CN109584051A - The overdue risk judgment method and device of client based on micro- Expression Recognition - Google Patents
The overdue risk judgment method and device of client based on micro- Expression Recognition Download PDFInfo
- Publication number
- CN109584051A CN109584051A CN201811549647.4A CN201811549647A CN109584051A CN 109584051 A CN109584051 A CN 109584051A CN 201811549647 A CN201811549647 A CN 201811549647A CN 109584051 A CN109584051 A CN 109584051A
- Authority
- CN
- China
- Prior art keywords
- micro
- video
- client
- expression
- shape change
- 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
- 230000014509 gene expression Effects 0.000 title claims abstract description 199
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000008859 change Effects 0.000 claims abstract description 80
- 238000000605 extraction Methods 0.000 claims abstract description 38
- 238000010801 machine learning Methods 0.000 claims description 24
- 239000000284 extract Substances 0.000 claims description 5
- 235000013399 edible fruits Nutrition 0.000 claims description 4
- 238000012545 processing Methods 0.000 description 11
- 230000001815 facial effect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000011218 segmentation Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000005291 magnetic effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 210000000352 storage cell Anatomy 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- 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
- G06V40/176—Dynamic expression
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The disclosure is directed to a kind of overdue risk judgment method and devices of client based on micro- Expression Recognition, belong to micro- Expression Recognition applied technical field, this method comprises: within the first time limit after time point of refunding, video calling calling connection is initiated to the client terminal for not completing the client to refund at time point of refunding, after call is established, the voice of preset different problems is played in call, obtains face's video when answering a question of client；Obtain the sequence of frames of video of the period of different problems in face's video；Using micro- Expression Recognition from the sequence of frames of video, the video frame feature with micro- expression shape change in the period of different problems is extracted；Judge whether client can be overdue more than the second time limit, and second time limit was greater than for the first time limit according to the video frame feature with micro- expression shape change in the period of the different problems of extraction.This method can automatically, accurately obtain the overdue information of client by micro- Expression Recognition.
Description
Technical field
This disclosure relates to micro- Expression Recognition applied technical field, in particular to a kind of visitor based on micro- Expression Recognition
The overdue risk judgment method and device in family.
Background technique
It is one of the pith of loan transaction after loan, but overdue rate is higher after borrowing at present, air control is incomplete, overdue
The increase of rate will lead to cash flow circulation not enough, influence company's profitability, cause public trust power inadequate, reduce business hair
Exhibition ability.And the overdue risk of client is difficult to judge, the overdue risk judgment method of client is mainly at present: passing through bank
The continuous follow-up of personnel itself obtains, and is judged by the overdue situation of customer historical.The shortcoming of such acquisition modes
It is: cannot needs manually to carry out, the judgement of overdue situation is not accurate enough, constantly automatically directly according to the overdue information of customer acquisition
Follow up labor intensive resource, and can bring the not good experience of client.
Client with overdue risk can generate delicate expression shape change, while these to topic relevant to overdue topic
The variation degree of delicate expression can react the heart of client really about overdue feelings expected from oneself to a certain extent
Condition, and tend to occur in a very short period of time.So can use based on the micro- Expression Recognition of AI, is answered and set according to client
Particular problem relevant to overdue risk when video, micro- expression when being answered a question using client in video is automatic, accurate
The overdue risk information for identifying client.
Accordingly, it is desirable to provide a kind of overdue risk judgment method and device of client based on micro- Expression Recognition.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The disclosure is designed to provide a kind of overdue risk judgment scheme of the client based on micro- Expression Recognition, and then at least
It is automatic, accurately judge the overdue risk of client to a certain extent without the bad experience of client is carried out.
According to one aspect of the disclosure, a kind of overdue risk judgment method of the client based on micro- Expression Recognition is provided, is wrapped
It includes:
Within the first time limit after time point of refunding, to the client terminal hair for not completing the client to refund at time point of refunding
Video calling calling connection is played, after call is established, the voice of preset different problems is played in call, obtains client
Face's video when answering a question；
Obtain the sequence of frames of video of the period of different problems in face's video；
Using micro- Expression Recognition from the sequence of frames of video, extracting in the period of different problems, there is micro- expression to become
The video frame feature of change；
Whether client is judged according to the video frame feature with micro- expression shape change in the period of the different problems of extraction
Can be overdue more than the second time limit, second time limit was greater than for the first time limit.
In a kind of exemplary embodiment of the disclosure, within the first time limit after time point of refunding, in the time of refunding
The client terminal that point does not complete the client to refund initiates video calling calling connection, after call is established, by preset difference
The voice of problem plays in call, and face's video when answering a question for obtaining client includes:
Within the first time limit after time point of refunding, from the daily set time point of daystart, to when refunding
Between put and do not complete the client terminal of the client to refund and initiate video calling calling connection, it is logical until being successfully established video with client
Words；
After video calling is established, the voice of preset different problems is played in call；
Obtain face's video when answering a question of client.
It is described to obtain the period of different problems in face's video in a kind of exemplary embodiment of the disclosure
Sequence of frames of video, comprising:
Obtain the video of the period of different problems, the language for the problem of period of the difference problems is by will identify that
At the beginning of sound point to next problem voice at the beginning of point be identified as the determination of problem time section；
After the video in different problem time sections that will acquire resolves into video frame, sequence of frames of video is formed.
It is described to utilize micro- Expression Recognition from the sequence of frames of video in a kind of exemplary embodiment of the disclosure, it mentions
The video frame feature with micro- expression shape change in the period of different problems is taken to include:
The video frame of micro- expression shape change is identified from sequence of frames of video using micro- Expression Recognition；
From the micro- expression textural characteristics of face extracted in the video frame with micro- expression shape change identified in video frame.
In a kind of exemplary embodiment of the disclosure, having in the period according to the different problems of extraction is micro-
The video frame feature of expression shape change judges whether client can be overdue more than the second time limit, and second time limit wraps greater than the first time limit
It includes:
The video frame feature with micro- expression shape change of extraction is inputted trained machine learning model in advance to sentence
It is disconnected, the first risk judgment result is exported by machine learning model；
The video frame feature with micro- expression shape change of extraction is sentenced with micro- expression textural characteristics comparison in micro- expression library
It is disconnected, export the second risk judgment result；
According to the first risk judgment result and the second risk judgment as a result, judging that client whether can according to pre-defined rule
It is overdue more than the second time limit.
In a kind of exemplary embodiment of the disclosure, the video frame feature with micro- expression shape change by extraction is defeated
Enter preparatory trained machine learning model to be judged, the first risk judgment result exported by machine learning model, comprising:
The video frame feature with micro- expression shape change extracted in each problem time section is inputted into machine learning model, by
Machine learning model exports the risk judgment result corresponding to each problem respectively；
By first most as final output of frequency of occurrence in the risk judgment result corresponding to each problem
Risk judgment result.
In a kind of exemplary embodiment of the disclosure, the video frame feature by extraction with micro- expression shape change with
Micro- expression textural characteristics in micro- expression library compare judgement, export the second risk judgment result, comprising:
By the video frame feature with micro- expression shape change of each problem time section respectively with micro- expression in micro- expression library
Textural characteristics comparison judgement, using the most judging result of frequency of occurrence as the judging result of the problem time section；
According to the judging result of each problem time section, most the second risk as final output of frequency of occurrence is sentenced
Disconnected result.
According to one aspect of the disclosure, a kind of overdue risk judgment device of the client based on micro- Expression Recognition is provided, is wrapped
It includes:
First obtains module, for being refunded within the first time limit after time point of refunding to not completing at time point of refunding
The client terminal of client initiate video calling calling connection, after call is established, the voice of preset different problems is existed
It is played in call, obtains face's video when answering a question of client；
Second obtains module, for obtaining the sequence of frames of video of the period of different problems in face's video；
Extraction module, in the period for from the sequence of frames of video, extracting different problems using micro- Expression Recognition
The video frame feature with micro- expression shape change；
Judgment module, for the video frame feature with micro- expression shape change in the period according to the different problems of extraction
Judge whether client can be overdue more than the second time limit, and second time limit was greater than for the first time limit.
According to one aspect of the disclosure, a kind of computer readable storage medium is provided, is stored thereon with based on micro- expression
The overdue risk judgment program of the client of identification, which is characterized in that the overdue risk judgment journey of the client based on micro- Expression Recognition
The process described above is realized when sequence is executed by processor.
According to one aspect of the disclosure, a kind of electronic equipment is provided characterized by comprising
Processor；And
Memory, the overdue risk judgment program of the client based on micro- Expression Recognition for storing the processor；Wherein,
The processor is configured to execute the above institute based on the overdue risk judgment program of the client of micro- Expression Recognition via execution is described
The method stated.
The overdue risk judgment method and device of a kind of client based on micro- Expression Recognition of the disclosure, firstly, in the time of refunding
In the first time limit after point, video calling calling is initiated to the client terminal for not completing the client to refund at time point of refunding and is connected
It connects, after call is established, the voice of preset different problems is played in call, obtains face when answering a question of client
Portion's video；The first time limit after refund time point illustrates that client has had overdue risk omen, this just needs to further confirm that
Whether client can be further serious overdue, by the foundation of automatic video frequency calling connection, and by preset with overdue phase
The problem of pass communicates with client can get automatically client for the true of relevant issues in the case where no manually participation
Real facial video, and then can be used to extract the micro- expression of client in the next steps, carry out overdue risk judgment.Then, it obtains
Take the sequence of frames of video of the period of different problems in face's video；Client can generate in various degree about different problems
Micro- expression shape change, obtain the sequence of frames of video of the period of different problems, can subsequent step obtain be directed to different problems
Synthesis obtains final judging result after obtaining corresponding judging result.Then, using micro- Expression Recognition from the video frame sequence
In column, the video frame feature with micro- expression shape change in the period of different problems is extracted；The video of each problem time section
Possibility in frame sequence with micro- expression shape change only has a few, after these video frame extractions with micro- expression shape change
Subsequent calculating working efficiency can be effectively improved.Finally, there is micro- table according in the period of the different problems of extraction
The video frame feature of end of love judges whether client can be overdue more than the second time limit, and second time limit was greater than for the first time limit；This
Sample can utilize visitor according to several video frame features with micro- expression shape change in the period of the different problems got
The feature for micro- expression that family is most really shown about overdue problem, without the bad experience of client is carried out, automatic,
Accurately judge the serious overdue risk of client, that is, whether can be overdue more than the second time limit.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.It should be evident that the accompanying drawings in the following description is only the disclosure
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 schematically shows a kind of flow chart of overdue risk judgment method of the client based on micro- Expression Recognition.
Fig. 2 schematically shows a kind of Application Scenarios-Example of overdue risk judgment method of the client based on micro- Expression Recognition
Figure.
Fig. 3 schematically shows a kind of judge whether client can the overdue method flow diagram more than the second time limit.
Fig. 4 schematically shows a kind of block diagram of overdue risk judgment device of the client based on micro- Expression Recognition.
Fig. 5 schematically shows a kind of electricity for realizing the overdue risk judgment method of the above-mentioned client based on micro- Expression Recognition
Sub- device examples block diagram.
Fig. 6 schematically show it is a kind of for realizing above-mentioned based on the overdue risk judgment method of the client of micro- Expression Recognition
Calculation machine readable storage medium storing program for executing.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in any suitable manner in one or more embodiments.In the following description, it provides perhaps
More details fully understand embodiment of the present disclosure to provide.It will be appreciated, however, by one skilled in the art that can
It is omitted with technical solution of the disclosure one or more in the specific detail, or others side can be used
Method, constituent element, device, step etc..In other cases, be not shown in detail or describe known solution to avoid a presumptuous guest usurps the role of the host and
So that all aspects of this disclosure thicken.
In addition, attached drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical attached drawing mark in figure
Note indicates same or similar part, thus will omit repetition thereof.Some block diagrams shown in the drawings are function
Energy entity, not necessarily must be corresponding with physically or logically independent entity.These function can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
The overdue risk judgment method of client based on micro- Expression Recognition is provided firstly in this example embodiment, this is based on
The overdue risk judgment method of the client of micro- Expression Recognition can run on server, can also run on server cluster or cloud clothes
Business device etc., certainly, those skilled in the art can also run method of the invention in other platforms according to demand, this exemplary reality
It applies and does not do particular determination in example to this.Refering to what is shown in Fig. 1, should overdue risk judgment method of client based on micro- Expression Recognition can be with
The following steps are included:
Step S110. does not complete the client's to refund within the first time limit after time point of refunding, at time point of refunding
Client terminal initiates video calling calling connection, and after call is established, the voice of preset different problems is broadcast in call
It puts, obtains face's video when answering a question of client.
Step S120. obtains the sequence of frames of video of the period of different problems in face's video.
Step S130. from the sequence of frames of video, extracts the tool in the period of different problems using micro- Expression Recognition
There is the video frame feature of micro- expression shape change.
Step S140. judges according to the video frame feature with micro- expression shape change in the period of the different problems of extraction
Whether client can be overdue more than the second time limit, and second time limit was greater than for the first time limit.
In the overdue risk judgment method of the above-mentioned client based on micro- Expression Recognition, firstly, first after time point of refunding
In time limit, video calling calling connection is initiated to the client terminal for not completing the client to refund at time point of refunding, call is established
Afterwards, the voice of preset different problems is played in call, obtains face's video when answering a question of client；It refunds
The first time limit after time point illustrates that client has had overdue risk omen, this just needs to further confirm that whether client can be into
One step is seriously overdue, by the foundation of automatic video frequency calling connection, and by preset to overdue related problem and visitor
The true facial video that client can be got automatically in the case where no manually participation for relevant issues is linked up at family,
And then can be used to extract the micro- expression of client in the next steps, carry out overdue risk judgment.Then, face's video is obtained
The sequence of frames of video of the period of middle difference problem；Client can generate different degrees of micro- expression shape change about different problems,
The sequence of frames of video of the period of different problems is obtained, can obtain in subsequent step and sentence for the acquisition of different problems is corresponding
Synthesis obtains final judging result after disconnected result.Then, it using micro- Expression Recognition from the sequence of frames of video, extracts difference and asks
The video frame feature with micro- expression shape change in the period of topic；There is micro- table in the sequence of frames of video of each problem time section
The possibility of end of love only has a few, by it can effectively improve after these video frame extractions with micro- expression shape change after
Continuous calculating working efficiency.Finally, special according to the video frame with micro- expression shape change in the period of the different problems of extraction
Sign judges whether client can be overdue more than the second time limit, and second time limit was greater than for the first time limit；It thus can be according to acquisition
Several video frame features with micro- expression shape change in the period of the different problems arrived, using client most really about exceeding
The feature for micro- expression that phase problem is shown, it is automatic, accurately judge client's without the bad experience of client is carried out
Serious overdue risk, that is, whether can be overdue more than the second time limit.
In the following, by conjunction with attached drawing to the overdue risk judgment of the above-mentioned client based on micro- Expression Recognition in this example embodiment
Each step in method carries out detailed explanation and explanation.
In step s 110, within the first time limit after time point of refunding, the visitor to refund is not completed at time point of refunding
The client terminal at family initiates video calling calling connection, and after call is established, the voice of preset different problems is being conversed
Middle broadcasting obtains face's video when answering a question of client.
In this example embodiment, refering to what is shown in Fig. 2, firstly, first time limit of the server 201 after time point of refunding
It is interior, video call connection is initiated to client terminal 202, which, which can be mobile terminal device, (such as can be hand
Machine), it is also possible to other and has store or the terminal device (such as can be camera, wrist-watch etc.) of shooting video capability,
There is no special restriction on this for this example.Further, which may include one, also may include multiple, this example
There is no special restriction on this；When more than 201 client terminal of server is successfully established video calling connection, by preset, storage
The voice of the different problems of presence server plays in call, while client carries out answer these problems；Client is required in advance
It needs face to be presented in video in answer to a question；Server 201 obtains client from client terminal 202 in real time and answers a question
It face's video of process and saves in the server.Further, the different problem be include at least one with it is overdue
Incoherent problem, other problems to it is overdue related.Client can be made relatively to loosen when answering a question in this way, to obtain more
Add the facial video of true performance client circumstances.
In a kind of this exemplary embodiment, within the first time limit after time point of refunding, to refund time point not
The client terminal for completing the client to refund initiates video calling calling connection, after call is established, by preset different problems
Voice played in call, face's video when answering a question for obtaining client includes:
Within the first time limit after time point of refunding, from the daily set time point of daystart, to when refunding
Between put and do not complete the client terminal of the client to refund and initiate video calling calling connection, it is logical until being successfully established video with client
Words；
After video calling is established, the voice of preset different problems is played in call；
Obtain face's video when answering a question of client.
Firstly, when client does not refund at time point of refunding, within the first overdue time limit, from overdue daystart, often
It a set time point, system initiate video connection from trend client terminal；First overdue time limit was generally 5-8 days, Gu
Fixed time point can be such as 8 points daily of morning.The first time limit after client, which reaches the overdue time, refunds time point
It is interior, video calling is initiated to client, which illustrates that client has and overdue risk occurs.But client is overdue
The reason of time in the first time limit may be the client for really having overdue risk, it is also possible to be normal clients because of extraneous original
Cause because delaying overdue；In turn, by automatic video frequency converse intervention, further confirm that the client presently, there are specific wind
Dangerous situation condition.Then, it is played out after video calling the problem of presetting being connected, wherein the problem of presetting can be
The problem related to overdue situation, the problem related to overdue situation can stimulate client that micro- expression shape change occurs naturally；?
It may include with overdue incoherent problem, client can be made to loosen phychology in this way, and then obtain more valuable video.
The problem of enquirement, the interval of play time of voice can be Fixed Time Interval, such as can be and put question to according to every 3 minutes
One problem, is conducive to the segmentation of later period video in this way；Time needed for being also possible to the answer according to problem plays, and has in this way
There is the sufficient time to reply conducive to client, and then obtains more added with the video of quality.Example can be for the problem of overdue correlation
Such as: whether having capital turnover problem in the recent period, if any being caused by what reason；Whether loan is had elsewhere；Whether clearly provide a loan
It is overdue to will lead to reference record of bad behavior；The mode of making loans whether clearly provided a loan；Whether the card of refund is in normal use etc.；Herein
Do not do particular determination.It is saved in the server finally, obtaining the facial video that client answers a question in real time, wherein the view of acquisition
Frequency be include all enquirement processes duration video；The process for obtaining video provides the face of client and the specific position of camera
It sets, guarantees that the video obtained understands including face part.
In the step s 120, the sequence of frames of video of the period of different problems in face's video is obtained.
In this example embodiment, by the view of all processes answered a question comprising client got in preceding step
It frequently, then, will be every firstly, according to the period of different problems progress by Video segmentation at the video-frequency band of each problem of correspondence
Section video forms sequence of frames of video after resolving into video frame.It can be obtained in the next steps for different problems and one in this way
The corresponding judging result of a problem, can integrate more due to the weighted of the judging result of different problems, in subsequent step
A result obtains final as a result, can effectively improve the accuracy rate of judgement.
Further, this exemplary embodiment, it may also is that forming video after whole video is decomposed framing first
Frame sequence；The sequence of frames of video of the period corresponding to different problems is finally divided into according to the period of different problems.
Originally in a kind of exemplary embodiment, the video frame sequence of the period of different problems in face's video is obtained
Column, comprising:
Obtain the video of the period of different problems, the language for the problem of period of the difference problems is by will identify that
At the beginning of sound point to next problem voice at the beginning of point be identified as the determination of problem time section；
After the video in different problem time sections that will acquire resolves into video frame, sequence of frames of video is formed.
Firstly, the time point that the time point and next problem voice that are started by each problem voice recorded start is made
Then Video segmentation is opened based on these cut-points for cut-point；The video between each cut-point after finally obtaining segmentation
With regard to corresponding to the video of the period of each problem.For example, video has putd question to 10 problems altogether from the beginning to the end, first is asked
Topic 0 separately begins to play, and 3 timesharing of Second Problem starts to play, then comes out the video extraction of 0-3 time segment and be used as first
The video of problem time section；And so on, then video can be obtained into 10 sections of small videos according to the period segmentation of each problem.
The face video of all clients in the process putd question in each small video comprising the problem, power of the different problems about overdue rate
Weight is different, and the judging result that can integrate each problem obtains final judging result.Then, video frame is exactly to form video
Frame identifies when the video frame of each video inputs with frame head, is used as decomposition foundation by the frame head mark of each frame of record,
After video is resolved into video frame based on these frame heads mark, sequence of frames of video is formed；Micro- Expression Recognition is by continuously regarding
The variation of the privileged site of adjacent two frame in frequency frame, identifies micro- expression shape change；So the portion in each problem time section
The sequence of frames of video divided in video can be used to judge micro- expression shape change of the client when answering the problem.
In step s 130, using micro- Expression Recognition from the sequence of frames of video, in period for extracting different problems
The video frame feature with micro- expression shape change.
In this example embodiment, judge have in sequence of frames of video in different time periods first with micro- Expression Recognition
Then the video frame of micro- expression shape change extracts these video frame features with micro- expression shape change identified, for subsequent
Step carries out calculating analysis, wherein video frame feature can be micro- expression textural characteristics；Can not have by the way that exclusion is other in this way
There is the video frame of micro- expression shape change, so that calculated load be effectively reduced, improves treatment effeciency.
Originally in a kind of exemplary embodiment, using micro- Expression Recognition from the sequence of frames of video, different problems are extracted
Period in the video frame feature with micro- expression shape change, comprising:
The video frame of micro- expression shape change is identified from sequence of frames of video using micro- Expression Recognition；
From the micro- expression textural characteristics of face extracted in the video frame with micro- expression shape change identified in video frame.
It can be specific in the face of adjacent two frame by sentencing in sequence of frames of video based on the micro- Expression Recognition technology of existing AI
The delicate variation at position, identifies the video frame with micro- expression shape change；Then, these are extracted with micro- expression shape change
Video frame, and the micro- expression texture of face in several video frames is extracted, for example, can scan using micro- Expression Recognition AI
Facial expression image in Facial action unit, while can also scan the texture of skin variation, and combine deformable point
Galaxy is established facial detailed model and is fed back.
Originally in a kind of exemplary embodiment, the micro- expression textural characteristics of face are extracted from video frame, comprising:
Face is identified from video frame；
In the predetermined position texture feature extraction of the face identified, as the micro- expression textural characteristics of face.
Firstly, identifying face from video frame picture using face recognition technology, then pass through the predetermined of locating human face
Position, such as micro- expressive features position abundant in the predetermined positions such as eyes, mouth is navigated to by face recognition technology every time,
Then the textural characteristics for extracting the predetermined position, as micro- expression textural characteristics；It in this way can be by extracting the micro- of key position
Expression textural characteristics, further improve computational efficiency.
In step S140, according to the video frame feature with micro- expression shape change in the period of the different problems of extraction
Judge whether client can be overdue more than the second time limit, and second time limit was greater than for the first time limit.
In this example embodiment, according to the video with micro- expression shape change in the period of the different problems of extraction
Frame feature judges whether client can be overdue more than the second time limit, and micro- expression is that the physiology for the most true psychological activity for reacting people is special
Therefore sign can be used to considering about overdue true heart for accurate response client；By the micro- expression shape change for extracting client
Video frame feature accurately client's heart activity can be characterized using scientific algorithm, and then can accurately judge
Whether client overdue can illustrate the overdue risk probability of client wherein the second time limit was greater than for the first time limit more than the second time limit out
Than more serious, need to be intervened using means, to reduce overdue risk.
In a kind of originally exemplary embodiment, refering to what is shown in Fig. 3, according to the tool in the period of the different problems of extraction
There is the video frame feature of micro- expression shape change to judge whether client can be overdue more than the second time limit, and second time limit is greater than the first phase
Limit, including step S310, step S320 and step S330, in which:
In step s310, the video frame feature with micro- expression shape change of extraction is inputted into trained engineering in advance
It practises model to be judged, the first risk judgment result is exported by machine learning model；
In step s 320, by micro- expression line in the video frame feature with micro- expression shape change of extraction and micro- expression library
Characteristic Contrast judgement is managed, the second risk judgment result is exported；
In step S330, according to the first risk judgment result and the second risk judgment as a result, according to pre-defined rule
Judge whether client can be overdue more than the second time limit.
Step S310, step S320 and step S330 are explained in detail and are illustrated below, firstly, by extraction
Video frame feature with micro- expression shape change inputs trained machine learning model in advance and is judged, by machine learning model
Export the first risk judgment result；Wherein, the training method of the machine learning model is；By micro- expression textural characteristics group sample
It has been demarcated as micro- expression textural characteristics group of risky client in set, the micro- expression textural characteristics group for the client that compromises, just
The normal time limit micro- expression textural characteristics group of client inputs training machine learning model respectively, and each feature group includes predetermined characteristic number
A micro- expression textural characteristics of face, machine learning model export risk judgment result；If the judging result inaccuracy of output
The coefficient for adjusting machine learning model, re-starts judgement, until output result is consistent with what is demarcated in advance；First risk judgment
As a result it can be a kind of in risk client, compromise client and normal clients.
Then, by micro- expression textural characteristics pair in the video frame feature with micro- expression shape change of extraction and micro- expression library
Than judgement, the second risk judgment result is exported；The micro- expression for the client for having demarcated risk is stored in micro- expression library
Textural characteristics pass through micro- expression textural characteristics pair in the video frame feature with micro- expression shape change that will be extracted and micro- expression library
Than for example, by micro- expression textural characteristics in the video frame with micro- expression shape change and the risky client in micro- expression library
Micro- expression textural characteristics, the micro- expression textural characteristics for the client that compromises, the normal micro- expression textural characteristics of time limit client carry out respectively
Comparison exports comparing result.Wherein, the control methods of micro- expression textural characteristics are as follows: with the continuous view with micro- expression shape change
The pixel in the lower left corner of frequency frame image is that origin (0,0) establishes rectangular coordinate system, and the pixel in each frame image is sat with right angle
A point represents in mark system.It is 0, ordinate as 1 pixel that (0,1), which represents abscissa, and (1,0) represents abscissa as 1, ordinate
Pixel of the abscissa as m, ordinate as n is represented for 0 pixel ... ... (m, n), wherein m and n is positive integer.In micro- expression library
Image it is equally processed.Then, by the pixel value of each pixel of each frame image respectively with identical seat in micro- expression library
After the pixel value of target pixel subtracts each other, the difference of the pixel of the obtained frame all pixels point is summed, when the difference of the frame pixel
Illustrate that two kinds of micro- expressions are similar when the sum of value is less than predetermined threshold, to export the judgement knot of similar micro- expression generic
Fruit.
Finally, according to the first risk judgment result and the second risk judgment as a result, whether judging client according to pre-defined rule
Can it is overdue more than the second time limit, for example, when be both judged as more than when, just determination client can be more than the second time limit；It is logical in this way
It crosses two kinds of calculation synthesis to be judged, the accuracy of judging result can be effectively ensured.
In a kind of originally exemplary embodiment, the video frame feature input with micro- expression shape change of extraction is instructed in advance
The machine learning model perfected is judged, exports the first risk judgment result by machine learning model, comprising:
The video frame feature with micro- expression shape change extracted in each problem time section is inputted into machine learning model, by
Machine learning model exports the risk judgment result corresponding to each problem respectively；
By first most as final output of frequency of occurrence in the risk judgment result corresponding to each problem
Risk judgment result.
Firstly, the video frame feature with micro- expression shape change of the extraction in the different periods is inputted engineering respectively
Model is practised, has machine learning model to export multiple judging results, wherein there is a judging result in each period, for example, view
Frequency division is segmented into 10 periods, can thus obtain 10 judging results；Then, the work that frequency of occurrence in judging result is most
For final output the first risk judgment as a result, there is 8 risk clients in such as 10 judging results, 1 compromise client, 1
The judging result of the client is then positioned risk client by normal clients；It may insure client to the sensibility of different problems in this way
Difference, and caused by risk judgment result inaccuracy.
Video frame feature and micro- expression library in a kind of this exemplary embodiment, by extraction with micro- expression shape change
In micro- expression textural characteristics compare judgement, export the second risk judgment result, comprising:
By the video frame feature with micro- expression shape change of each problem time section respectively with micro- expression in micro- expression library
Textural characteristics comparison judgement, using the most judging result of frequency of occurrence as the judging result of the problem time section；
According to the judging result of each problem time section, most the second risk as final output of frequency of occurrence is sentenced
Disconnected result.
Firstly, by the video frame feature with micro- expression shape change of each problem time section respectively with it is micro- in micro- expression library
The comparison judgement of expression textural characteristics, will be in the micro- expression textural characteristics and micro- expression library in the video frame with micro- expression shape change
Micro- expression textural characteristics of risky client, the micro- expression textural characteristics for the client that compromises, the normal micro- expression texture of time limit client
Feature compares respectively, comparing result is exported, wherein multiple video frames with micro- expression shape change in every section of video can obtain
To multiple judging results, by the judging result of the most period the most of quantity in judging result, for example, the period mentions
5 video frames with micro- expression shape change are got, and then obtain 5 judging results, wherein 3 risk clients, 1 positive regular guest
Risk client, then is set to the judging result of the period by family, 1 compromise client；In this way, the time can be accurately obtained
Section, that is, the problem corresponding client risk.Then, according to the judging result of each problem time section, will go out
Most the second risk judgment result as final output of occurrence number；For example, Video segmentation is 10 periods, thus can
Obtain 10 judging results；Then, the first risk judgment knot as final output that frequency of occurrence in judging result is most
There are 8 risk clients, 1 compromise client, 1 normal clients, then by the judgement knot of the client in fruit, such as 10 judging results
Fruit positions risk client；May insure that client is different to the sensibility of different problems in this way, and caused by risk judgment result not
Accuracy.
In a kind of originally exemplary embodiment, the first risk judgment result and the second risk judgment are the result is that risk is objective
Family, compromise one of client and normal clients, wherein risk client is the client that can be more than the second time limit, and normal clients are
The client in the second time limit is not exceeded, compromise client is the client between risk client and compromise client；
It is described, according to the first risk judgment result and the second risk judgment as a result, judging client according to pre-defined rule
Whether can be overdue more than the second time limit, comprising:
When the first risk judgment result and the second risk judgment result are all risk clients, judge that client is risk visitor
Family；
When the first risk judgment result and the second risk judgment result are all compromise clients, judge that client is compromise visitor
Family；
When the first risk judgment result and the second risk judgment result are all normal clients, judge that client is positive regular guest
Family；
When two kinds of results are inconsistent, using client as client undetermined, judged by other methods.
Pass through, two kinds of judgment modes, exports two same judging results of judgment mode as final judging result, in turn
Whether obtain client can be overdue more than the second time limit；It in this way can be to avoid the bring when the result of one of which judgement has error
Judging result inaccuracy, and then effectively improve judging result accuracy.
The disclosure additionally provides a kind of overdue risk judgment device of the client based on micro- Expression Recognition.Refering to what is shown in Fig. 4, should
The overdue risk judgment device of client based on micro- Expression Recognition may include the first acquisition module 410, second obtain module 420,
Extraction module 430 and judgment module 440.Wherein:
First acquisition module 410 can be used within the first time limit after time point of refunding, to refund time point it is not complete
Video calling calling connection is initiated at the client terminal of the client of refund, after call is established, by preset different problems
Voice plays in call, obtains face's video when answering a question of client；
Second acquisition module 420 can be used for obtaining the video frame sequence of the period of different problems in face's video
Column；
Extraction module 430 can be used for using micro- Expression Recognition from the sequence of frames of video, extract different problems when
Between the video frame feature with micro- expression shape change in section；
Judgment module 440 can be used for the video with micro- expression shape change in the period according to the different problems of extraction
Frame feature judges whether client can be overdue more than the second time limit, and second time limit was greater than for the first time limit.
The detail of each module is in correspondence in the overdue risk judgment device of the above-mentioned client based on micro- Expression Recognition
The overdue risk judgment of the client based on micro- Expression Recognition in be described in detail, therefore details are not described herein again.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
In addition, although describing each step of method in the disclosure in the accompanying drawings with particular order, this does not really want
These steps must be executed in this particular order by asking or implying, or having to carry out step shown in whole could realize
Desired result.Additional or alternative, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/
Or a step is decomposed into execution of multiple steps etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, mobile terminal or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can be realized the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
The electronic equipment 500 of this embodiment according to the present invention is described referring to Fig. 5.The electronics that Fig. 5 is shown
Equipment 500 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 5, electronic equipment 500 is showed in the form of universal computing device.The component of electronic equipment 500 can wrap
It includes but is not limited to: at least one above-mentioned processing unit 510, at least one above-mentioned storage unit 520, the different system components of connection
The bus 530 of (including storage unit 520 and processing unit 510).
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 510
Row, so that various according to the present invention described in the execution of the processing unit 510 above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 510 can execute step S110 as shown in fig. 1: refunding
In the first time limit after time point, video calling calling is initiated to the client terminal for not completing the client to refund at time point of refunding
After call is established, the voice of preset different problems is played in call connection, obtains when answering a question of client
Face's video；S120: the sequence of frames of video of the period of different problems in face's video is obtained；Step S130: it utilizes micro-
For Expression Recognition from the sequence of frames of video, the video frame with micro- expression shape change extracted in the period of different problems is special
Sign；Step S140: client is judged according to the video frame feature with micro- expression shape change in the period of the different problems of extraction
Whether can be overdue more than the second time limit, second time limit was greater than for the first time limit.
Storage unit 520 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 5201 and/or cache memory unit 5202, it can further include read-only memory unit (ROM) 5203.
Storage unit 520 can also include program/utility with one group of (at least one) program module 5205
5204, such program module 5205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 530 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 500 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, the equipment that also client can be enabled interact with the electronic equipment 500 with one or more communicates, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 500 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 550.Also, electronic equipment 500 can be with
By network adapter 560 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 560 is communicated by bus 530 with other modules of electronic equipment 500.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 500, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product comprising program code, when described program product is run on the terminal device, institute
Program code is stated for executing the terminal device described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
Refering to what is shown in Fig. 6, describing the program product for realizing the above method of embodiment according to the present invention
600, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in client
It calculates and executes in equipment, partly executes on the client device, being executed as an independent software package, partially in client's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to client computing device, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In addition, above-mentioned attached drawing is only the schematic theory of processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
Claims (10)
1. a kind of overdue risk judgment method of client based on micro- Expression Recognition characterized by comprising
Within the first time limit after time point of refunding, view is initiated to the client terminal for not completing the client to refund at time point of refunding
The connection of frequency dial-up after call is established, the voice of preset different problems is played in call, obtains returning for client
Face's video when question and answer is inscribed；
Obtain the sequence of frames of video of the period of different problems in face's video；
Using micro- Expression Recognition from the sequence of frames of video, extract in the period of different problems with micro- expression shape change
Video frame feature；
Judge whether client can exceed according to the video frame feature with micro- expression shape change in the period of the different problems of extraction
Phase was more than the second time limit, and second time limit was greater than for the first time limit.
2. the method according to claim 1, wherein in first time limit after time point of refunding, Xiang
The client terminal that refund time point does not complete the client to refund initiates video calling calling connection will set in advance after call foundation
The voice of fixed different problems plays in call, and face's video when answering a question for obtaining client includes:
Within the first time limit after time point of refunding, from the daily set time point of daystart, at time point of refunding
The client terminal for not completing the client to refund initiates video calling calling connection, until being successfully established video calling with client；
After video calling is established, the voice of preset different problems is played in call；
Obtain face's video when answering a question of client.
3. the method according to claim 1, wherein the time for obtaining different problems in face's video
The sequence of frames of video of section, comprising:
Obtain the video of the period of different problems, the voice for the problem of period of the difference problems is by will identify that
Sart point in time to next problem voice at the beginning of point be identified as problem time section and determine；
After the video in different problem time sections that will acquire resolves into video frame, sequence of frames of video is formed.
4. the method according to claim 1, wherein described utilize micro- Expression Recognition from the sequence of frames of video
In, the video frame feature with micro- expression shape change extracted in the period of different problems includes:
The video frame of micro- expression shape change is identified from sequence of frames of video using micro- Expression Recognition；
From the micro- expression textural characteristics of face extracted in the video frame with micro- expression shape change identified in video frame.
5. the method according to claim 1, wherein the tool in the period according to the different problems of extraction
There is the video frame feature of micro- expression shape change to judge whether client can be overdue more than the second time limit, and second time limit is greater than the first phase
Limit includes:
The video frame feature with micro- expression shape change of extraction is inputted trained machine learning model in advance to judge, by
Machine learning model exports the first risk judgment result；
Micro- expression textural characteristics in the video frame feature with micro- expression shape change of extraction and micro- expression library are compared and are judged, it is defeated
Second risk judgment result out；
According to the first risk judgment result and the second risk judgment as a result, judging whether client can be overdue according to pre-defined rule
More than the second time limit.
6. method according to claim 5, which is characterized in that the video frame feature with micro- expression shape change by extraction
It inputs trained machine learning model in advance to be judged, the first risk judgment result is exported by machine learning model, comprising:
The video frame feature with micro- expression shape change extracted in each problem time section is inputted into machine learning model, by machine
Learning model exports the risk judgment result corresponding to each problem respectively；
By most the first risk as final output of frequency of occurrence in the risk judgment result corresponding to each problem
Judging result.
7. according to the method described in claim 5, it is characterized in that, the video frame with micro- expression shape change by extraction is special
Sign is compared with micro- expression textural characteristics in micro- expression library to be judged, the second risk judgment result is exported, comprising:
By the video frame feature with micro- expression shape change of each problem time section respectively with micro- expression texture in micro- expression library
Characteristic Contrast judgement, using the most judging result of frequency of occurrence as the judging result of the problem time section；
According to the judging result of each problem time section, by most the second risk judgment knot as final output of frequency of occurrence
Fruit.
8. a kind of overdue risk judgment device of client based on micro- Expression Recognition characterized by comprising
First obtains module, for not completing the visitor to refund at time point of refunding within the first time limit after time point of refunding
The client terminal at family initiates video calling calling connection, and after call is established, the voice of preset different problems is being conversed
Middle broadcasting obtains face's video when answering a question of client；
Second obtains module, for obtaining the sequence of frames of video of the period of different problems in face's video；
Extraction module, for from the sequence of frames of video, extracting the tool in the period of different problems using micro- Expression Recognition
There is the video frame feature of micro- expression shape change；
Judgment module, for the video frame feature judgement with micro- expression shape change in the period according to the different problems of extraction
Whether client can be overdue more than the second time limit, and second time limit was greater than for the first time limit.
9. a kind of computer readable storage medium is stored thereon with the overdue risk judgment program of client based on micro- Expression Recognition,
It is characterized in that, the client based on micro- Expression Recognition overdue risk judgment program realizes claim when being executed by processor
The described in any item methods of 1-7.
10. a kind of electronic equipment characterized by comprising
Processor；And
Memory, the overdue risk judgment program of the client based on micro- Expression Recognition for storing the processor；Wherein, described
Processor is configured to require 1-7 via the execution overdue risk judgment program of client based on micro- Expression Recognition come perform claim
Described in any item methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811549647.4A CN109584051A (en) | 2018-12-18 | 2018-12-18 | The overdue risk judgment method and device of client based on micro- Expression Recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811549647.4A CN109584051A (en) | 2018-12-18 | 2018-12-18 | The overdue risk judgment method and device of client based on micro- Expression Recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109584051A true CN109584051A (en) | 2019-04-05 |
Family
ID=65929916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811549647.4A Pending CN109584051A (en) | 2018-12-18 | 2018-12-18 | The overdue risk judgment method and device of client based on micro- Expression Recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109584051A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090001848A (en) * | 2007-05-28 | 2009-01-09 | 에스케이 텔레콤주식회사 | Method and system monitoring facial expression |
| CN102103617A (en) * | 2009-12-22 | 2011-06-22 | 华为终端有限公司 | Method and device for acquiring expression meanings |
| CN107180234A (en) * | 2017-06-01 | 2017-09-19 | 四川新网银行股份有限公司 | The credit risk forecast method extracted based on expression recognition and face characteristic |
| CN107704834A (en) * | 2017-10-13 | 2018-02-16 | 上海壹账通金融科技有限公司 | Householder method, device and storage medium are examined in micro- expression face |
| CN107862598A (en) * | 2017-09-30 | 2018-03-30 | 平安普惠企业管理有限公司 | Long-range the interview measures and procedures for the examination and approval, server and readable storage medium storing program for executing |
| CN108510194A (en) * | 2018-03-30 | 2018-09-07 | 平安科技（深圳）有限公司 | Air control model training method, Risk Identification Method, device, equipment and medium |
| CN108537160A (en) * | 2018-03-30 | 2018-09-14 | 平安科技（深圳）有限公司 | Risk Identification Method, device, equipment based on micro- expression and medium |
| CN108596760A (en) * | 2018-05-14 | 2018-09-28 | 平安普惠企业管理有限公司 | loan risk evaluation method and server |
-
2018
- 2018-12-18 CN CN201811549647.4A patent/CN109584051A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090001848A (en) * | 2007-05-28 | 2009-01-09 | 에스케이 텔레콤주식회사 | Method and system monitoring facial expression |
| CN102103617A (en) * | 2009-12-22 | 2011-06-22 | 华为终端有限公司 | Method and device for acquiring expression meanings |
| CN107180234A (en) * | 2017-06-01 | 2017-09-19 | 四川新网银行股份有限公司 | The credit risk forecast method extracted based on expression recognition and face characteristic |
| CN107862598A (en) * | 2017-09-30 | 2018-03-30 | 平安普惠企业管理有限公司 | Long-range the interview measures and procedures for the examination and approval, server and readable storage medium storing program for executing |
| CN107704834A (en) * | 2017-10-13 | 2018-02-16 | 上海壹账通金融科技有限公司 | Householder method, device and storage medium are examined in micro- expression face |
| CN108510194A (en) * | 2018-03-30 | 2018-09-07 | 平安科技（深圳）有限公司 | Air control model training method, Risk Identification Method, device, equipment and medium |
| CN108537160A (en) * | 2018-03-30 | 2018-09-14 | 平安科技（深圳）有限公司 | Risk Identification Method, device, equipment based on micro- expression and medium |
| CN108596760A (en) * | 2018-05-14 | 2018-09-28 | 平安普惠企业管理有限公司 | loan risk evaluation method and server |
Non-Patent Citations (1)
| Title |
|---|
| 吴永哲: "20180829金融反欺诈是AI多模态情感计算最佳落地场景", pages 1 - 3, Retrieved from the Internet <URL:https://www.sohu.com/a/250656997_545428> * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111488433B (en) | Artificial intelligence interactive system suitable for bank and capable of improving field experience | |
| US10504268B1 (en) | Systems and methods for generating facial expressions in a user interface | |
| US11163978B2 (en) | Method and device for face image processing, storage medium, and electronic device | |
| CN109660744A (en) | The double recording methods of intelligence, equipment, storage medium and device based on big data | |
| CN111310705A (en) | Image recognition method and device, computer equipment and storage medium | |
| CN112543936B (en) | Motion structure self-attention-drawing convolution network model for motion recognition | |
| US20220138536A1 (en) | Actional-structural self-attention graph convolutional network for action recognition | |
| CN112233698A (en) | Character emotion recognition method and device, terminal device and storage medium | |
| EP3917131A1 (en) | Image deformation control method and device and hardware device | |
| CN108491823A (en) | Method and apparatus for generating eye recognition model | |
| CN111862990B (en) | Speaker identity verification method and system | |
| CN111291151A (en) | Interaction method and device and computer equipment | |
| Cristani et al. | Look at who’s talking: Voice activity detection by automated gesture analysis | |
| CN113128368B (en) | Method, device and system for detecting character interaction relationship | |
| CN109934191A (en) | Information processing method and device | |
| CN113111782A (en) | Video monitoring method and device based on salient object detection | |
| CN109389492A (en) | Method, system, equipment and the storage medium of probability of cheating are calculated based on micro- expression | |
| CN109784185A (en) | Client's food and drink evaluation automatic obtaining method and device based on micro- Expression Recognition | |
| CN112365957A (en) | Psychological treatment system based on virtual reality | |
| CN109031201A (en) | The voice localization method and device of Behavior-based control identification | |
| CN113868472A (en) | Method for generating digital human video and related equipment | |
| CN111144374B (en) | Facial expression recognition method and device, storage medium and electronic equipment | |
| CN117253287A (en) | Action prediction model training method based on domain generalization, related method and product | |
| CN109584051A (en) | The overdue risk judgment method and device of client based on micro- Expression Recognition | |
| CN113035176B (en) | Voice data processing method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB02 | Change of applicant information |
Address after: 201, room 518000, building A, No. 1, front Bay Road, Qianhai Shenzhen Guangdong Shenzhen Hong Kong cooperation zone (Qianhai business secretary) Applicant after: Shenzhen one ledger Intelligent Technology Co., Ltd. Address before: 518000 Guangdong city of Shenzhen province Qianhai Shenzhen Hong Kong cooperation zone before Bay Road No. 1 building 201 room A Applicant before: Shenzhen one ledger Intelligent Technology Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |