is earliest
Highest one facial image entered when site as the client.
Optionally, many service networks are provided with automatically-controlled door at present, sense someone by technologies such as infrared sensings and lean on
Automatic door opening when close can also open trigger signal triggering camera in the embodiment of the present invention according to automatically-controlled door and open acquisition figure
Picture can make camera not work when no client enters with this, save electric energy and can reduce amount of images.
It is of course also possible to pass through suitable position setting human body sensing sensor (such as infrared sensing near gate camera
Device etc.), it is close for sensing human body, and opened using sensing signal triggering gate camera, to acquire the image that client enters.
Step S200: facial image at the end of the business handling of a client is obtained.
Specifically, when client receives to service, using camera according to the image of preset interval acquisition client, and know in real time
Face in other image, when recognizing client and changing, then be a upper client finish to service next client into
Facial image when point of presence identifies facial image at the end of the business handling of a client by this principle.
Alternatively it is also possible to, when business personnel terminates an operation flow, trigger an image in business personnel's transacting business
Signal is obtained to camera, camera acquires a customer image, as facial image of client at the end of business handling.
Step S300: at the end of according to the business handling facial image carry out in the database images match obtain it is described
Facial image when client enters site；
Specifically, the feature string of facial image at the end of being handled according to the client traffic goes screening in database to have phase
With the facial image of feature string, client facial image when entering site is obtained.
Step S400: by facial image at the end of facial image when entering site of the client and the business handling
The Expression Recognition model for inputting pre-training respectively obtains facial expression recognition result and industry of the client when entering site
The facial expression recognition result being engaged at the end of handling.
It will be appreciated by persons skilled in the art that people can show different facial expressions under different psychologic status
And limb action.For example people's eyebrow is raised up, is crowded together, he, which is particularly likely that, is in frightened, worry or worry；Nose
Hole is turned up, and lip is tightly closed lightly, and indicates whether or not there is the anger of method control；Chin raises, the self-accusation of mouth sagging table；It is simple eye it is micro- narrow, unilateral mouth
Angle is micro- to choose, and table is not considered worth doing, scorned.It is therefore possible to use artificial intelligence (AI) technology, pass through mood known to the magnanimity chosen in advance
The facial image training of label obtains an Expression Recognition model, by identifying client in image with trained Expression Recognition model
Expression.
Step S500: according to the client enter site when facial expression recognition result and business handling at the end of
Facial expression recognition evaluation of result described in client to the satisfaction of site.
In the embodiment of the present invention, facial expression recognition result includes: generic expression, positive mood and negative emotions.
Specifically, by indignation, detest, fear, is happy, sad, surprised and naturally more than this 7 kinds of expression labels belong to respectively
Three kinds of recognition results.Wherein, indignation, detest, fear to belong to negative emotions with sad, it is happy to belong to positive mood, it is surprised
With belong to generic expression naturally.
When client is to when the satisfaction evaluation value of service is by entering site to client and two at the end of transacting business
The facial expression recognition result of point is compared to obtain.Specifically, digitized processing is carried out to the facial expression recognition result,
Negative emotions assignment -1, generic expression assignment 0, positive mood assignment 1 are subtracted by the mood value at the end of calculating business handling
Mood value when into site, if result is negative value, then it represents that it is dissatisfied, if result is 0, then it represents that and it is general, if knot
Fruit is positive value, then it represents that satisfied.
It is worth noting that the embodiment of the present invention can be stored in the same of database by facial image when client is entered site
When, identify facial expression recognition when client enters site as a result, thereby, it is possible to reduce processing latency.It is of course also possible to
At the end of getting a client traffic and handling after facial image, then by the facial image and industry when entering site of client
Facial image input Expression Recognition model carries out image recognition at the end of business is handled, and will not be known to the client of non-transacting business with this
Facial expression recognition when it does not enter site is as a result, reduce resource consumption.
Through the above technical solution it is known that the site satisfaction provided in an embodiment of the present invention based on Expression Recognition is commented
Valence method, can be in the case where client be noninductive, based on client when entering site and human face expression at the end of transacting business
Recognition result determines that the client realizes noninductive evaluation, mention to the satisfaction evaluation value of the site without the operation of client
Customer experience is risen.
In an alternative embodiment, referring to Fig. 3, should site satisfaction evaluation method based on Expression Recognition can be with
Including the following contents:
Step S350: respectively to it is described enter site when facial image and the business handling at the end of facial image into
Row pretreatment.
Specifically, using OpenCv respectively to it is described enter site when facial image and the business handling at the end of people
Face image cut, sharpened, overturning processing, when obtaining multiple treated to enter site after facial image and multiple processing
Business handling at the end of facial image；
Remold multiple respectively using difference arithmetic treated when entering site facial image and multiple treated industry
Facial image obtains facial image when entering site and multiple remodelings after multiple remodelings of pre-set dimension at the end of business is handled
Facial image at the end of business handling afterwards.
It is worth noting that the pre-set dimension can be 48 × 48 matrix, it is also possible to 64 × 64 matrix, the present invention is real
Example is applied to this with no restriction, it is only necessary to by image preprocessing to the calculating input requirements for meeting facial expression recognition.
Wherein, by being pre-processed to facial image, it can be improved the quality of facial image, improve subsequent Expression Recognition
Accuracy.
In an alternative embodiment, the Expression Recognition model of the pre-training is convolutional neural networks (CNN) model, should
Model 7 expression labels of output are indignation respectively, detest, fear, is happy, is sad, surprised and naturally, input is after pre-processing
Facial image, export for the score value of 7 expression labels, and using the label of top score as recognition result, and according to
According to recognition result, the facial expression recognition result of client is determined.Specifically, facial expression recognition result includes: generic expression, just
Face mood and negative emotions, indignation are detested, fear to belong to negative emotions with sad, happy to belong to positive mood, it is surprised and
Naturally generic expression is belonged to.
Wherein, which may include: input layer, convolutional layer, pond layer and full articulamentum.Input
Layer is for receiving input picture；Convolutional layer is used to extract the feature of the input picture, and pond layer is used for described image feature
Carry out pond；Full articulamentum obtains expression label, the tag characterization user for classifying to the characteristics of image of Chi Huahou
Expression.
In one further embodiment, referring to fig. 4, the site satisfaction evaluation method based on Expression Recognition is somebody's turn to do may be used also
To include the following contents:
Step S10: building convolutional neural networks model；
Wherein, the convolutional neural networks program of open source can be used or call the convolutional neural networks model in matlab real
It is existing.
Step S20: the convolutional neural networks model is trained to obtain using the image pattern of known label described
The Expression Recognition model of pre-training；
Wherein, in the image pattern of the known label, each image pattern includes an image and a label, is somebody's turn to do
The corresponding expression of the tag representation image.
Specifically, the image in each image pattern is inputted into the convolutional neural networks model and obtains Expression Recognition knot
Fruit；The Expression Recognition result label corresponding to the image is compared；Convolutional Neural net is adjusted according to comparison result
The parameter of network model obtains the Expression Recognition model of the pre-training.
In an alternative embodiment, also the site satisfaction evaluation method based on Expression Recognition can also include:
The Expression Recognition model of the pre-training is tested using the test sample of known label, and by the model
Output is used as test result；
Based on the test result and the corresponding known label of the test sample, the Expression Recognition of the pre-training is judged
Whether model meets preset requirement；
If so, using "current" model as the object module for being used for Expression Recognition；
If it is not, then being optimized to "current" model and/or re-starting model training using updated training sample set.
In an alternative embodiment, being somebody's turn to do the site satisfaction evaluation method based on Expression Recognition can also include:
The photo of camera acquisition is obtained, and extracts the facial image in photo, obtains client's facial image.
Based on the same inventive concept, the embodiment of the present application also provides a kind of site satisfaction evaluation based on Expression Recognition
Device can be used to implement method described in above-described embodiment, as described in the following examples.Due to based on Expression Recognition
The principle that site satisfaction evaluation device solves the problems, such as is similar to the above method, therefore the site satisfaction based on Expression Recognition is commented
The implementation of valence device may refer to the implementation of the above method, and overlaps will not be repeated.It is used below, term " unit " or
The combination of the software and/or hardware of predetermined function may be implemented in person's " module ".Although device described in following embodiment is preferable
Ground is realized with software, but the realization of the combination of hardware or software and hardware is also that may and be contemplated.
Fig. 5 is the structural block diagram one of the site satisfaction evaluation device based on Expression Recognition in the embodiment of the present invention.Such as
Shown in Fig. 5, should site satisfaction evaluation device based on Expression Recognition when including: into site facial image obtain module 10,
Facial image obtains module 20, images match module 30, Expression Recognition module 40 and satisfaction evaluation at the end of business handling
Module 50.
Facial image obtains module 10 and obtains facial image when each client enters site and be stored in database when into site
In；
Specifically, image is acquired according to preset interval by being mounted on the gate camera at site gate, and by face figure
As in deposit database.
It is worth noting that since gate camera is according to preset interval acquisition image, so, it, can for same user
The image that multiple clients enter gate can be acquired, at the image storing data library for acquiring gate camera, can be passed through
Image recognition processing technology comes out the duplicate optical sieving comprising same client, by one or the clarity that the time is earliest
Highest one facial image entered when site as the client.
Optionally, many service networks are provided with automatically-controlled door at present, sense someone by technologies such as infrared sensings and lean on
Automatic door opening when close can also open trigger signal triggering camera in the embodiment of the present invention according to automatically-controlled door and open acquisition figure
Picture can make camera not work when no client enters with this, save electric energy and can reduce amount of images.
It is of course also possible to pass through suitable position setting human body sensing sensor (such as infrared sensing near gate camera
Device etc.), it is close for sensing human body, and opened using sensing signal triggering gate camera, to acquire the image that client enters.
Facial image at the end of the business handling of facial image acquisition module 20 one client of acquisition at the end of business handling；
Specifically, when client receives to service, using camera according to the image of preset interval acquisition client, and know in real time
Face in other image, when recognizing client and changing, then be a upper client finish to service next client into
Facial image when point of presence identifies facial image at the end of the business handling of a client by this principle.
Alternatively it is also possible to, when business personnel terminates an operation flow, trigger an image in business personnel's transacting business
Signal is obtained to camera, camera acquires a customer image, as facial image of client at the end of business handling.
Images match module 30 according to the business handling at the end of facial image carry out images match in the database and obtain
Facial image when entering site to the client；
Specifically, the feature string of facial image at the end of being handled according to the client traffic goes screening in database to have phase
With the facial image of feature string, client facial image when entering site is obtained.
Expression Recognition module 40 by it is described enter site when facial image and the business handling at the end of facial image
The Expression Recognition model for inputting pre-training respectively obtains facial expression recognition result and industry of the client when entering site
The facial expression recognition result being engaged at the end of handling；
It will be appreciated by persons skilled in the art that people can show different facial expressions under different psychologic status
And limb action.For example people's eyebrow is raised up, is crowded together, he, which is particularly likely that, is in frightened, worry or worry；Nose
Hole is turned up, and lip is tightly closed lightly, and indicates whether or not there is the anger of method control；Chin raises, the self-accusation of mouth sagging table；It is simple eye it is micro- narrow, unilateral mouth
Angle is micro- to choose, and table is not considered worth doing, scorned.It is therefore possible to use artificial intelligence (AI) technology, pass through mood known to the magnanimity chosen in advance
The facial image training of label obtains an Expression Recognition model, by identifying client in image with trained Expression Recognition model
Expression.
Satisfaction evaluation module 50 is done according to facial expression recognition result and business of the client when into site
Satisfaction of the client described in facial expression recognition evaluation of result at the end of reason to business service.
In the embodiment of the present invention, facial expression recognition result includes: generic expression, positive mood and negative emotions.
Specifically, by indignation, detest, fear, is happy, sad, surprised and naturally more than this 7 kinds of expression labels belong to respectively
Three kinds of recognition results.Wherein, indignation, detest, fear to belong to negative emotions with sad, it is happy to belong to positive mood, it is surprised
With belong to generic expression naturally.
When client is to when the satisfaction evaluation value of service is by entering site to client and two at the end of transacting business
The facial expression recognition result of point is compared to obtain.Specifically, digitized processing is carried out to the facial expression recognition result,
Negative emotions assignment -1, generic expression assignment 0, positive mood assignment 1 are subtracted by the mood value at the end of calculating business handling
Mood value when into site, if result is negative value, then it represents that it is dissatisfied, if result is 0, then it represents that and it is general, if knot
Fruit is positive value, then it represents that satisfied.
It is worth noting that the embodiment of the present invention can be stored in the same of database by facial image when client is entered site
When, identify facial expression recognition when client enters site as a result, thereby, it is possible to reduce processing latency.It is of course also possible to
At the end of getting a client traffic and handling after facial image, then by the facial image and industry when entering site of client
Facial image input Expression Recognition model carries out image recognition at the end of business is handled, and will not be known to the client of non-transacting business with this
Facial expression recognition when it does not enter site is as a result, reduce resource consumption.
Through the above technical solution it is known that the site satisfaction provided in an embodiment of the present invention based on Expression Recognition is commented
Valence device, can be in the case where client be noninductive, based on client when entering site and human face expression at the end of transacting business
Recognition result determines that the client realizes noninductive evaluation, mention to the satisfaction evaluation value of the site without the operation of client
Customer experience is risen.
In an alternative embodiment, referring to Fig. 6, should site satisfaction evaluation device based on Expression Recognition can be with
It include: preprocessing module 35.
Preprocessing module 35 respectively to it is described enter site when facial image and the business handling at the end of face figure
As being pre-processed.
Specifically, the preprocessing module 35 includes: image processing unit and image remodeling unit.
Image processing unit, using OpenCv respectively to this enter site when facial image and the business handling at the end of
Facial image cut, sharpened, overturning processing, facial image and multiple processing when obtaining multiple treated to enter site
Facial image at the end of business handling afterwards；
Image remolds unit, remolds multiple respectively using difference arithmetic treated when entering site facial image and more
Facial image obtains facial image when entering site after multiple remodelings of pre-set dimension at the end of business handling that treated
And facial image at the end of the business handling after multiple remodelings.
It is worth noting that the pre-set dimension can be 48 × 48 matrix, it is also possible to 64 × 64 matrix, the present invention is real
Example is applied to this with no restriction, it is only necessary to by image preprocessing to the calculating input requirements for meeting facial expression recognition.
Wherein, by being pre-processed to facial image, it can be improved the quality of facial image, improve subsequent Expression Recognition
Accuracy.
In an alternative embodiment, the Expression Recognition model of the pre-training is convolutional neural networks (CNN) model, should
Model 7 expression labels of output are indignation respectively, detest, fear, is happy, is sad, surprised and naturally, input is after pre-processing
Facial image, export for the score value of 7 expression labels, and using the label of top score as recognition result, and according to
According to recognition result, the facial expression recognition result of client is determined.Specifically, facial expression recognition result includes: generic expression, just
Face mood and negative emotions, indignation are detested, fear to belong to negative emotions with sad, happy to belong to positive mood, it is surprised and
Naturally generic expression is belonged to.
Wherein, which may include: input layer, convolutional layer, pond layer and full articulamentum.Input
Layer is for receiving input picture；Convolutional layer is used to extract the feature of the input picture, and pond layer is used for described image feature
Carry out pond；Full articulamentum obtains expression label, the tag characterization user for classifying to the characteristics of image of Chi Huahou
Expression.
In an alternative embodiment, being somebody's turn to do the site satisfaction evaluation device based on Expression Recognition can also include: mould
Type constructs module and model training module.
Wherein, the model construction module is for constructing convolutional neural networks model.
It is worth noting that the convolutional neural networks program of open source can be used or call the convolutional Neural net in matlab
Network model realization.
Model training module is trained to obtain using the image pattern of known label to the convolutional neural networks model
The Expression Recognition model of the pre-training；
Wherein, in the image pattern of the known label, each image pattern includes an image and a label, is somebody's turn to do
The corresponding expression of the tag representation image.
Specifically, which includes: Expression Recognition unit, comparing unit and parameter adjustment unit.
Image in each image pattern is inputted the convolutional neural networks model and obtains expression knowledge by Expression Recognition unit
Other result；
The Expression Recognition result label corresponding to the image is compared by comparing unit；
Parameter adjustment unit adjusts the parameter of convolutional neural networks model according to comparison result, obtains the table of the pre-training
Feelings identification model.
In an alternative embodiment, being somebody's turn to do the site satisfaction evaluation device based on Expression Recognition can also include: mould
Type test module, model judgment module, model output module and model adjust module.
Model measurement module tests the Expression Recognition model of the pre-training using the test sample of known label,
And using the output of the model as test result；
Model judgment module is based on the test result and the corresponding known label of the test sample, judges the pre- instruction
Whether experienced Expression Recognition model meets preset requirement；
If the Expression Recognition model of model output module pre-training meets preset requirement, using "current" model as being used for table
The object module of feelings identification；
If the Expression Recognition model of model adjustment module pre-training does not meet preset requirement, "current" model is optimized
And/or model training is re-started using updated training sample set.
In an alternative embodiment, being somebody's turn to do the site satisfaction evaluation device based on Expression Recognition can also include: figure
As extraction module, the photo of camera acquisition is obtained, and extracts the facial image in photo, obtains client's facial image.
Device, module or the unit that above-described embodiment illustrates can specifically be realized, Huo Zheyou by computer chip or entity
Product with certain function is realized.It is a kind of typical to realize that equipment is electronic equipment, specifically, electronic equipment for example can be with
For personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media player,
Any in navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment sets
Standby combination.
Electronic equipment specifically includes memory, processor and storage on a memory and can in a typical example
The computer program run on a processor, the processor realize following step when executing described program:
It obtains facial image when each client enters site and is stored in database；
Obtain facial image at the end of the business handling of a client；
Facial image carries out images match in the database and obtains client's entrance at the end of according to the business handling
Facial image when site；
Facial image at the end of facial image when entering site of the client and the business handling is inputted respectively
The Expression Recognition model of pre-training obtains facial expression recognition result and business handling knot of the client when entering site
Facial expression recognition result when beam；
According to the client enter site when facial expression recognition result and business handling at the end of face table
Satisfaction of the client described in feelings recognition result evaluation to site.
As can be seen from the above description, electronic equipment provided in an embodiment of the present invention, can be used for obtaining in the case where client is noninductive
Satisfaction evaluation value is taken, without the operation of client, noninductive evaluation is realized, improves customer experience.
Below with reference to Fig. 7, it illustrates the structural representations for the electronic equipment 600 for being suitable for being used to realize the embodiment of the present application
Figure.
As shown in fig. 7, electronic equipment 600 includes central processing unit (CPU) 601, it can be according to being stored in read-only deposit
Program in reservoir (ROM) 602 is loaded into random access storage device (RAM) from storage section 608) program in 603 and
Execute various work appropriate and processing.In RAM603, also it is stored with system 600 and operates required various programs and data.
CPU601, ROM602 and RAM603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to bus
604。
I/O interface 605 is connected to lower component: the importation 606 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 608 including hard disk etc.；
And including such as LAN card, the communications portion 609 of the network interface card of modem etc..Communications portion 609 via such as because
The network of spy's net executes communication process.Driver 610 is also connected to I/O interface 605 as needed.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 610, in order to read from thereon
Computer program be mounted as needed such as storage section 608.
Particularly, according to an embodiment of the invention, may be implemented as computer above with reference to the process of flow chart description
Software program.For example, the embodiment of the present invention includes a kind of computer readable storage medium, it is stored thereon with computer program,
The computer program realizes following step when being executed by processor:
It obtains facial image when each client enters site and is stored in database；
Obtain facial image at the end of the business handling of a client；
Facial image carries out images match in the database and obtains client's entrance at the end of according to the business handling
Facial image when site；
Facial image at the end of facial image when entering site of the client and the business handling is inputted respectively
The Expression Recognition model of pre-training obtains facial expression recognition result and business handling knot of the client when entering site
Facial expression recognition result when beam；
According to the client enter site when facial expression recognition result and business handling at the end of face table
Satisfaction of the client described in feelings recognition result evaluation to site.
As can be seen from the above description, computer readable storage medium provided in an embodiment of the present invention, can be used for noninductive in client
In the case where obtain satisfaction evaluation value realize noninductive evaluation without the operation of client, improve customer experience.
In such embodiments, which can be downloaded and installed from network by communications portion 609,
And/or it is mounted from detachable media 611.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit can be realized in the same or multiple software and or hardware when application.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method of element, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The application can describe in the general context of computer-executable instructions executed by a computer, such as program
Module.Generally, program module includes routines performing specific tasks or implementing specific abstract data types, programs, objects, group
Part, data structure etc..The application can also be practiced in a distributed computing environment, in these distributed computing environments, by
Task is executed by the connected remote processing devices of communication network.In a distributed computing environment, program module can be with
In the local and remote computer storage media including storage equipment.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.
The above description is only an example of the present application, is not intended to limit this application.For those skilled in the art
For, various changes and changes are possible in this application.All any modifications made within the spirit and principles of the present application are equal
Replacement, improvement etc., should be included within the scope of the claims of this application.
Claims (14)
1. a kind of site satisfaction evaluation method based on Expression Recognition characterized by comprising
It obtains facial image when each client enters site and is stored in database；
Obtain facial image at the end of the business handling of a client；
Facial image carries out images match and obtains the client entering site in the database at the end of according to the business handling
When facial image；
Facial image at the end of facial image when entering site of the client and the business handling is inputted into pre- instruction respectively
At the end of experienced Expression Recognition model obtains facial expression recognition result and business handling of the client when entering site
Facial expression recognition result；
According to the client enter site when facial expression recognition result and business handling at the end of human face expression know
Satisfaction of the client described in other evaluation of result to site.
2. the site satisfaction evaluation method according to claim 1 based on Expression Recognition, which is characterized in that further include:
Respectively to it is described enter site when facial image and the business handling at the end of facial image pre-process.
3. the site satisfaction evaluation method according to claim 1 based on Expression Recognition, which is characterized in that the pre- instruction
Experienced Expression Recognition model is convolutional neural networks model.
4. the site satisfaction evaluation method according to claim 3 based on Expression Recognition, which is characterized in that further include:
Construct convolutional neural networks model；
The convolutional neural networks model is trained to obtain the expression of the pre-training using the image pattern of known label
Identification model；
Wherein, in the image pattern of the known label, each image pattern includes an image and a label, the label
Indicate the corresponding expression of the image.
5. the site satisfaction evaluation method according to claim 4 based on Expression Recognition, which is characterized in that the use
The image pattern of known label is trained the convolutional neural networks model to obtain the Expression Recognition model of the pre-training,
Include:
Image in each image pattern is inputted into the convolutional neural networks model and obtains Expression Recognition result；
The Expression Recognition result label corresponding to the image is compared；
The parameter that convolutional neural networks model is adjusted according to comparison result, obtains the Expression Recognition model of the pre-training.
6. the site satisfaction evaluation method according to claim 5 based on Expression Recognition, which is characterized in that further include:
The Expression Recognition model of the pre-training is tested using the test sample of known label, and by the output of the model
As test result；
Based on the test result and the corresponding known label of the test sample, the Expression Recognition model of the pre-training is judged
Whether preset requirement is met；
If so, using "current" model as the object module for being used for Expression Recognition；
If it is not, then being optimized to "current" model and/or re-starting model training using updated training sample set.
7. a kind of site satisfaction evaluation device based on Expression Recognition characterized by comprising
Facial image obtains module when into site, obtains facial image when each client enters site and is stored in database；
Facial image obtains module at the end of business handling, obtains facial image at the end of the business handling of a client；
Images match module, according to the business handling at the end of facial image carry out in the database images match obtain it is described
Facial image when client enters site；
Expression Recognition module, facial image difference at the end of facial image when the entrance site and the business handling is defeated
The Expression Recognition model for entering pre-training obtains facial expression recognition result and business handling of the client when entering site
At the end of facial expression recognition result；
Satisfaction evaluation module terminates according to facial expression recognition result and business handling of the client when into site
When facial expression recognition evaluation of result described in client to the satisfaction of business service.
8. the site satisfaction evaluation device according to claim 7 based on Expression Recognition, which is characterized in that further include:
Preprocessing module, respectively to it is described enter site when facial image and the business handling at the end of facial image carry out
Pretreatment.
9. the site satisfaction evaluation device according to claim 7 based on Expression Recognition, which is characterized in that the pre- instruction
Experienced Expression Recognition model is convolutional neural networks model.
10. the site satisfaction evaluation device according to claim 9 based on Expression Recognition, which is characterized in that further include:
Model construction module constructs convolutional neural networks model；
Model training module is trained to obtain described using the image pattern of known label to the convolutional neural networks model
The Expression Recognition model of pre-training；
Wherein, in the image pattern of the known label, each image pattern includes an image and a label, the label
Indicate the corresponding expression of the image.
11. the site satisfaction evaluation device according to claim 10 based on Expression Recognition, which is characterized in that the mould
Type training module includes:
Image in each image pattern is inputted the convolutional neural networks model and obtains Expression Recognition knot by Expression Recognition unit
Fruit；
The Expression Recognition result label corresponding to the image is compared by comparing unit；
Parameter adjustment unit adjusts the parameter of convolutional neural networks model according to comparison result, obtains the expression of the pre-training
Identification model.
12. the site satisfaction evaluation device according to claim 11 based on Expression Recognition, which is characterized in that also wrap
It includes:
Model measurement module tests the Expression Recognition model of the pre-training using the test sample of known label, and
Using the output of the model as test result；
Model judgment module is based on the test result and the corresponding known label of the test sample, judges the pre-training
Expression Recognition model whether meet preset requirement；
Model output module, if the Expression Recognition model of pre-training meets preset requirement, using "current" model as being used for expression
The object module of identification；
Model adjust module, if the Expression Recognition model of pre-training does not meet preset requirement, to "current" model optimize and/
Or model training is re-started using updated training sample set.
13. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor is realized as claimed in any one of claims 1 to 6 based on table when executing described program
The step of site satisfaction evaluation method of feelings identification.
14. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program quilt
Processor realizes the step of the site satisfaction evaluation method as claimed in any one of claims 1 to 6 based on Expression Recognition when executing
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910767413.5A CN110458140A (en) | 2019-08-20 | 2019-08-20 | Site satisfaction evaluation method and apparatus based on Expression Recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910767413.5A CN110458140A (en) | 2019-08-20 | 2019-08-20 | Site satisfaction evaluation method and apparatus based on Expression Recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110458140A true CN110458140A (en) | 2019-11-15 |
Family
ID=68487916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910767413.5A Pending CN110458140A (en) | 2019-08-20 | 2019-08-20 | Site satisfaction evaluation method and apparatus based on Expression Recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110458140A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368646A (en) * | 2020-02-15 | 2020-07-03 | 快优智能技术有限公司 | Intelligent counter expression interaction method |
| CN111639549A (en) * | 2020-05-12 | 2020-09-08 | 中信银行股份有限公司 | Method and device for determining service satisfaction degree and electronic equipment |
| CN111687863A (en) * | 2020-06-24 | 2020-09-22 | 中国银行股份有限公司 | Network point robot self-adjusting method and device |
| CN111814649A (en) * | 2020-06-30 | 2020-10-23 | 平安国际智慧城市科技股份有限公司 | Customer service expression practicing method based on artificial intelligence and related equipment |
| CN112907306A (en) * | 2021-05-06 | 2021-06-04 | 北京惠朗时代科技有限公司 | Customer satisfaction judging method and device |
| CN113921098A (en) * | 2021-10-14 | 2022-01-11 | 江苏木盟智能科技有限公司 | Medical service evaluation method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107194316A (en) * | 2017-04-20 | 2017-09-22 | 广东数相智能科技有限公司 | A kind of evaluation method of mood satisfaction, apparatus and system |
| US20190034706A1 (en) * | 2010-06-07 | 2019-01-31 | Affectiva, Inc. | Facial tracking with classifiers for query evaluation |
| CN109858410A (en) * | 2019-01-18 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Service evaluation method, apparatus, equipment and storage medium based on Expression analysis |
-
2019
- 2019-08-20 CN CN201910767413.5A patent/CN110458140A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190034706A1 (en) * | 2010-06-07 | 2019-01-31 | Affectiva, Inc. | Facial tracking with classifiers for query evaluation |
| CN107194316A (en) * | 2017-04-20 | 2017-09-22 | 广东数相智能科技有限公司 | A kind of evaluation method of mood satisfaction, apparatus and system |
| CN109858410A (en) * | 2019-01-18 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Service evaluation method, apparatus, equipment and storage medium based on Expression analysis |
Non-Patent Citations (2)
| Title |
|---|
| SHAN LI: ""Deep Facial Expression Recognition: A Survey"", 《ARXIV》 * |
| 秦艳超: ""人脸识别技术方向"", 《HTTPS://WWW.JIANSHU.COM/P/EA45A378A311》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368646A (en) * | 2020-02-15 | 2020-07-03 | 快优智能技术有限公司 | Intelligent counter expression interaction method |
| CN111639549A (en) * | 2020-05-12 | 2020-09-08 | 中信银行股份有限公司 | Method and device for determining service satisfaction degree and electronic equipment |
| CN111687863A (en) * | 2020-06-24 | 2020-09-22 | 中国银行股份有限公司 | Network point robot self-adjusting method and device |
| CN111687863B (en) * | 2020-06-24 | 2021-10-01 | 中国银行股份有限公司 | Network point robot self-adjusting method and device |
| CN111814649A (en) * | 2020-06-30 | 2020-10-23 | 平安国际智慧城市科技股份有限公司 | Customer service expression practicing method based on artificial intelligence and related equipment |
| CN111814649B (en) * | 2020-06-30 | 2024-07-02 | 平安国际智慧城市科技股份有限公司 | Customer service expression exercise method based on artificial intelligence and related equipment |
| CN112907306A (en) * | 2021-05-06 | 2021-06-04 | 北京惠朗时代科技有限公司 | Customer satisfaction judging method and device |
| CN112907306B (en) * | 2021-05-06 | 2022-04-08 | 北京惠朗时代科技有限公司 | Customer satisfaction judging method and device |
| CN113921098A (en) * | 2021-10-14 | 2022-01-11 | 江苏木盟智能科技有限公司 | Medical service evaluation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110472592A (en) | Service satisfaction evaluation method and device based on Expression Recognition | |
| CN110458140A (en) | Site satisfaction evaluation method and apparatus based on Expression Recognition | |
| CN105095827B (en) | Facial expression recognition device and method | |
| Tiwari | Supervised learning: From theory to applications | |
| US10943156B2 (en) | Machine-implemented facial health and beauty assistant | |
| CN109993734A (en) | Method and apparatus for output information | |
| CN109949286A (en) | Method and apparatus for output information | |
| CN108334647A (en) | Data processing method, device, equipment and the server of Insurance Fraud identification | |
| CN108875932A (en) | Image-recognizing method, device and system and storage medium | |
| KR20200105480A (en) | Machine-implemented facial health and beauty orthosis | |
| CN106295591A (en) | Gender identification method based on facial image and device | |
| CN109376766A (en) | A kind of portrait prediction classification method, device and equipment | |
| CN109978870A (en) | Method and apparatus for output information | |
| CN112215696A (en) | Personal credit evaluation and interpretation method, device, equipment and storage medium based on time sequence attribution analysis | |
| CN109933782A (en) | User emotion prediction technique and device | |
| CN108509994A (en) | character image clustering method and device | |
| Ambika | Enhancing security in IoT instruments using artificial intelligence | |
| CN110517247A (en) | Obtain the method and device of information | |
| CN110532838A (en) | Object test equipment and method and storage medium | |
| CN108596094A (en) | Personage's style detecting system, method, terminal and medium | |
| CN108921138A (en) | Method and apparatus for generating information | |
| Yadav et al. | In-browser attendance system using face recognition and serverless edge computing | |
| Dodd et al. | Facial emotion recognition and the future of work | |
| Li | Design and implementation of an intelligent education management platform based on face recognition | |
| Modak et al. | A novel multimodal biometric authentication framework using rule-based ANFIS based on hybrid level fusion |
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: 20191115 |
|
| RJ01 | Rejection of invention patent application after publication |