CN109543011A - Question and answer data processing method, device, computer equipment and storage medium - Google Patents
Question and answer data processing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109543011A CN109543011A CN201811235466.4A CN201811235466A CN109543011A CN 109543011 A CN109543011 A CN 109543011A CN 201811235466 A CN201811235466 A CN 201811235466A CN 109543011 A CN109543011 A CN 109543011A
- Authority
- CN
- China
- Prior art keywords
- answer
- user
- data
- question
- value
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 103
- 238000012545 processing Methods 0.000 claims abstract description 20
- 230000008569 process Effects 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 17
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000012549 training Methods 0.000 description 11
- 239000000463 material Substances 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000013507 mapping Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000001815 facial effect Effects 0.000 description 4
- SBNFWQZLDJGRLK-UHFFFAOYSA-N phenothrin Chemical compound CC1(C)C(C=C(C)C)C1C(=O)OCC1=CC=CC(OC=2C=CC=CC=2)=C1 SBNFWQZLDJGRLK-UHFFFAOYSA-N 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000011897 real-time detection Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 239000012141 concentrate Substances 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000008921 facial expression Effects 0.000 description 2
- 230000001755 vocal effect Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
This application involves artificial intelligence field, a kind of question and answer data processing method, device, computer equipment and storage medium are provided.The described method includes: receiving the user's answer data and user's answer image that terminal is sent;Determine whether user's answer data are correct according to default decision procedure;When determining that user's answer data are correct, object table mutual affection value corresponding with user's answer image is determined according to preset table mutual affection value method of determination;Object question data are determined according to the corresponding default enquirement data method of determination of the object table mutual affection value;The object question data are sent to the terminal to be shown.It can be improved the accuracy of question and answer data processing using this method.
Description
Technical field
This application involves field of artificial intelligence, more particularly to a kind of question and answer data processing method, device, computer
Equipment and storage medium.
Background technique
Question and answer under traditional credit scene depend on artificial realization mostly, with the continuous development of artificial intelligence technology, by
Gradually there is the intelligent answer based on systemic human-computer interaction, replaces business personnel to put question to user from terminal, reduce for industry
The training for industry cost of business person.
However, the verification mode for the intelligent answer realized at present is relatively simple, usually point-to-point verification mode takes
Business device is by determining that the correctness of user's answer data verifies current intelligent answer.In that way it is possible to lead to verification
Accuracy is low, to reduce the precision of intelligent answer, i.e., for the question and answer data during intelligent answer, there are question and answer data
Handle the low problem of accuracy.
Summary of the invention
Based on this, it is necessary to which in view of the above technical problems, providing a kind of can be improved asking for question and answer data processing accuracy
Answer data processing method, device, computer equipment and storage medium.
A kind of question and answer data processing method, which comprises
Receive the user's answer data and user's answer image that terminal is sent;
Determine whether user's answer data are correct according to default decision procedure;
When determining that user's answer data are correct, determines according to preset table mutual affection value method of determination and answered with the user
Inscribe the corresponding object table mutual affection value of image;
Object question data are determined according to the corresponding default enquirement data method of determination of the object table mutual affection value;
The object question data are sent to the terminal to be shown.
User's answer image includes user's answer image in one of the embodiments,;It is described to work as the judgement use
When family answer data are correct, target expression corresponding with user's answer image is determined according to preset table mutual affection value method of determination
Score value, comprising:
When determining that user's answer data are correct, user's answer is obtained according to user's answer image is corresponding
Image;
User's answer image is inputted trained micro- Expression Recognition model in advance to predict, obtains corresponding use
The micro- expression in family;
The micro- expression of the user is inputted trained expression score value prediction model in advance to predict, obtains target expression
Score value.
User's answer image includes user's answer video in one of the embodiments,;It is described to work as the judgement use
When family answer data are correct, target expression corresponding with user's answer image is determined according to preset table mutual affection value method of determination
Score value, comprising:
When determining that user's answer data are correct, user's answer is obtained according to user's answer image is corresponding
Video;
The video frame of preset quantity is extracted from user's answer video according to default extracting mode;
The corresponding expression score value of each video frame is determined respectively;
Object table mutual affection value corresponding with user's answer image is determined according to each expression score value is corresponding.
It is described in one of the embodiments, that corresponding default enquirement data method of determination is worth according to the object table mutual affection
Determine object question data, comprising:
The object table mutual affection value is compared with preset table mutual affection value;
When the object table mutual affection value reaches the preset table mutual affection value, default topic types are chosen from default exam pool
Object question data.
User's answer data and user's answer image and current enquirement data pair in one of the embodiments,
It answers;It is described that object question data are determined according to the corresponding default enquirement data method of determination of the object table mutual affection value, comprising:
The object table mutual affection value is compared with preset table mutual affection value;
When the object table mutual affection value is lower than the preset table mutual affection value, according to the current enquirement data according to default
Selection mode, selection object question data corresponding with the current enquirement data.
User's answer data and user's answer image and current enquirement data pair in one of the embodiments,
It answers;The current enquirement data are corresponding with preset comprehensive score value;The method also includes:
When the object table mutual affection value is lower than the preset table mutual affection value, adjusted according to default score value adjustment mode dynamic
The preset comprehensive score value;
According to the preset comprehensive score value and preset comprehensive score value adjusted, determination is corresponding with the object question data
Comprehensive scores.
It is described in one of the embodiments, that corresponding default enquirement data method of determination is worth according to the object table mutual affection
Before determining object question data, the method also includes:
According to default answer score value method of determination, target answer score value corresponding with user's answer data is determined;
Corresponding target comprehensive scores are determined with the object table mutual affection value according to the target answer score value;
Existing answer total score is updated according to the target comprehensive scores are corresponding;
When updated answer total score meets preset stopping condition, stop current question and answer process, Xiang Suoshu terminal hair
Send corresponding prompt information.
A kind of question and answer data processing equipment, described device include:
Receiving module, for receiving the user's answer data and user's answer image of terminal transmission;
Determination module, for determining whether user's answer data are correct according to default decision procedure;
Score value determining module is used for when determining that user's answer data are correct, according to preset table mutual affection value determination side
Formula determines object table mutual affection value corresponding with user's answer image;
Data determining module is putd question to, it is true for being worth corresponding default enquirement data method of determination according to the object table mutual affection
It sets the goal and puts question to data;
Sending module is shown for the object question data to be sent to the terminal.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes the step of question and answer data processing method provided in any one embodiment of the application when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of question and answer data processing method provided in any one embodiment of the application is provided when row.
Above-mentioned question and answer data processing method, device, computer equipment and storage medium receive user's answer that terminal is sent
Data and user's answer image determine whether user's answer data are correct, i.e. the correctness of judgement user's answer data, and according to
The correctness of user's answer data executes corresponding step, improves the treatment effeciency of question and answer data.When judgement user's answer number
According to it is correct when, determine object table mutual affection value corresponding to user's answer image, determined next time according to object table mutual affection value is corresponding
Object question data when enquirement, and identified object question data are sent to terminal and are shown, to be sent out by terminal
Play question and answer process next time.In this way, in conjunction with the corresponding determining question and answer process institute next time of user's answer data and user's answer image
Corresponding target question and answer data improve the processing accuracy for the question and answer data in current question and answer process.
Detailed description of the invention
Fig. 1 is the application scenario diagram of question and answer data processing method in one embodiment;
Fig. 2 is the flow diagram of question and answer data processing method in one embodiment;
Fig. 3 is the flow diagram of question and answer data processing method in another embodiment;
Fig. 4 is the structural block diagram of question and answer data processing equipment in one embodiment;
Fig. 5 is the structural block diagram of question and answer data processing equipment in another embodiment;
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Question and answer data processing method provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, eventually
End 102 is communicated with server 104 by network by network.Server 104 receives user's answer number that terminal 102 is sent
User's answer image institute is determined when determining that user's answer data are correct according to default decision procedure according to user's answer image
Corresponding object table mutual affection value, the default enquirement data method of determination according to corresponding to object table mutual affection value determine corresponding target
Data are putd question to, and identified object question data are sent to terminal 102 and are shown.Wherein, terminal 102 can with but it is unlimited
Then various personal computers, laptop, smart phone, tablet computer and portable wearable device, server 104 can
To be realized with the independent server either server cluster that forms of multiple servers.
In one embodiment, as shown in Fig. 2, providing a kind of question and answer data processing method, it is applied to Fig. 1 in this way
In server for be illustrated, comprising the following steps:
S202 receives user's answer data and user's answer image that terminal is sent.
Wherein, user's answer data are users for the current answer data for puing question to the corresponding feedback of data.User's answer number
The text data being manually entered according to specifically can be user in terminal is also possible to terminal pair when user answers current enquirement data
Answer collected voice messaging.User's answer image is to put question to data corresponding when corresponding to feedback answer data for current in user
Collected image information.User's answer data specifically can be corresponding collected image information during user's answer, than
As user puts question to data collected image information or user's answer when terminal is manually entered text data to work as current
Collected image information is corresponded to when preceding enquirement data.Image information specifically can be collected with image by image collection device
Or information existing for the forms such as video.User's answer image may include but be not limited to be user's answer image and user's answer view
Frequently.The collected image including user's facial image is corresponded to when the such as user's answer of user's answer image.User's answer video
For example corresponding collected video during user's answer, i.e. user carry out collected video during answer operation.Image
Collector can be camera, and camera can be arranged in the camera of terminal, be also possible to and terminal point-to-point connection
Individual components.User's answer data are corresponding with user's answer image.
Current enquirement data are current enquirement data, i.e., enquirement data corresponding to current question and answer data handling procedure.
It is current to put question to data that specifically refer to the enquirement data namely newest enquirement data nearest from current time.Put question to data
It is directed to problem data when user puts question to.Data are putd question to specifically to can be the text data being shown by display screen,
It can be the voice messaging shown by way of voice broadcast.The current user's answer number for puing question to data and terminal current feedback
Want to correspond to according to user's answer image.
Specifically, the user's answer data and user that server receiving terminal is sent by wireless network or cable network are answered
Inscribe image.User's answer data and user's answer image are corresponding with current enquirement data.Terminal receives server transmission
When current enquirement data, received current enquirement number is shown to user in such a way that voice broadcast or display screen are shown
According to, and real-time detection user puts question to data to correspond to feedback user answer data for before deserving.Terminal obtains and user's answer
The corresponding user's answer image of data, and accessed user's answer image and corresponding user's answer data are sent to clothes
Business device.
In one embodiment, server receives question and answer instruction, and question and answer instruction obtains based on the received works as accordingly
Accessed current enquirement data are sent to terminal by preceding enquirement data.Server is instructed according to question and answer from pre-stored pre-
If selecting current enquirement data in exam pool.Server can also be instructed from pre-stored enquirement centralized uploading according to question and answer and be obtained accordingly
Enquirement material, generated according to accessed enquirement material and corresponding current put question to data.Wherein, default exam pool is by multiple
Put question to the enquirement data set of data composition.The material set for puing question to material collection to be made of multiple enquirement materials.Put question to material ratio
Such as identification card number, native place, now occupy ground.
In one embodiment, when terminal shows current enquirement data to user, real-time detection user puts question to for current
The answer operation of data obtains corresponding user's answer data according to detected answer operation.Answer operation such as user
The voice messaging generated when answer data are given an oral account in the typing operation of terminal or user.
S204 determines whether user's answer data are correct according to default decision procedure.
Wherein, default decision procedure is the preset whether correct mode of judgement user's answer data.It is default to determine
Mode is for determining the whether correct foundation of user's answer data.Default decision procedure, which can be, answers received user
Topic data are compared with pre-stored default answer, determine whether user's answer data are correct according to comparison result is corresponding, i.e.,
The corresponding correctness for determining user's answer data.Default answer is the correct option or model answer of default settings.
Specifically, server inquires pre-stored preset according to current enquirement data corresponding with user's answer data are corresponding
Answer matches the default answer inquired with received user's answer data, and corresponding according to matching result
Determine whether user's answer data are correct.When successful match, server then determines that user's answer data are correct;When it fails to match
When, then determine user's answer error in data.Server can calculate the matching rate between default answer and relative users answer data.
When the matching rate of calculating reaches preset matching rate threshold value, server then determines user's answer data and accordingly default answer
With success.
In one embodiment, when user's answer data are text data, server by the received text data of institute with
The corresponding default answer inquired is matched, and then determines the correctness of this article notebook data.In one embodiment, work as user
When answer data-voice information, server carries out speech recognition to the voice messaging and obtains corresponding speech text content, will know
Not Chu speech text content matched with corresponding default answer, to determine the correctness of the speech text content, in turn
Determine the correctness of corresponding voice messaging.
S206, when determining that user's answer data are correct, according to the determination of preset table mutual affection value method of determination and user's answer
The corresponding object table mutual affection value of image.
Wherein, preset table mutual affection value method of determination is preset for determining target according to user's answer image is corresponding
The mode of expression score value.Default expression method of determination specifically can be extracts the micro- table of corresponding user from user's answer image
Feelings determine target expression corresponding with user's answer image according to the micro- expression of the user extracted by means of micro- Expression Recognition technology
Score value.Object table mutual affection value is divided according to user's expression of the corresponding determination of user's answer image corresponding with user's answer data
Value.Object table mutual affection value specifically can be the corresponding determining user's expression of the micro- expression of user for being included according to user's answer image
Score value.Object table mutual affection value can be used for characterizing that user is practical knows that a possibility that currently puing question to correct option corresponding to data is big
It is small.Object table mutual affection value is higher to show that user practical a possibility that knowing correct option is bigger.In other words, object table mutual affection value
It can be that determining according to the micro- expression of user, user is practical knows that a possibility that currently puing question to correct option corresponding to data is big
It is small.Object table mutual affection value can be used for determining that user when answering current enquirement data, is done because correct option is actually known
Answer out, or because actually it is unaware of the answer that correct option is made by conjecture.Object table mutual affection value can refer to
Score corresponding to the micro- expression of user, such as 80 points.Object table mutual affection value may also mean that percentage corresponding to the micro- expression of user
Number, such as 80%.Wherein, object table mutual affection value is that 80% can refer to that user is at practical a possibility that knowing correct option
80%.
The micro- expression of user (micro-expression) is the very of short duration facial expression for being unable to autonomous control of the mankind,
It is the very quick expression for a kind of duration being only 1/25 second to 1/5 second.The micro- expression of user be cannot artificially hide or
Camouflage, it is able to reflect out the facial expression of the real feelings of people.Determining user can be corresponded to according to the micro- expression of user to ask in answer
It is simple and direct when topic, or exists and hesitate.
Specifically, when determining that user's answer data are correct, server is answered from user corresponding with user's answer data
The micro- expression of corresponding user is extracted in topic image, and by means of micro- Expression Recognition technology, according to the micro- expression of the user extracted
Determine object table mutual affection value corresponding with user's answer image.User's answer image is inputted trained micro- expression by server
Identification model is predicted, the micro- expression of corresponding user is obtained.Server has trained the micro- expression input of user that prediction obtains
Expression score value prediction model predicted, obtain corresponding object table mutual affection value, namely obtain corresponding with user's answer image
Object table mutual affection value.
In one embodiment, when determining that user's answer data are correct, server is defeated by corresponding user's answer image
Enter the prediction model trained to be predicted, obtains corresponding target labels score value.
S208 determines object question data according to the corresponding default enquirement data method of determination of object table mutual affection value.
Wherein, object question data are the enquirement data initiated next time to user when puing question to.Object question data refer to
Another problem data after currently puing question to data.Object question data specifically can be and can be shown by display screen
Text data is also possible to the voice messaging that can be shown by way of voice broadcast.Default enquirement data method of determination is pre-
What is first set is used to determine that respective objects put question to the mode of data according to object table mutual affection value.It is default put question to data method of determination with
Object table mutual affection value is corresponding.Default enquirement data method of determination, which specifically can be, randomly chooses object question from default exam pool
Data are also possible to put question to data to determine corresponding object question data according to current.
Specifically, server determines corresponding default enquirement data method of determination according to identified object table mutual affection value,
And corresponding object question data are determined according to identified default enquirement data method of determination.Target is pre-stored in server
Expression score value and the default corresponding relationship putd question between data method of determination.Server should according to the corresponding inquiry of object table mutual affection value
Object table mutual affection value and the corresponding default corresponding relationship putd question between data method of determination, and according to the corresponding relationship inquired
Determine default enquirement data method of determination corresponding with the object table mutual affection value.Server can be according to default enquirement data determination side
Formula selects the object question data of preset kind from pre-stored default exam pool.Server can also be true according to default enquirement data
Determine mode, puts question to data and the determining object question number relevant to current enquirement data of the knowledge mapping constructed according to current
According to.
In one embodiment, preset table mutual affection value section and default enquirement data method of determination are pre-stored in server
Between corresponding relationship.Server matches object table mutual affection value with pre-stored preset table mutual affection value section, will match
Default enquirement data method of determination corresponding to successful preset table mutual affection value section, is determined as corresponding with the object table mutual affection value
Default enquirement data method of determination.Server by object table mutual affection value respectively with each expression in preset table mutual affection value section
Score value is matched, to determine whether the object table mutual affection value falls into the preset table mutual affection value section, so that it is determined that object table
Matching result between mutual affection value and preset table mutual affection value section.
In one embodiment, server selection target can put question to data from default exam pool.Server can also be from prestoring
The enquirement centralized uploading of storage obtains corresponding enquirement material, and generates corresponding object question according to accessed enquirement material
Data.Object question data put question to data can be related or uncorrelated to current.Object question data and current enquirement number
It can be the same or different according to corresponding topic types.Topic types corresponding to object question data specifically can basis
It is current to put question to topic types corresponding to data, object table mutual affection value and corresponding default enquirement data method of determination corresponding true
It is fixed.
Object question data are sent to terminal and are shown by S210.
Specifically, server determines corresponding mesh according to default enquirement data method of determination corresponding to object table mutual affection value
After mark puts question to data, identified object question data are sent to terminal.Terminal leads to received object question data
Cross that display screen is shown or the mode of voice broadcast shows relative users.
In one embodiment, terminal is in such a way that voice broadcast or display screen are shown to received by user's displaying
When object question data, real-time detection user corresponds to feedback user answer data for the object question data, and will be detected
To user's answer data be sent to server so that user's answer data continue to execute server based on the received
State the correlation step of question and answer data processing method.
Above-mentioned question and answer data processing method, receive terminal for the current user's answer data for puing question to the corresponding feedback of data and
User's answer image determines the correctness of user's answer data, and executes corresponding step according to the correctness of user's answer data
Suddenly, the treatment effeciency of question and answer data is improved.When determining that user's answer data are correct, determine corresponding to user's answer image
Object table mutual affection value, according to the corresponding object question data determined when puing question to next time of object table mutual affection value, and will be identified
Object question data are sent to terminal and are shown, to initiate question and answer process next time by terminal.In this way, in conjunction with user's answer
Target question and answer data corresponding to data and the corresponding determining question and answer process next time of user's answer image, improve to be directed to and currently ask
Answer the processing accuracy of the question and answer data in process.
In one embodiment, user's answer image includes user's answer image;Step S206 includes: when judgement user answers
When topic data are correct, user's answer image is obtained according to user's answer image is corresponding;User's answer image is inputted into training in advance
Good micro- Expression Recognition model is predicted, the micro- expression of corresponding user is obtained;The micro- expression input of user is trained in advance
Expression score value prediction model is predicted, object table mutual affection value is obtained.
Wherein, user's answer image, which refers to, corresponds to the collected image including user's facial image in user's answer.
User's facial image refer to include user's face image.User's facial image, which specifically can be, carries out answer operation in user
When the collected user's head portrait photo of institute or user's major part shine.Micro- Expression Recognition model is according to the training sample set obtained in advance
Carry out model training acquisition, can be used in model according to the unknown micro- expression of user of known user's answer image prediction.
Expression score value prediction model be carried out according to the training sample set that obtains in advance model training acquisition, can be used in known to
The micro- expression of user predict the model of unknown object table mutual affection value.
Specifically, when determining that user's answer data are correct, server is answered from user corresponding with user's answer data
Corresponding user's answer image is obtained in topic image.Server is inputted accessed user's answer image as input feature vector
In preparatory trained micro- Expression Recognition model, the user's answer image inputted is carried out by micro- Expression Recognition model pre-
It surveys, obtains the micro- expression of corresponding user.The micro- expression input of the user that server obtains micro- Expression Recognition model prediction is instructed in advance
The expression score value prediction model perfected predicts the micro- expression of the user by the expression score value prediction model, obtains corresponding
Object table mutual affection value.
In one embodiment, server obtains the first training sample set, which includes target user
The micro- expression of target user corresponding to answer image and target user's answer image.Wherein, target user's answer image has more
A, each target user's answer image is corresponding with the micro- expression of corresponding target user.Server concentrates first training sample
Each user's answer image respectively as input feature vector, it is special using the micro- expression of corresponding target user as desired output
Sign, is trained micro- Expression Recognition model of initialization, obtains the micro- Expression Recognition model trained.Server can obtain more
A target user's answer image, and corresponding target user's answer image is obtained from each target user's answer image respectively.
In one embodiment, server obtains the second training sample set, and the second training sample set includes that target user is micro-
Object table mutual affection value corresponding to expression and the micro- expression of the target user.Wherein, the micro- expression of target user has multiple, each target
The micro- expression of user is corresponding with corresponding object table mutual affection value.The micro- table of each target user that server concentrates the second training sample
Feelings are respectively as input feature vector, using corresponding object table mutual affection value as desired output feature, to the expression of initialization
Score value prediction model is trained, and obtains the expression score value prediction model trained.Server can obtain multiple target users and answer
Image is inscribed, corresponding target is extracted from each target user's answer image by the micro- Expression Recognition model trained respectively and is used
The micro- expression in family.
In one embodiment, user's answer image includes multiframe user's answer image.When determine user's answer data just
When true, server obtains corresponding multiframe user answer image from user's answer image.Server is by every framed user's answer figure
It is predicted as inputting the micro- Expression Recognition model trained respectively, obtains the micro- expression of corresponding user, and prediction is obtained
Each micro- expression of user inputs the expression score value prediction model trained respectively and predicts, obtains corresponding expression score value.Service
Device expression score value according to corresponding to every framed user's answer image, it is corresponding to determine object table corresponding to relative users answer image
Mutual affection value.For example, server can be weighted evaluation to the corresponding expression score value of every framed user's answer image, corresponding mesh is obtained
Mark expression score value.
In above-described embodiment, by means of the micro- Expression Recognition model and expression score value prediction model trained, according to user
User's answer image included by answer image obtains corresponding object table mutual affection value, improves the prediction effect of object table mutual affection value
Rate and accuracy, to improve question and answer data-handling efficiency and accuracy.
In one embodiment, user's answer image includes user's answer video;Step S206 includes: when judgement user answers
When topic data are correct, user's answer video is obtained according to user's answer image is corresponding;According to default extracting mode from user's answer
The video frame of preset quantity is extracted in video;The corresponding expression score value of each video frame is determined respectively;According to each expression score value pair
It should determine object table mutual affection value corresponding with user's answer image.
Wherein, user's answer video refers to corresponds to collected video during user's answer, i.e., user carries out answer
Collected video in operating process.Video frame is the basic composition unit of user's answer video.One video frame corresponds to video
In a tableaux, multiple video frames form videos.Preset quantity is preset numerical value, can be according to the actual situation
It is customized, such as 3.Default extracting mode is the preset side that preset quantity video frame is extracted from user's answer video
Formula.Default extracting mode is used to indicate the video frame how server obtains preset quantity from user's answer video.It is default to mention
Take mode can be from user's answer video obtain preset quantity successive video frames, be also possible to according to preset step-length from
The video frame of preset quantity is obtained in family answer video.
Specifically, when determining that user's answer data are correct, server is answered from user corresponding with user's answer data
Corresponding user's answer video is obtained in topic image.Server is according to default extracting mode from accessed user's answer video
The middle video frame for extracting preset quantity, and micro- Expression Recognition model and expression score value prediction model by means of having trained, according to
Aforesaid way respectively predicts each video frame, obtains expression score value corresponding to each video frame.Server is according to pre-
If the corresponding expression score value of the video frame of quantity, determination object table mutual affection corresponding with relative users answer image is corresponded to
Value.Expression score value corresponding to each video frame can be weighted evaluation by server, obtain corresponding object table mutual affection value.Service
Device can also be using expression score value corresponding to each video frame as input feature vector, and trained score value prediction model carries out in advance for input
Prediction, obtains corresponding object table mutual affection value.
In one embodiment, server obtains the successive video frames of preset quantity from user's answer video.At one
In embodiment, server obtains the video frame of preset quantity according to preset step-length from user's answer video.Wherein, acquired
Interval in the video frame of preset quantity between any two adjacent video frame is preset step-length.Preset step-length refers to acquisition phase
The interval of adjacent two video frames.Preset step-length specifically can be the video frame of specified quantity, such as 5 frames.Server is answered in user
It inscribes in video and obtains a video frame every the video frame of specified quantity, until stopping obtaining when getting the video frame of preset quantity
It takes.
In above-described embodiment, server extracts preset quantity video frame, the comprehensive preset quantity from user's answer video
The corresponding expression score value of video frame determines respective objects expression score value, improves the accuracy of object table mutual affection value, thus
Improve the accuracy of question and answer data processing.
In one embodiment, step S208 includes: to be compared object table mutual affection value with preset table mutual affection value;Work as mesh
When mark expression score value reaches preset table mutual affection value, the object question data of default topic types are chosen from default exam pool.
Wherein, preset table mutual affection value is preset expression point threshold, such as 86 points or 86%.Default expression
Score value is that the corresponding default foundation for puing question to data method of determination is determined according to object table mutual affection value.Default topic types are to set in advance
Fixed topic types.Topic types, which refer to, puts question to type corresponding to data, such as identity type, address style.Identity type
Enquirement data such as " six bit digitals are how many after the ID card No. that could you tell me ", the enquirement data of address style such as " ask
Where ask you current inhabitation address is ".
Specifically, identified object table mutual affection value is compared by server with preset table mutual affection value.When target expression
When score value reaches preset table mutual affection value, show that expression of user during answer is normally, that is, to show according to user's answer
Image can determine that the practical correct option for knowing currently to put question to data of user, further demonstrate relative users answer data just
True property, server choose the object question data of default topic types from pre-stored default exam pool.
In one embodiment, server local is pre-configured with one or more topic types corresponding with question and answer link.
For multiple topic types of pre-configuration, it is right in corresponding question and answer process institute that server local is pre-configured with multiple topic types
Answer question and answer sequence, such as address style enquirements data later be identity type enquirement data.Assuming that currently puing question to data
Corresponding topic types are address style, put question to object table mutual affection value corresponding to data to reach preset table mutual affection value currently
When, server determines that topic types corresponding to object question data are identity type according to the question and answer sequence of pre-configuration.Service
Device then screens the enquirement data of identity type from default exam pool, and selection target puts question to number from the enquirement data filtered out
According to.
In one embodiment, default topic types corresponding to object question data are putd question to corresponding to data with current
Topic types it is different.
In above-described embodiment, number is currently putd question to when determining that user is directed to according to user's answer data and user's answer image
When correct according to user's answer data of corresponding feedback, then the enquirement data of other default topic types is selected to continue to mention to user
It asks, to reduce enquirement data bulk, to reduce the question and answer data processing quantity in entire question and answer process, and then improves question and answer number
According to treatment effeciency.
In one embodiment, user's answer data and user's answer image are corresponding with current enquirement data;Step S208
It include: to be compared object table mutual affection value with preset table mutual affection value;When object table mutual affection value is lower than preset table mutual affection value, root
Put question to data according to default selection mode, selection object question data corresponding with current enquirement data according to current.
Wherein, default selection mode is preset for according to the current side for puing question to data selection target to put question to data
Formula.Default selection mode specifically can be the object question data relevant to current enquirement data of the selection from default exam pool,
It can be and corresponding object question data are selected based on the knowledge mapping constructed.It is mentioned according to the target that default selection mode selects
It asks topic types corresponding to data, puts question to topic types corresponding to data can be the same or different with current.
Specifically, server compares object table mutual affection value corresponding to user's answer image and preset table mutual affection value
Compared with.When object table mutual affection value be lower than preset table mutual affection value when, server according to default selection mode according to user's answer data
Current enquirement data corresponding with user's answer image select object question data relevant to preceding enquirement data are deserved.Service
Device can put question to data to select object question data relevant to preceding enquirement data are deserved from default exam pool according to current.Server
Data can also be putd question to select relevant object question data from the knowledge mapping constructed according to current.It is current put question to data with
Corresponding determining object question data can be corresponding with identical or corresponding keyword, identical or corresponding keyword it is such as identical or
Some similar address.
In one embodiment, when object table mutual affection value is lower than preset table mutual affection value, server puts question to number according to current
According to corresponding user's answer data, object question number relevant to user's answer data is selected according to default selection mode
According to.It illustrates, it is assumed that current to put question to data are " could you tell me where current inhabitation address is ", the corresponding user received answers
Inscribing data is " I currently stays in Nanshan District, Shenzhen City Science Court road 28 ".When object table mutual affection value is lower than preset table mutual affection value,
Server may select corresponding target to mention according to the address " Nanshan District, Shenzhen City Science Court road 28 " in user's answer data
Ask data, such as " No. 28 from Nanshan District, Shenzhen City Science Court road 50 meters of range Nei Youge China Merchants Banks ".
In one embodiment, default exam pool is the exam pool being pre-configured in database.The knowledge mapping constructed is
The data structure based on figure constructed in advance according to knowledge mapping building mode.The building of knowledge mapping can be based on known knowledge
Map construction mode realizes that details are not described herein.
In above-described embodiment, when determining that user's answer data are correct, and according to the relative users answer scope interpretation user
When the correctness of answer data leaves a question open, selection object question data relevant to current enquirement data, according to object question number
Deserve the preceding correctness for puing question to data according to further determining that, so that the current user identity for carrying out answer operation of verifying is reliable
Property, it ensure that the correctness of question and answer data processing.
In one embodiment, user's answer data and user's answer image are corresponding with current enquirement data;It is current to put question to
Data are corresponding with preset comprehensive score value;Above-mentioned question and answer data processing method further include: when object table mutual affection value is lower than default expression
When score value, according to default score value adjustment mode dynamic adjustment preset comprehensive score value;According to preset comprehensive score value and adjusted pre-
If comprehensive scores, comprehensive scores corresponding with object question data are determined.
Wherein, preset comprehensive score value is preset comprehensive scores corresponding with current enquirement data.Preset comprehensive point
Value includes preset table mutual affection value and default answer score value.Preset comprehensive score value can be regarded as currently puing question to full marks corresponding to data
Score value.Default answer score value can be regarded as full marks score value corresponding to user's answer data, such as when user puts question to for current
When user's answer data of data feedback are consistent with correct option, then corresponding target answer data are determined as full marks score value,
Answer score value will be preset and be determined as target answer score value.Similarly, preset table mutual affection value can be regarded as user's answer image institute
Corresponding full marks score value.
Specifically, when object table mutual affection value is lower than preset table mutual affection value, server is moved according to default score value adjustment mode
State adjusts preset comprehensive score value corresponding to current enquirement data corresponding with user's answer data and user's answer image.Service
Device puts question to preset comprehensive score value corresponding to data according to preset comprehensive score value adjusted and before deserving, corresponding to determine that target mentions
Ask comprehensive scores corresponding to data.When being left a question open according to the correctness of user's answer scope interpretation relative users answer data,
Server is then by the current partial scores dynamic transfer putd question in preset comprehensive score value corresponding to data to object question data.
In one embodiment, preset comprehensive score value includes preset table mutual affection value and default answer score value.When target expression
When score value is lower than preset table mutual affection value, server puts question to preset table mutual affection value corresponding to data to be determined as mentioning with target for current
Ask data corresponding comprehensive scores.Meanwhile server puts question to default answer score value corresponding to data to be determined as adjusting for current
Preset comprehensive score value afterwards.Server can put question in preset comprehensive score value corresponding to data according to current, preset table mutual affection value
With the corresponding score value accounting of default answer score value, the corresponding expression determined in comprehensive scores corresponding to object question data
Score value and answer score value.
In one embodiment, when object table mutual affection value is lower than preset table mutual affection value, server is according to user's answer number
Comprehensive point of corresponding target is determined according to the corresponding target answer score value of determination, and according to target answer score value and object table mutual affection value
Value, and then identified target comprehensive scores are determined as comprehensive scores corresponding with object question data.
In one embodiment, when object table mutual affection value is lower than preset table mutual affection value, server is according to default score value ratio
Preset comprehensive score value corresponding to data is putd question to current, determines that current enquirement data and object question data dynamic adjust respectively
Corresponding comprehensive scores afterwards.It illustrates, it is assumed that default score value ratio is 3:2, i.e., after execution dynamic adjustment step, works as premise
The ratio for asking data and the corresponding comprehensive scores of object question data is 3:2.Assuming that preset comprehensive score value is 50 points, according to
Default score value is 30 points than corresponding determining preset comprehensive score adjusted, corresponding with current enquirement data, object question
Comprehensive scores corresponding to data are 20 points.
In one embodiment, server local is pre-configured with and puts question to data bulk involved in question and answer link, and every
Preset comprehensive score value corresponding to a enquirement data.
In one embodiment, server local is pre-configured with multiple topic types corresponding with question and answer link, and every
Preset comprehensive score value corresponding to a topic types.Wherein, preset comprehensive score value corresponding to each topic types can be identical
It can also be different.For the topic types of class must be answered, it can configure higher preset comprehensive score value, the topic types of class must be answered such as
Identity class.In question and answer link, when selecting the enquirement data of some topic types for the first time, server will be corresponding to the topic types
Preset comprehensive score value, be determined as preset comprehensive score value corresponding to the enquirement data selected for the first time for the topic types.
In above-described embodiment, when being left a question open according to the correctness of user's answer scope interpretation relative users answer data, move
The current pre- comprehensive scores for puing question to data of state adjustment, and comprehensive scores corresponding to corresponding determining object question data, in order to
According to object question data and the current enquirement corresponding target comprehensive scores of data, determines and putd question to corresponding to data before deserving
Final target comprehensive scores, taking property of target comprehensive scores standard is improved, to improve the accuracy of question and answer data processing.
In one embodiment, before step S208, above-mentioned question and answer data processing method further include: according to default answer point
It is worth method of determination, determines target answer score value corresponding with user's answer data;According to target answer score value and object table mutual affection
Value determines corresponding target comprehensive scores;Existing answer total score is updated according to target comprehensive scores are corresponding;When updated
When answer total score meets preset stopping condition, stop current question and answer process, sends corresponding prompt information to terminal.
Wherein, answer score value method of determination is preset to be predetermined according to the corresponding determining target answer of user's answer data
The mode of score value.Default answer score value method of determination can be according to the matching between user's answer data and corresponding default answer
Rate, and default answer score value corresponding to current enquirement data determine corresponding target answer score value.Such as, it is assumed that it presets comprehensive
Closing score value is 50 points, and calculating resulting matching rate is 80%, then corresponding determining target answer score value is 40 points.Default answer point
Value method of determination is also possible to predict the preparatory trained answer score value prediction model of user's answer data input, obtain
Corresponding target answer score value.
Existing answer total score refers to according to corresponding to the current one or more enquirement data putd question to before data
The corresponding determining total score of target comprehensive scores.The one or more puts question to target comprehensive scores corresponding to data, and works as
Target comprehensive scores corresponding to preceding enquirement data correspond to same user identifier.In other words, data are currently putd question to and are deserved
Target comprehensive scores corresponding to one or more enquirement data between preceding enquirement data, are according to same user for phase
The user's answer data and the corresponding determining answer score value of user's answer image of the corresponding feedback of data should be putd question to.Answer total score can
To be according to the corresponding determining total score of the corresponding target comprehensive scores of multiple enquirement data.Answer total score can be pair
The total score that multiple target comprehensive scores are directly summed or weighted sum obtains.Preset stopping condition is to preset
For determining whether to stop the foundation of current question and answer process.Preset stopping condition specifically can be updated answer total score
Reach default total score threshold value.
Specifically, server determines corresponding target according to user's answer data according to default answer score value method of determination
Answer score value, and the target answer score value and corresponding object table mutual affection value are subjected to summation and obtain comprehensive point of corresponding target
Value.Server user identifier according to corresponding to user's answer data and user's answer image, the corresponding existing answer of inquiry are total
Score value, and put question to target comprehensive scores corresponding to data are corresponding to update inquired answer total score according to current.Service
Updated answer total score is compared by device with default total score threshold value.When updated answer total score reaches default total
When point threshold, server stops current question and answer process, does not continue to execute according to the corresponding default enquirement of object table mutual affection value
Data method of determination determines the correlation step of object question data.Server generates corresponding according to updated answer total score
Prompt information, and it is sent to terminal.
It illustrates, it is assumed that current enquirement data are the third road problem datas that relative users are answered, in the manner described above
Target comprehensive scores corresponding to the determining third road problem data are 20 points, first of problem data and second topic number
It is respectively 30 points and 20 points according to corresponding target comprehensive scores, then existing answer total score is 50 points, after corresponding update
Answer total score be 70 points.Assuming that default total score threshold value is 60 points, then updated answer total score is greater than default total score
It is worth threshold value, meets preset stopping condition.
In one embodiment, server is directly summed or is weighted to target answer score value and object table mutual affection value
Summation, obtains corresponding target comprehensive scores.The weight of weighted sum can be customized.
In one embodiment, process is examined when the question and answer data processing method in above-mentioned each embodiment is applied to debt-credit face
In question and answer link when, server stops corresponding question and answer process, and examines the prompt information passed through to terminal push expression face.Face
It examines and refers to user identity is audited during lending and borrowing business is handled.
In one embodiment, server statistics put question to data count amount, and by the enquirement data count amount of statistics and in advance
If amount threshold is compared.When the enquirement data count amount of statistics reaches preset quantity threshold value, server then stops currently
Question and answer process, and target comprehensive scores corresponding to data are corresponding to update existing answer total score according to puing question to before deserving, into
And corresponding prompt information is pushed to terminal according to updated answer total score and default total score threshold value.It is answered when updated
When topic total score reaches default total score threshold value, server sends expression face to terminal and examines the prompt information passed through.After update
Answer total score when being lower than default total score threshold value, server sends the prompt information that failure is examined in expression face to terminal.
In one embodiment, when determining that user's answer data are correct, server will can preset accordingly answer score value
It is determined as target comprehensive scores.When determining user's answer error in data, server can determine corresponding target answer score value
For zero.
In one embodiment, when determining user's answer error in data corresponding to current enquirement data, server can
Stop current question and answer process, and sends corresponding prompt information to terminal.Server can also select default topic from default exam pool
The object question data of mesh type continue to execute current question and answer stream according to selected object question data in the manner described above
Journey.The total quantity of the enquirement data of server statistics relative users answer error in data, when the total quantity of statistics reaches default total
When quantity, server stops current question and answer process, and sends corresponding prompt information to terminal.
In one embodiment, user's answer voice messaging that server receiving terminal is sent, to user's answer voice
Information carries out Application on Voiceprint Recognition and obtains corresponding vocal print feature, and the identity of relative users is further verified according to vocal print feature.Its
In, Application on Voiceprint Recognition can realize that details are not described herein based on existing various sound groove recognition technology in e.When according to user's answer data
When correct for the current user's answer data for puing question to data with user's answer scope interpretation relative users, server is obtained from terminal
Take corresponding user's answer voice messaging.
In one embodiment, server obtains the tone and intonation of user from user's answer voice messaging, and according to
Tell that the tone got and intonation further verify the correctness of user's answer data.
As shown in figure 3, in one embodiment, provide a kind of question and answer data processing method, this method specifically include with
Lower step:
S302 receives user's answer data and user's answer image that terminal is sent.
S304 determines whether user's answer data are correct according to default decision procedure.
S306 obtains user's answer image according to user's answer image is corresponding when determining that user's answer data are correct.
User's answer image is inputted trained micro- Expression Recognition model in advance and predicted, obtained corresponding by S308
The micro- expression of user.
The micro- expression of user is inputted trained expression score value prediction model in advance and predicted, obtains object table by S310
Mutual affection value.
S312 obtains user's answer video according to user's answer image is corresponding when determining that user's answer data are correct.
S314 extracts the video frame of preset quantity according to default extracting mode from user's answer video.
S316 determines the corresponding expression score value of each video frame respectively.
S318 corresponds to determination object table mutual affection value corresponding with user's answer image according to each expression score value.
S320 determines target answer score value corresponding with user's answer data according to default answer score value method of determination.
S322 determines corresponding target comprehensive scores with object table mutual affection value according to target answer score value.
S324 updates existing answer total score according to target comprehensive scores are corresponding.
S326 stops current question and answer process when updated answer total score meets preset stopping condition, sends out to terminal
Send corresponding prompt information.
Object table mutual affection value is compared by S328 with preset table mutual affection value.
S330 chooses default topic types when object table mutual affection value reaches preset table mutual affection value from default exam pool
Object question data.
S332 puts question to data according to default selecting party when object table mutual affection value is lower than preset table mutual affection value according to current
Formula, selection object question data corresponding with current enquirement data;User's answer data and user's answer image and current enquirement
Data are corresponding.
Object question data are sent to terminal and are shown by S334.
In above-described embodiment, by means of the correctness of user's answer Image-aided verifying relative users answer data, when testing
When card user's answer data are correct, corresponding object question number is determined according to object table mutual affection value corresponding to user's answer image
According to improving the accuracy of question and answer data processing.Further, determined whether to stop current question and answer stream according to answer total score
Journey improves the efficiency of question and answer data processing.
It should be understood that although each step in the flow chart of Fig. 2-3 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-3
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 4, providing a kind of question and answer data processing equipment 400, comprising: receiving module
402, determination module 404, score value determining module 406, enquirement data determining module 408 and sending module 410, in which:
Receiving module 402, for receiving the user's answer data and user's answer image of terminal transmission.
Determination module 404, for determining whether user's answer data are correct according to default decision procedure.
Score value determining module 406 is used for when determining that user's answer data are correct, according to preset table mutual affection value method of determination
Determine object table mutual affection value corresponding with user's answer image.
Data determining module 408 is putd question to, it is true for being worth corresponding default enquirement data method of determination according to object table mutual affection
It sets the goal and puts question to data.
Sending module 410 is shown for object question data to be sent to terminal.
In one embodiment, user's answer image includes user's answer image;Score value determining module 406 is also used to work as
When determining that user's answer data are correct, user's answer image is obtained according to user's answer image is corresponding;User's answer image is defeated
Enter preparatory trained micro- Expression Recognition model to be predicted, obtains the micro- expression of corresponding user;The micro- expression input of user is pre-
First trained expression score value prediction model is predicted, obtains object table mutual affection value.
In one embodiment, user's answer image includes user's answer video;Score value determining module 406 is also used to work as
When determining that user's answer data are correct, user's answer video is obtained according to user's answer image is corresponding;According to default extracting mode
The video frame of preset quantity is extracted from user's answer video;The corresponding expression score value of each video frame is determined respectively;According to each
Expression score value corresponds to determination object table mutual affection value corresponding with user's answer image.
In one embodiment, data determining module 408 is putd question to, is also used to object table mutual affection value and preset table mutual affection value
It is compared;When object table mutual affection value reaches preset table mutual affection value, the target of default topic types is chosen from default exam pool
Put question to data.
In one embodiment, user's answer data and user's answer image are corresponding with current enquirement data;Put question to data
Determining module 408 is also used to for object table mutual affection value being compared with preset table mutual affection value;When object table mutual affection value is lower than default
When expression score value, put question to data according to default selection mode, selection object question corresponding with current enquirement data according to current
Data.
As shown in figure 5, in one embodiment, user's answer data and user's answer image and current data pair are putd question to
It answers;It is current that data is putd question to be corresponding with preset comprehensive score value;Above-mentioned question and answer data processing equipment 400, further includes: score value adjusts module
412;
Score value adjusts module 412, for being adjusted according to default score value when object table mutual affection value is lower than preset table mutual affection value
Mode dynamic adjustment preset comprehensive score value;According to preset comprehensive score value and preset comprehensive score value adjusted, determination is mentioned with target
Ask data corresponding comprehensive scores.
In one embodiment, above-mentioned question and answer data processing equipment 400 further include: total score update module 414;
Total score update module 414, for according to default answer score value method of determination, determination to be corresponding with user's answer data
Target answer score value;Corresponding target comprehensive scores are determined with object table mutual affection value according to target answer score value;According to target
Comprehensive scores are corresponding to update existing answer total score;When updated answer total score meets preset stopping condition, stop
Current question and answer process sends corresponding prompt information to terminal.
Specific about question and answer data processing equipment limits the limit that may refer to above for question and answer data processing method
Fixed, details are not described herein.Modules in above-mentioned question and answer data processing equipment can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 6.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing corresponding to current enquirement data corresponding with user's answer data and user's answer image
Default answer.The network interface of the computer equipment is used to communicate with external terminal by network connection.The computer program
To realize a kind of question and answer data processing method when being executed by processor.
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor realize the step of the question and answer data processing method in above-mentioned each embodiment when executing computer program
Suddenly.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes the step of question and answer data processing method in above-mentioned each embodiment when being executed by processor.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of question and answer data processing method, which comprises
Receive the user's answer data and user's answer image that terminal is sent;
Determine whether user's answer data are correct according to default decision procedure;
When determining that user's answer data are correct, according to the determination of preset table mutual affection value method of determination and user's answer shadow
As corresponding object table mutual affection value;
Object question data are determined according to the corresponding default enquirement data method of determination of the object table mutual affection value;
The object question data are sent to the terminal to be shown.
2. the method according to claim 1, wherein user's answer image includes user's answer image;Institute
It states when determining that user's answer data are correct, according to the determination of preset table mutual affection value method of determination and user's answer image
Corresponding object table mutual affection value, comprising:
When determining that user's answer data are correct, user's answer figure is obtained according to user's answer image is corresponding
Picture;
User's answer image is inputted preparatory trained micro- Expression Recognition model to predict, it is micro- to obtain corresponding user
Expression;
The micro- expression of the user is inputted trained expression score value prediction model in advance to predict, obtains object table mutual affection
Value.
3. the method according to claim 1, wherein user's answer image includes user's answer video;Institute
It states when determining that user's answer data are correct, according to the determination of preset table mutual affection value method of determination and user's answer image
Corresponding object table mutual affection value, comprising:
When determining that user's answer data are correct, user's answer view is obtained according to user's answer image is corresponding
Frequently;
The video frame of preset quantity is extracted from user's answer video according to default extracting mode;
The corresponding expression score value of each video frame is determined respectively;
Object table mutual affection value corresponding with user's answer image is determined according to each expression score value is corresponding.
4. the method according to claim 1, wherein described mention according to corresponding preset of the object table mutual affection value
Ask that data method of determination determines object question data, comprising:
The object table mutual affection value is compared with preset table mutual affection value;
When the object table mutual affection value reaches the preset table mutual affection value, the mesh of default topic types is chosen from default exam pool
Mark puts question to data.
5. the method according to claim 1, wherein user's answer data and user's answer image with
It is current to put question to data corresponding;It is described to determine that target mentions according to the corresponding default enquirement data method of determination of the object table mutual affection value
Ask data, comprising:
The object table mutual affection value is compared with preset table mutual affection value;
When the object table mutual affection value is lower than the preset table mutual affection value, according to the current enquirement data according to default selection
Mode, selection object question data corresponding with the current enquirement data.
6. according to claim 1 to method described in 5, which is characterized in that user's answer data and user's answer shadow
As puing question to data corresponding with current;The current enquirement data are corresponding with preset comprehensive score value;The method also includes:
When the object table mutual affection value is lower than the preset table mutual affection value, according to described in default score value adjustment mode dynamic adjustment
Preset comprehensive score value;
According to the preset comprehensive score value and preset comprehensive score value adjusted, determination is corresponding comprehensive with the object question data
Close score value.
7. according to claim 1 to method described in 5, which is characterized in that described corresponding pre- according to object table mutual affection value
If before puing question to data method of determination to determine object question data, the method also includes:
According to default answer score value method of determination, target answer score value corresponding with user's answer data is determined;
Corresponding target comprehensive scores are determined with the object table mutual affection value according to the target answer score value;
Existing answer total score is updated according to the target comprehensive scores are corresponding;
When updated answer total score meets preset stopping condition, stop current question and answer process, Xiang Suoshu terminal sends phase
The prompt information answered.
8. a kind of question and answer data processing equipment, which is characterized in that described device includes:
Receiving module, for receiving the user's answer data and user's answer image of terminal transmission;
Determination module, for determining whether user's answer data are correct according to default decision procedure;
Score value determining module is used for when determining that user's answer data are correct, true according to preset table mutual affection value method of determination
Fixed object table mutual affection value corresponding with user's answer image;
Data determining module is putd question to, for determining mesh according to the corresponding default enquirement data method of determination of the object table mutual affection value
Mark puts question to data;
Sending module is shown for the object question data to be sent to the terminal.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811235466.4A CN109543011A (en) | 2018-10-16 | 2018-10-16 | Question and answer data processing method, device, computer equipment and storage medium |
PCT/CN2018/125151 WO2020077874A1 (en) | 2018-10-16 | 2018-12-29 | Method and apparatus for processing question-and-answer data, computer device, and storage medium |
SG11201913925YA SG11201913925YA (en) | 2018-10-16 | 2018-12-29 | Question and answer data processing method and apparatus, computer device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811235466.4A CN109543011A (en) | 2018-10-16 | 2018-10-16 | Question and answer data processing method, device, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109543011A true CN109543011A (en) | 2019-03-29 |
Family
ID=65844994
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811235466.4A Pending CN109543011A (en) | 2018-10-16 | 2018-10-16 | Question and answer data processing method, device, computer equipment and storage medium |
Country Status (3)
Country | Link |
---|---|
CN (1) | CN109543011A (en) |
SG (1) | SG11201913925YA (en) |
WO (1) | WO2020077874A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110134795A (en) * | 2019-04-17 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Generate method, apparatus, computer equipment and the storage medium of validation problem group |
CN110311788A (en) * | 2019-06-28 | 2019-10-08 | 京东数字科技控股有限公司 | Auth method, device, electronic equipment and readable medium |
CN110569347A (en) * | 2019-09-10 | 2019-12-13 | 出门问问信息科技有限公司 | Data processing method and device, storage medium and electronic equipment |
CN110851218A (en) * | 2019-10-23 | 2020-02-28 | 中国建设银行股份有限公司 | Personal interface operation function adding method and device based on personnel relationship |
CN112037029A (en) * | 2020-09-01 | 2020-12-04 | 中国银行股份有限公司 | Automatic generation method and device for bank credit approval problem |
CN112861784A (en) * | 2020-08-19 | 2021-05-28 | 北京猿力未来科技有限公司 | Answering method and device |
CN113822645A (en) * | 2021-09-07 | 2021-12-21 | 广州网才信息技术有限公司 | Interview management system, equipment and computer medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107680019A (en) * | 2017-09-30 | 2018-02-09 | 百度在线网络技术(北京)有限公司 | A kind of implementation method of Examination Scheme, device, equipment and storage medium |
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 |
CN108335193A (en) * | 2018-01-12 | 2018-07-27 | 深圳壹账通智能科技有限公司 | Whole process credit methods, device, equipment and readable storage medium storing program for executing |
CN108647211A (en) * | 2018-05-17 | 2018-10-12 | 宁波薄言信息技术有限公司 | A kind of method for pushing of children for learning content |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8539359B2 (en) * | 2009-02-11 | 2013-09-17 | Jeffrey A. Rapaport | Social network driven indexing system for instantly clustering people with concurrent focus on same topic into on-topic chat rooms and/or for generating on-topic search results tailored to user preferences regarding topic |
CN103593054B (en) * | 2013-11-25 | 2018-04-20 | 北京光年无限科技有限公司 | A kind of combination Emotion identification and the question answering system of output |
CN104299178A (en) * | 2014-07-11 | 2015-01-21 | 北京神州智联科技有限公司 | Facial-recognition-based network teaching method and system |
-
2018
- 2018-10-16 CN CN201811235466.4A patent/CN109543011A/en active Pending
- 2018-12-29 WO PCT/CN2018/125151 patent/WO2020077874A1/en active Application Filing
- 2018-12-29 SG SG11201913925YA patent/SG11201913925YA/en unknown
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107680019A (en) * | 2017-09-30 | 2018-02-09 | 百度在线网络技术(北京)有限公司 | A kind of implementation method of Examination Scheme, device, equipment and storage medium |
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 |
CN108335193A (en) * | 2018-01-12 | 2018-07-27 | 深圳壹账通智能科技有限公司 | Whole process credit methods, device, equipment and readable storage medium storing program for executing |
CN108647211A (en) * | 2018-05-17 | 2018-10-12 | 宁波薄言信息技术有限公司 | A kind of method for pushing of children for learning content |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110134795A (en) * | 2019-04-17 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Generate method, apparatus, computer equipment and the storage medium of validation problem group |
CN110311788A (en) * | 2019-06-28 | 2019-10-08 | 京东数字科技控股有限公司 | Auth method, device, electronic equipment and readable medium |
CN110569347A (en) * | 2019-09-10 | 2019-12-13 | 出门问问信息科技有限公司 | Data processing method and device, storage medium and electronic equipment |
CN110851218A (en) * | 2019-10-23 | 2020-02-28 | 中国建设银行股份有限公司 | Personal interface operation function adding method and device based on personnel relationship |
CN110851218B (en) * | 2019-10-23 | 2023-08-25 | 中国建设银行股份有限公司 | Personnel relationship-based method and device for adding personal interface operation functions |
CN112861784A (en) * | 2020-08-19 | 2021-05-28 | 北京猿力未来科技有限公司 | Answering method and device |
CN112861784B (en) * | 2020-08-19 | 2024-02-20 | 北京猿力未来科技有限公司 | Answering method and device |
CN112037029A (en) * | 2020-09-01 | 2020-12-04 | 中国银行股份有限公司 | Automatic generation method and device for bank credit approval problem |
CN112037029B (en) * | 2020-09-01 | 2024-02-27 | 中国银行股份有限公司 | Automatic generation method and device for bank credit approval problem |
CN113822645A (en) * | 2021-09-07 | 2021-12-21 | 广州网才信息技术有限公司 | Interview management system, equipment and computer medium |
Also Published As
Publication number | Publication date |
---|---|
SG11201913925YA (en) | 2020-05-28 |
WO2020077874A1 (en) | 2020-04-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109543011A (en) | Question and answer data processing method, device, computer equipment and storage medium | |
CN112037791B (en) | Conference summary transcription method, apparatus and storage medium | |
CN109754811A (en) | Sound-source follow-up method, apparatus, equipment and storage medium based on biological characteristic | |
CN109473106A (en) | Vocal print sample collection method, apparatus, computer equipment and storage medium | |
CN110162776A (en) | Interaction message processing method, device, computer equipment and storage medium | |
CN110442697B (en) | Man-machine interaction method, system, computer equipment and storage medium | |
CN108429745A (en) | The authentication method and Verification System of login, webpage login method and system | |
CN110321863A (en) | Age recognition methods and device, storage medium | |
CN110458732A (en) | Training Methodology, device, computer equipment and storage medium | |
CN109783604A (en) | Information extracting method, device and computer equipment based on a small amount of sample | |
CN110177182A (en) | Sensitive data processing method, device, computer equipment and storage medium | |
CN110222780A (en) | Object detecting method, device, equipment and storage medium | |
CN110134795A (en) | Generate method, apparatus, computer equipment and the storage medium of validation problem group | |
CN109859298A (en) | A kind of image processing method and its device, equipment and storage medium | |
CN109886110A (en) | Micro- expression methods of marking, device, computer equipment and storage medium | |
CN109920436A (en) | It is a kind of that the device and method of ancillary service is provided | |
CN109560941A (en) | Minutes method, apparatus, intelligent terminal and storage medium | |
CN109460891A (en) | Data processing method, device and computer equipment based on satisfaction evaluation | |
CN110009480A (en) | The recommended method in judicial collection path, device, medium, electronic equipment | |
CN110134830A (en) | Video information data processing method, device, computer equipment and storage medium | |
CN110047484A (en) | A kind of speech recognition exchange method, system, equipment and storage medium | |
KR20170126667A (en) | Method for generating conference record automatically and apparatus thereof | |
CN109753275A (en) | Recommended method, device, storage medium and the electronic equipment of Application Programming Interface | |
CN113158900A (en) | Training method, device and equipment for human face living body detection model and storage medium | |
CN109785834A (en) | A kind of voice data sample acquisition system and its method based on identifying code |
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 | ||
AD01 | Patent right deemed abandoned | ||
AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20231208 |