CN109767317A - Loan review method, device, equipment and medium based on membership rating - Google Patents
Loan review method, device, equipment and medium based on membership rating Download PDFInfo
- Publication number
- CN109767317A CN109767317A CN201811536534.0A CN201811536534A CN109767317A CN 109767317 A CN109767317 A CN 109767317A CN 201811536534 A CN201811536534 A CN 201811536534A CN 109767317 A CN109767317 A CN 109767317A
- Authority
- CN
- China
- Prior art keywords
- user
- sub
- information
- loan
- membership grade
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012552 review Methods 0.000 title abstract description 6
- 238000011156 evaluation Methods 0.000 claims description 51
- 238000012550 audit Methods 0.000 claims description 49
- 230000001815 facial effect Effects 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 14
- 239000012634 fragment Substances 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 208000019901 Anxiety disease Diseases 0.000 description 7
- 230000036506 anxiety Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000036651 mood Effects 0.000 description 6
- 238000011161 development Methods 0.000 description 3
- 238000009432 framing Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000153 supplemental effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明公开了一种基于会员等级评定的贷款审核方法、装置、设备及介质，在通过用户基本信息确定用户可以成为会员之后进一步通过语音数据和视频数据来确定用户的会员等级，在保证用户进行会员注册效率的同时进一步保证了会员等级分配的准确性和有效性。并且通过对不同用户标识对应的不同会员等级来获取不同的用户基本信息，从而完成贷款的审核，更好地提高了贷款审核的效率。
The invention discloses a loan review method, device, equipment and medium based on membership rating. After determining that the user can become a member through basic user information, the user's membership rating is further determined through voice data and video data. The efficiency of membership registration further ensures the accuracy and effectiveness of membership level assignment. In addition, different basic information of users is obtained through different membership levels corresponding to different user IDs, so as to complete the loan review and better improve the efficiency of loan review.
Description
Technical field
The present invention relates to data processing field more particularly to a kind of loan checking methods based on membership grade evaluation, dress
It sets, equipment and medium.
Background technique
Recently as the fast development of China's economy, the personal credit of China consumer finance credit industry and credit setup
Score evaluation services have obtained high speed and have flourished, and personal credit's industry and individual credit risk evaluation services industry are with huge
Market potential and higher prospective earnings become the hot spot of financial market competition, each financial institution using development consumptive loan as
The important component of development strategy, and the principal risk that bank faces in business process is exactly credit risk.However, at present
The approval process that domestic financial institution provides a loan to personal consumption is relatively complicated, needs to audit the various information of user.
Part financial institution is proposed membership system at present, determines membership grade according to the essential information of user, however, this member etc.
Grade method of determination is evaluated according only to the essential information of user, and data source is more single, and the membership grade thereby determined that lacks
Weary certain accuracy and validity.And the review efficiency of the method for current loan audit is not also high.
Summary of the invention
The embodiment of the present invention provide it is a kind of based on membership grade evaluation loan checking method, device, computer equipment and
Storage medium, to solve the problems, such as that loan review efficiency is not high.
A kind of loan checking method based on membership grade evaluation, comprising:
Membership grade evaluation request is obtained, the membership grade evaluation request includes user identifier and user basic information；
The first preset rules are obtained, is scored according to first preset rules the user basic information, is obtained
Basic score；
If the basic score is more than default scoring threshold value, sends information collection and request to client；
Obtain voice data and video data that client returns；
Additional scoring is obtained according to the voice data and the video data；
The membership grade of the user identifier is obtained according to the basic score and the additional scoring；
Loan audit request is obtained, the loan audit request includes user identifier；
Corresponding membership grade is obtained according to the user identifier；
The corresponding pending nuclear information of the user identifier is obtained according to the membership grade；
The second preset rules are obtained, is scored according to second preset rules the pending nuclear information, is used
Family scoring；
It is scored to obtain loan msu message according to the user.
A kind of loan audit device based on membership grade evaluation, comprising:
Membership grade evaluates request module, and for obtaining membership grade evaluation request, the membership grade evaluation is asked
It asks including user identifier and user basic information；
Basic score obtains module, for obtaining the first preset rules, according to first preset rules to the user
Essential information scores, and obtains basic score；
Information collection request sending module sends information and adopts if being more than default scoring threshold value for the basic score
Collection is requested to client；
Data acquisition module, for obtaining the voice data and video data of client return；
Additional scoring obtains module, for obtaining additional scoring according to the voice data and the video data；
Membership grade determining module, for obtaining the user identifier according to the basic score and the additional scoring
Membership grade；
Loan audit request module, for obtaining loan audit request, the loan audit request includes that user marks
Know；
Membership grade obtains module, for obtaining corresponding membership grade according to the user identifier；
Pending data obtaining module, for obtaining the corresponding pending letter of the user identifier according to the membership grade
Breath；
User, which scores, obtains module, for obtaining the second preset rules, according to second preset rules to described pending
Nuclear information scores, and obtains user's scoring；
Loan msu message determining module obtains loan msu message for scoring according to the user.
A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing
The computer program run on device, the processor realized when executing the computer program it is above-mentioned based on membership grade evaluation
The step of loan checking method.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter
Calculation machine program realizes the step of above-mentioned loan checking method based on membership grade evaluation when being executed by processor.
In the above-mentioned loan checking method based on membership grade evaluation, device, computer equipment and storage medium, obtaining
It to after member's registration request, is scored according to the first preset rules user basic information, obtains user base scoring；If
User base is scored above default scoring threshold value, then sends information collection and request to client；And obtain the use of client return
The voice data and video data at family；The additional scoring of user is obtained according to voice data and video data；According to basic score
The membership grade of user is obtained with additional scoring.After determining that user can become member by user basic information further
The membership grade that user is determined by voice data and video data, it is further while guaranteeing user's member registration efficiency
It ensure that the accuracy and validity of membership grade distribution.And then after getting loan audit request, audited according to loan
User identifier in request obtains corresponding membership grade；The corresponding pending nuclear information of user identifier is obtained according to membership grade；
Msu message is treated according to the second preset rules to score, and obtains user's scoring；It finally scores to obtain to provide a loan according to user and examine
Nuclear information.Different user basic informations is obtained by identifying corresponding different membership grades to different user, to complete
The audit of loan preferably improves the efficiency of loan audit.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the application environment signal of the loan checking method in one embodiment of the invention based on membership grade evaluation
Figure；
Fig. 2 is an exemplary diagram of the loan checking method in one embodiment of the invention based on membership grade evaluation；
Fig. 3 is another exemplary diagram of the loan checking method in one embodiment of the invention based on membership grade evaluation；
Fig. 4 is another exemplary diagram of the loan checking method in one embodiment of the invention based on membership grade evaluation；
Fig. 5 is another exemplary diagram of the loan checking method in one embodiment of the invention based on membership grade evaluation；
Fig. 6 is another exemplary diagram of the loan checking method in one embodiment of the invention based on membership grade evaluation；
Fig. 7 is a functional block diagram of the loan audit device in one embodiment of the invention based on membership grade evaluation；
Fig. 8 is another functional block diagram of the loan audit device in one embodiment of the invention based on membership grade evaluation；
Fig. 9 is a schematic diagram of computer equipment in one embodiment of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Loan checking method provided in an embodiment of the present invention based on membership grade evaluation, can be applicable to the application such as Fig. 1
In environment, wherein client (computer equipment) is communicated by network with server-side.Client asks member's ranking
It asks and is sent to server-side, server-side obtains the first preset rules, it is scored according to the first preset rules user basic information,
Obtain basic score；If user base is scored above default scoring threshold value, sends information collection and request to client；Obtain visitor
The voice data and video data that family end returns；Additional scoring is obtained according to voice data and video data；Finally according to basis
Scoring and additional scoring obtain the membership grade of user.And then after getting loan audit request, asked according to loan audit
User identifier in asking obtains corresponding membership grade；The corresponding pending nuclear information of user identifier is obtained according to membership grade；Root
Msu message is treated according to the second preset rules to score, and obtains user's scoring；It is finally scored to obtain loan audit according to user
Information.Wherein, client (computer equipment) can be, but not limited to various personal computers, laptop, smart phone, put down
Plate computer and portable wearable device.Server-side can use the server of the either multiple server compositions of independent server
Cluster is realized.
In one embodiment, as shown in Fig. 2, a kind of loan checking method based on membership grade evaluation is provided, with the party
Method is illustrated for applying the server-side in Fig. 1, is included the following steps:
S10: membership grade evaluation request is obtained, membership grade evaluation request includes user identifier and user basic information.
Wherein, membership grade evaluation request is that the evaluation for the member subscription proposed to existing customer that client is initiated is asked
It asks.Specifically, user inputs corresponding instruction or information by client to trigger membership grade evaluation request or user
At the scene or sales counter is filed an application, and is requested by contact staff by client sponsor member ranking.Client is by the meeting
Member's ranking request is sent to server-side, and server-side gets membership grade evaluation request.User identifier refers to can be only
One identifies the information of user.In one embodiment, user identifier can be certificate number, user name or user number.User
Number refer to the identiflication number for the distribution of a platform, application program or system user, the corresponding unique member number of a user.
User basic information includes the information relevant with user that the needs that may relate to during membership grade evaluation are audited.It is optional
Ground, user basic information include the identity information of user, assets information, income information, reference information, loan information, hand-held set
At least one of standby information, social account information, third-party platform consumption information or loan application behavioural information etc..
S20: the first preset rules are obtained, is scored according to the first preset rules user basic information, obtains basis
Scoring.
Wherein, the first preset rules are a pre-set standards of grading, which can be according to reality
The needs of loan product are configured, and can also be counted to obtain according to historical data, specifically can according to actual needs and
Setting, details are not described herein.After the configuration for being previously-completed the first preset rules, which is stored in service
In end.It is scored according to the first preset rules user basic information and is scored to get to user base.It is alternatively possible to be
Each single item user basic information sets first preset rules, to obtain more accurate user base scoring.
It illustratively, can be identity information if user basic information includes the identity information and assets information of user
The first different preset rules are respectively set with assets information.For example, if identity information includes gender, occupation, age and body
Situation.It then can be respectively that different genders, occupation, age bracket and physical condition preset different score values, further according to this
The corresponding identity information of user identifier come obtain corresponding score value and be overlapped to get arrive identity information score value.And for
Assets information can then preset different assets sections, and the different corresponding score values in assets section is also different, then basis
The assets information of the user identifier finds corresponding assets section, that is, gets the corresponding score value of assets information.Finally by identity
The corresponding score value of information and assets information are directly or indirectly added one score value and are scored to get to user base.
Ground connection, which is added, among it can be presented as in advance be that differently different weights is arranged in user basic information, and each user is basic
The score value of information is overlapped again later multiplied by corresponding weight.
S30: it if basic score is more than default scoring threshold value, sends information collection and requests to client.
After basic score is calculated, the basic score and default scoring threshold value are compared, if the basis is commented
Point be more than default scoring threshold value, then illustrate that basic score has passed through preliminary audit survey, can with the judgement of further progress membership grade,
Therefore it issues information collection to request to client, to prompt client to carry out corresponding information collection, be requested by information collection
To obtain further information.Preferably, information collection request includes information collection content.The information collection content, which refers to, to be needed
The information further to acquire to client, optionally, the information collection content can be a Duan Yuyin, by client to client
This section of voice is played, and acquires the voice data of client.It is to be appreciated that the information collection content can be for user's base
The lower information of score value carries out supplemental information acquisition in this information.For example, being acquired to the supplement of identity information, to income information
It further determines that or further determining that reference information.
In a specific embodiment, it if user base scoring is not above default scoring threshold value, issues registration and loses
The prompt information lost.It is to be appreciated that illustrating the essential information of user not if basic score is not above default scoring threshold value
It is up to standard, issue the prompt information of registration failure.
S40: voice data and video data that client returns are obtained.
Client acquires the voice data and video data of user by voice capture device and video capture device respectively.
Particularly, video data major embodiment be the facial parts of user in answer to a question video data.
S50: additional scoring is obtained according to voice data and video data.
In this step, the additional scoring of user is obtained by the voice data of acquisition and video data.It specifically, can be with
A speech assessment is obtained according to voice data and video scoring is obtained according to video data, then the two scores are added
Or it is weighted and is added to get the additional scoring of user is arrived.
Specifically, voice data can be carried out to the conversion of text data by speech recognition algorithm.And then according to this turn
Text data after change to carry out speech assessment for the voice data.The voice data can be beaten using specific people
Point, obtain speech assessment.Table is corresponded to it is possible to further preset a speech score, by presetting corresponding key
Word and score value, then the algorithm of string matching is used to carry out string matching for the text data after conversion, after conversion
Text data and speech score correspond to the matching degree of table to obtain speech assessment.And video scoring can carry out video data
Sub-frame processing, and micro- expression information after each framing or motor unit information are obtained to obtain.Optionally, if passing through micro- table
Feelings information obtains, then sets different correspondence score values in advance for each micro- expression information, further according to occurring in the video data
Micro- expression information obtain corresponding score value, and be added, obtain micro- expression scoring.It is to be appreciated that when micro- expression is believed
When breath is tranquil or happy, corresponding score value is higher, when micro- expression information is nervous or anxiety, corresponding score value compared with
It is low.After respectively obtaining speech assessment and the scoring of micro- expression, the two is weighted addition and is commented to get to the additional of user
Point.
S60: the membership grade of user identifier is obtained according to basic score and additional scoring.
Specifically, first basic score is directly or indirectly added with additional scoring and is commented to get the target to user
Point.Wherein, it is added to score and add to score based on being presented as in advance indirectly and different weights is set, by basic score
It scores respectively multiplied by being overlapped again after corresponding weight to get the target for arriving user with additional scoring.Obtaining the user
After the target scoring of mark, scored according to the target to inquire the membership grade that the user identifier can obtain.Optionally, in advance
Different score value sections is first set, and the corresponding membership grade in different score value sections is different.It is to be appreciated that point that numerical value is bigger
It is higher to be worth the corresponding membership grade in section.Therefore, inquire which target scoring belongs to after the target scoring for obtaining user
Score value section, then the corresponding membership grade in score value section is got to get the membership grade of the user identifier is arrived.
S70: loan audit request is obtained, loan audit request includes user identifier.
Wherein, what the loan application proposed to existing customer that loan audit request is initiated for client was audited asks
It asks.Specifically, user inputs corresponding instruction or information by client to trigger loan audit request or user existing
Field or sales counter are filed an application, and are passed through client by contact staff and are initiated loan audit request.Client asks loan audit
It asks and is sent to server-side, server-side gets loan audit request.Loan audit request includes user identifier.
S80: corresponding membership grade is obtained according to user identifier.
Specifically, the corresponding membership grade of the user is obtained according to user identifier.By the database in query service end,
Obtain the corresponding membership grade of the user identifier.
Further, if inquiring membership grade corresponding less than the user identifier in the database, member can be issued
Ranking request, prompts user to register.
S90: the corresponding pending nuclear information of user identifier is obtained according to membership grade.
In this step, the corresponding pending nuclear information of the user identifier is obtained by membership grade.In this motion, no
The pending nuclear information audited with user's needs of membership grade is different.It is to be appreciated that membership grade is higher, need to examine
The pending nuclear information of core is fewer, and membership grade is lower, and the pending nuclear information for needing to audit is more.It specifically, can be preparatory
Different pending nuclear informations is set for different membership grades.In this step, so that it may which the user is obtained according to membership grade
Identify corresponding pending nuclear information.Optionally, pending information includes the identity information, assets information, income information, sign of user
Letter information, loan information, handheld device information, social account information, third-party platform consumption information or loan application behavior letter
At least one of breath etc..
S100: the second preset rules are obtained, msu message is treated according to the second preset rules and scores, obtain user and comment
Point.
Wherein, the second preset rules are a pre-set standards of grading, which can be according to reality
The needs of loan product are configured, and can also be counted to obtain according to historical data, specifically can be according to practical Xu Ershe
Fixed, details are not described herein.After the configuration for being previously-completed the second preset rules, which is stored in server-side
In.Pending nuclear information is scored by second preset rules and is scored to get to user.It is alternatively possible to be each single item
One the second preset rules of pending information setting, to obtain more accurate user's scoring.The step specifically can and step
S12 is identical, and details are not described herein.
S110: it is scored to obtain loan msu message according to user.
Wherein, loan msu message is a feedback information to loan audit request, which embodies
The auditing result of loan audit request.Loan msu message includes passing through and not passing through.Specifically, according to user's scoring come
Obtain different loan msu messages.Corresponding score value section is set for different loan msu messages in advance, judgement should later
Which section user base scoring falls within to get to corresponding msu message.
Illustratively, using the standards of grading of hundred-mark system, for by with do not pass through respectively arranged score value section are as follows: [85,
100] and [0,85).At this point, corresponding loan msu message is to pass through if user's scoring is 90；If user's scoring is 75,
Corresponding loan msu message is not pass through.
In this embodiment, after getting member registration request, according to the first preset rules to user's base
This information scores, and obtains user base scoring；If user base is scored above default scoring threshold value, information collection is sent
It requests to client；And obtain the voice data and video data of the user of client return；According to voice data and video counts
According to the additional scoring for obtaining user；The membership grade of user is obtained according to basic score and additional scoring.Basic by user
Information determines that user can become the membership grade that member further determines user by voice data and video data later,
The accuracy and validity of membership grade distribution are further ensured while guaranteeing user's member registration efficiency.And then it is obtaining
After getting loan audit request, corresponding membership grade is obtained according to the user identifier in loan audit request；According to member
Grade obtains the corresponding pending nuclear information of user identifier；Msu message is treated according to the second preset rules to score, and is used
Family scoring；It is finally scored to obtain loan msu message according to user.By identifying corresponding different membership grades to different user
Different user basic informations is obtained, to complete the audit of loan, preferably improves the efficiency of loan audit.
In one embodiment, as shown in figure 3, obtaining additional scoring according to voice data and video data, specifically include as
Lower step:
S51: micro- expression information of user is obtained in video data.
Wherein, micro- expression information refers to micro- expression that correspondence image is embodied.It in this step, can be by presetting one
Time interval carrys out micro- expression information of timing acquisition video data septum reset part.Specifically, it can be set in video data
At predetermined time intervals obtain video data septum reset part micro- expression information.Illustratively, the predetermined time be 3s, 5s,
8s or 10s.
Specifically, the acquisition of corresponding facial image, and the people that will acquire are carried out to video data according to the predetermined time
Face image is input in the micro- Expression Recognition model pre-set and is identified, obtains micro- expression information.Specifically, micro- table
Feelings information can be tranquil, happy, nervous or anxiety etc..
S52: additional scoring is obtained according to voice data and micro- expression information.
In this step, the additional scoring of user is obtained according to voice data and micro- expression information.It is alternatively possible to respectively
It obtains a speech assessment according to voice data and micro- expression is obtained according to micro- expression information and score, then the two scores are carried out
It is added or weighting summation is to get the additional scoring for arriving user.
Specifically, voice data can be carried out to the conversion of text data by speech recognition algorithm.And then according to this turn
Text data after change to carry out speech assessment for the voice data.The voice data can be beaten using specific people
Point, obtain speech assessment.Table is corresponded to it is possible to further preset a speech score, by presetting corresponding key
Word and score value, then the algorithm of string matching is used to carry out string matching for the text data after conversion, after conversion
Text data and speech score correspond to the matching degree of table to obtain speech assessment.And micro- expression scoring can be believed by micro- expression
Breath sets different correspondence score values, further according to the micro- table occurred in the video data to obtain for each micro- expression information in advance
Feelings information obtains corresponding score value, and is added, and micro- expression scoring is obtained.It is to be appreciated that when micro- expression information is flat
When quiet or happy, corresponding score value is higher, and when micro- expression information is nervous or anxiety, corresponding score value is lower.Dividing
After not obtaining speech assessment and the scoring of micro- expression, the two is weighted and is added to get the additional scoring of user is arrived.
In this embodiment, micro- expression information of user is obtained in video data, and according to voice data and micro- table
The additional scoring of feelings acquisition of information user ensure that the accuracy that the additional scoring of user obtains.
In one embodiment, it as shown in figure 4, obtaining micro- expression information of user in video data, specifically includes as follows
Step:
S511: carrying out sub-frame processing to video data according to the first preset interval, obtain N facial image to be identified,
In, N is positive integer.
Wherein, which can be thought as a time value or represent the numerical value of frame number.According to setting
The first preset interval to video data carry out sub-frame processing, obtain N facial image to be identified, wherein N is positive integer.
Optionally, server-side can obtain facial image to be identified by way of screenshotss from video data.Specifically,
Can realize the process for obtaining facial image to be identified by OpenCV, OpenCV provide a simple and easy-to-use frame with
Extract the picture frame in video file.Illustratively, the operation that video reads and writees is carried out using VideoCapture class.
Corresponding video data is shown using cap=cv2.VideoCapture () function in VideoCapture class first, then is led to
Cap.read () function in VideoCapture class is crossed by preset frame per second reading video data, cap.read () function
There are two return values: ret and frame.Wherein, ret is Boolean, True is returned to if reading frame is correctly, if should
Video data has read ending, its return value is just False, it can passes through the return value of cap.read () function
It is finished to judge whether the video data reads.Frame is exactly current truncated picture, can be a three-dimensional matrice.It can
To understand ground, client directly can also carry out intercept operation to video data, obtain wait know after getting video data
Others' face image, i.e., the above-mentioned process that facial image to be identified is obtained from video data can also be realized by client.Visitor
Family end sends server-side for facial image to be identified again, and server-side directly gets facial image to be identified from client.
S512: N facial image to be identified being input in micro- Expression Recognition model and is identified, is obtained each to be identified
Micro- expression information of facial image.
Micro- Expression Recognition model is the identification model for judging face mood in input picture, micro- Expression Recognition model
It may determine that probability value of the face corresponding to preset a variety of moods in input picture, if the probability value of certain mood is more than to correspond to
Preset threshold, then obtaining the corresponding mood of the input picture is Emotion identification result.It, can be with for example, in the present embodiment
Mood in micro- Expression Recognition model is set as tranquil, happy, nervous and 4 kinds of anxiety.Specifically, difference can be acquired in advance
The great amount of samples image for representing this 4 kinds of moods is labeled, and is formed sample graph image set, is then selected corresponding neural network model
Or classifier is trained, and finally obtains micro- Expression Recognition model.
In this step, N obtained facial image to be identified is input in micro- Expression Recognition model and is identified, i.e.,
Obtain micro- expression information of each facial image to be identified.
In the present embodiment, sub-frame processing is carried out to video data by preset interval, obtains N face figure to be identified
Picture, and N facial image to be identified is input in micro- Expression Recognition model and is identified, obtain each facial image to be identified
Micro- expression information.It ensure that the accuracy that micro- expression information of video data obtains with this.
In one embodiment, voice data includes M sub- voice data sections, wherein M is positive integer.
Wherein, sub- voice data section is the message segment distinguished according to different problems or information point.Such as: voice data
In include user to the supplement acquisition of identity information, to income information further determine that or it is to reference information further
Voice data, then can be divided into 3 sub- voice data sections by the voice data such as determining.Each sub- voice data section represents difference
Information point.Further, it can also further be segmented according to difference problem further in each information point,
It is not specifically limited herein.Specifically, can when acquiring voice data according to each asked questions or guidance voice come
The division of sub- voice data section is carried out to collected voice data.
In the present embodiment, it as shown in figure 5, obtaining micro- expression information of user in video data, specifically includes as follows
Step:
S511 ': it is segmented according to the when ordered pair video data of M sub- voice data sections, obtains M sub-video data
Section.
It is to be appreciated that voice data and video data acquire simultaneously, therefore the period of the two is corresponding.Cause
This, first gets in M sub- voice data sections each sub- voice data section corresponding period, further according to the period to video counts
According to being segmented, M sub- video-data fragments are obtained.It is to be appreciated that sub- voice data section each at this time all has corresponding son
Video-data fragment.
S512 ': sub-frame processing is carried out to each sub-video data section according to the second preset interval, obtains each sub-video number
According to K facial image to be identified of section, wherein K is positive integer.
Wherein, which can be thought as a time value or represent the numerical value of frame number.According to setting
The second preset interval to video data carry out sub-frame processing, obtain K facial image to be identified of each sub-video data section,
Wherein, K is positive integer.The specific sub-frame processing mode can be similar with step S511, and which is not described herein again.
S513 ': K facial image to be identified of each sub-video data section is input in micro- Expression Recognition model and is carried out
Identification, obtains micro- expression information of each sub-video data section.
In this step, K facial image to be identified of obtained each sub-video data section micro- expression is input to know
It is identified in other model to get micro- expression information of each sub-video data section is arrived.Specific micro- Expression Recognition model can be with
Identical with step S512, which is not described herein again.
In this embodiment, first video data is segmented according to the period of M sub- voice data sections, obtains M
Sub-video data section.Sub-frame processing is carried out to each sub-video data section according to the second preset interval, obtains each sub-video number
According to K facial image to be identified of section, wherein K is positive integer；Finally by K face to be identified of each sub-video data section
Image is input in micro- Expression Recognition model and is identified, obtains micro- expression information of each sub-video data section.By voice number
It is associated according to video data, guarantees the accuracy that subsequent score value calculates.
In one embodiment, it as shown in fig. 6, obtaining additional scoring according to voice data and micro- expression information, specifically includes
Following steps:
S521: the speech score of each sub- voice data section is obtained.
Specifically, each sub- voice data section is carried out to the conversion of text data by speech recognition algorithm.And then basis
Text data after the conversion to carry out speech assessment for each sub- voice data section, obtains speech score.It is alternatively possible to adopt
It is given a mark with specific people to the voice data, obtains speech score.It is possible to further preset a speech score pair
Table is answered, by presetting corresponding keyword and score value, then uses the algorithm of string matching for the text data after conversion
Carry out string matching, according to after conversion text data and speech score correspond to the matching degree of table and obtain each sub- voice
The speech score of data segment.
S522: the power of corresponding each sub- voice data section is calculated according to micro- expression information of each sub-video data section
Value.
Each sub-video data section all includes micro- expression information, it is possible to understand that ground, micro- expression information are at least one.
By counting the quantity of different micro- expression informations in each sub-video data section, corresponding each sub- voice data section is set
Weight.Wherein, corresponding sub- voice data section refers to the correspondence for the period embodied in step S511 '.It specifically, can be according to every
One sub-video data Duan Zhongwei expression information is nervous or anxiety ratio corresponding weight is arranged, and micro- expression information is tight
It opens or the ratio of anxiety is higher, the weight is lower, and micro- expression information is that tranquil or happy ratio is higher, the weight
It is higher.It further, is more than certain threshold value when a sub-video data Duan Zhongwei expression information is nervous or anxiety ratio,
It is 0 that corresponding weight, which is then arranged,.Optionally, which is 75%, 80% or 85%.
S523: according to the additional scoring of the speech score of each sub- voice data section and weight computing user.
After the speech score and weight for obtaining each sub- voice data section, the additional scoring of user is calculated.Specifically,
The additional scoring of user can be calculated by the following formula:
Wherein, S is the additional scoring of user, AiFor the speech score of the i-th cross-talk voice data section, QiFor the i-th cross-talk voice
The corresponding weight of data segment, n are the quantity of sub- voice data section.
In this embodiment, the speech score for first obtaining each sub- voice data section, further according to each sub-video data
Micro- expression information of section calculates the weight of corresponding each sub- voice data section, finally according to the voice of each sub- voice data section
The additional scoring of score value and weight computing user.By the way that sub- voice data section and corresponding sub-video data section are associated,
And the setting of weight is carried out to speech score using corresponding micro- expression information, the additional scoring for further ensuring user calculates
Accuracy.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
In one embodiment, a kind of loan audit device based on membership grade evaluation is provided, should be commented based on membership grade
Loan checking method based on membership grade evaluation in fixed loan audit device and above-described embodiment corresponds.Such as Fig. 7 institute
Show, should include that membership grade evaluates request module 10, basic score obtains based on the loan audit device that membership grade is evaluated
Modulus block 20, information collection request sending module 30, data acquisition module 40, additional scoring acquisition module 50, membership grade are true
Cover half block 60, loan audit request module 70, membership grade obtain module 80, pending data obtaining module 90, user
Scoring obtains module 100 and loan msu message determining module 110.Detailed description are as follows for each functional module:
Membership grade evaluates request module 10, for obtaining membership grade evaluation request, membership grade evaluation request
Including user identifier and user basic information；
Basic score obtains module 20, for obtaining the first preset rules, is believed substantially according to the first preset rules user
Breath scores, and obtains basic score；
Information collection request sending module 30 sends information collection if being more than default scoring threshold value for basic score
It requests to client；
Data acquisition module 40, for obtaining the voice data and video data of client return；
Additional scoring obtains module 50, for obtaining additional scoring according to voice data and video data；
Membership grade determining module 60, for obtaining the membership grade of user identifier according to basic score and additional scoring；
Loan audit request module 70, for obtaining loan audit request, loan audit request includes user identifier；
Membership grade obtains module 80, for obtaining corresponding membership grade according to user identifier；
Pending data obtaining module 90, for obtaining the corresponding pending nuclear information of user identifier according to membership grade；
User, which scores, obtains module 100, for obtaining the second preset rules, treats msu message according to the second preset rules
It scores, obtains user's scoring；
Loan msu message determining module 110 obtains loan msu message for scoring according to user.
Preferably, as shown in figure 8, it includes micro- expression information acquiring unit 51 and additional scoring that additional scoring, which obtains module 50,
Acquiring unit 52.
Micro- expression information acquiring unit 51, for obtaining micro- expression information of user in video data；
Additional scoring acquiring unit 52, for obtaining additional scoring according to voice data and micro- expression information.
Preferably, micro- expression information acquiring unit 51 is used to carry out at framing video data according to the first preset interval
Reason, obtains N facial image to be identified, wherein N is positive integer；N facial image to be identified is input to micro- Expression Recognition mould
It is identified in type, obtains micro- expression information of each facial image to be identified.
Preferably, voice data includes M sub- voice data sections, wherein M is positive integer.Micro- expression information acquiring unit
51, for being segmented according to the when ordered pair video data of M sub- voice data sections, obtain M sub- video-data fragments；According to
Two preset intervals carry out sub-frame processing to each sub-video data section, obtain K face to be identified of each sub-video data section
Image, wherein K is positive integer；K facial image to be identified of each sub-video data section is input to micro- Expression Recognition model
In identified, obtain micro- expression information of each sub-video data section.
Preferably, the speech score that scoring acquiring unit 52 is used to obtain each sub- voice data section is added；According to each
Micro- expression information of sub-video data section calculates the weight of corresponding each sub- voice data section；According to each sub- voice data section
Speech score and weight computing user additional scoring.
Specific restriction about the loan audit device evaluated based on membership grade may refer to above for member etc.
The restriction of grade assessment method, details are not described herein.Modules in the above-mentioned loan audit device based on membership grade evaluation
It can be realized fully or partially through software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware or independently of
In processor in computer equipment, it can also be stored in a software form in the memory in computer equipment, in order to locate
It manages device and calls the corresponding operation of the above modules of execution.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 9.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 used to store the data arrived used in the above-mentioned loan checking method based on membership grade evaluation.The meter
The network interface for calculating machine equipment is used to communicate with external terminal by network connection.When the computer program is executed by processor
To realize a kind of loan checking method based on membership grade evaluation.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor are realized in above-described embodiment when executing computer program based on member
The step of loan checking method of ranking.
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 loan checking method based on membership grade evaluation in above-described 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..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of loan checking method based on membership grade evaluation characterized by comprising
Membership grade evaluation request is obtained, the membership grade evaluation request includes user identifier and user basic information；
The first preset rules are obtained, is scored according to first preset rules the user basic information, obtains basis
Scoring；
If the basic score is more than default scoring threshold value, sends information collection and request to client；
Obtain voice data and video data that client returns；
Additional scoring is obtained according to the voice data and the video data；
The membership grade of the user identifier is obtained according to the basic score and the additional scoring；
Loan audit request is obtained, the loan audit request includes user identifier；
Corresponding membership grade is obtained according to the user identifier；
The corresponding pending nuclear information of the user identifier is obtained according to the membership grade；
The second preset rules are obtained, is scored according to second preset rules the pending nuclear information, is obtained user and comment
Point；
It is scored to obtain loan msu message according to the user.
2. the loan checking method as described in claim 1 based on membership grade evaluation, which is characterized in that described according to
Voice data and the video data obtain additional scoring, specifically comprise the following steps:
Micro- expression information of user is obtained in the video data；
Additional scoring is obtained according to the voice data and micro- expression information.
3. the loan checking method as claimed in claim 2 based on membership grade evaluation, which is characterized in that described in the view
Frequency obtains micro- expression information of user in, specifically comprises the following steps:
Sub-frame processing is carried out to the video data according to the first preset interval, obtains N facial image to be identified, wherein N is
Positive integer；
Facial image to be identified described in N width is input in micro- Expression Recognition model and is identified, is obtained each described to be identified
Micro- expression information of facial image.
4. the loan checking method as claimed in claim 2 based on membership grade evaluation, which is characterized in that the voice data
Including M sub- voice data sections, wherein M is positive integer；
Micro- expression information that user is obtained in the video data, specifically comprises the following steps:
According to the M sub- voice data section when ordered pair described in video data be segmented, obtain M sub- video-data fragments；
Sub-frame processing is carried out to each sub-video data section according to the second preset interval, obtains each sub-video data
K facial image to be identified of section, wherein K is positive integer；
K facial image to be identified of each sub-video data section is input in micro- Expression Recognition model and is identified,
Obtain micro- expression information of each sub-video data section.
5. the loan checking method as claimed in claim 4 based on membership grade evaluation, which is characterized in that described according to
Voice data and micro- expression information obtain additional scoring, specifically comprise the following steps:
Obtain the speech score of each sub- voice data section；
The weight of corresponding each sub- voice data section is calculated according to micro- expression information of each sub-video data section；
According to the additional scoring of the speech score of each sub- voice data section and weight computing user.
6. a kind of loan based on membership grade evaluation audits device characterized by comprising
Membership grade evaluates request module, and for obtaining membership grade evaluation request, the membership grade evaluates request packet
Include user identifier and user basic information；
Basic score obtains module, basic to the user according to first preset rules for obtaining the first preset rules
Information scores, and obtains basic score；
Information collection request sending module sends information collection and asks if being more than default scoring threshold value for the basic score
It asks to client；
Data acquisition module, for obtaining the voice data and video data of client return；
Additional scoring obtains module, for obtaining additional scoring according to the voice data and the video data；
Membership grade determining module, for obtaining the member of the user identifier according to the basic score and the additional scoring
Grade；
Loan audit request module, for obtaining loan audit request, the loan audit request includes user identifier；
Membership grade obtains module, for obtaining corresponding membership grade according to the user identifier；
Pending data obtaining module, for obtaining the corresponding pending nuclear information of the user identifier according to the membership grade；
User, which scores, obtains module, for obtaining the second preset rules, according to second preset rules to the pending letter
Breath scores, and obtains user's scoring；
Loan msu message determining module obtains loan msu message for scoring according to the user.
7. the loan as claimed in claim 6 based on membership grade evaluation audits device, which is characterized in that additional scoring obtains
Module includes:
Micro- expression information acquiring unit, for obtaining micro- expression information of user in the video data；
Additional scoring acquiring unit, for obtaining additional scoring according to the voice data and micro- expression information.
8. the loan as claimed in claim 7 based on membership grade evaluation audits device, which is characterized in that the voice data
Including M sub- voice data sections, wherein M is positive integer；
Micro- expression information acquiring unit is used to be segmented according to the when ordered pair video data of M sub- voice data sections, obtains
To M sub- video-data fragments；Sub-frame processing is carried out to each sub-video data section according to the second preset interval, obtains each sub- view
The facial image to be identified of K of frequency data segment, wherein K is positive integer；By K face to be identified of each sub-video data section
Image is input in micro- Expression Recognition model and is identified, obtains micro- expression information of each sub-video data section.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
The step of 5 described in any item loan checking methods based on membership grade evaluation.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In realization is evaluated as described in any one of claim 1 to 5 based on membership grade when the computer program is executed by processor
Loan checking method the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811536534.0A CN109767317A (en) | 2018-12-15 | 2018-12-15 | Loan review method, device, equipment and medium based on membership rating |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811536534.0A CN109767317A (en) | 2018-12-15 | 2018-12-15 | Loan review method, device, equipment and medium based on membership rating |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109767317A true CN109767317A (en) | 2019-05-17 |
Family
ID=66450695
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811536534.0A Pending CN109767317A (en) | 2018-12-15 | 2018-12-15 | Loan review method, device, equipment and medium based on membership rating |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109767317A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114648344A (en) * | 2022-03-18 | 2022-06-21 | 中国建设银行股份有限公司 | Member registration method and device |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20040076152A (en) * | 2003-02-24 | 2004-08-31 | 조승호 | On-line loaning relay system using image communication and method thereof, and media that can record computer program sources for method thereof |
| KR20090030457A (en) * | 2007-09-20 | 2009-03-25 | 주식회사 트리플리치매니지먼트 | Loan product management system based on online network |
| CN102693508A (en) * | 2012-05-11 | 2012-09-26 | 杭州商友全球网信息技术有限公司 | Data processing method for bank loan application management |
| CN104715415A (en) * | 2013-12-13 | 2015-06-17 | 徐国良 | Loan Matching Platform System |
| WO2015106611A1 (en) * | 2014-01-16 | 2015-07-23 | 汉唐光电科技股份有限公司 | Loan marching platform system |
| US20150278941A1 (en) * | 2014-03-26 | 2015-10-01 | Wonga Technology Limited | Loan automation system |
| CN106960387A (en) * | 2017-04-28 | 2017-07-18 | 浙江工商大学 | Individual credit risk appraisal procedure and system |
| TWM547140U (en) * | 2016-11-17 | 2017-08-11 | 徐國良 | Apparatus for auditing loan platform members using data |
| CN107392451A (en) * | 2017-07-11 | 2017-11-24 | 重庆卡西匚匚科技有限公司 | A kind of risk control system |
| CN107437223A (en) * | 2017-08-17 | 2017-12-05 | 重庆小雨点小额贷款有限公司 | Credit information checking method, device and equipment |
| US20180005272A1 (en) * | 2016-06-30 | 2018-01-04 | Paypal, Inc. | Image data detection for micro-expression analysis and targeted data services |
| CN107704834A (en) * | 2017-10-13 | 2018-02-16 | 上海壹账通金融科技有限公司 | Householder method, device and storage medium are examined in micro- expression face |
| CN107862598A (en) * | 2017-09-30 | 2018-03-30 | 平安普惠企业管理有限公司 | Long-range the interview measures and procedures for the examination and approval, server and readable storage medium storing program for executing |
| CN107919137A (en) * | 2017-10-25 | 2018-04-17 | 平安普惠企业管理有限公司 | The long-range measures and procedures for the examination and approval, device, equipment and readable storage medium storing program for executing |
| 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 |
| CN108537160A (en) * | 2018-03-30 | 2018-09-14 | 平安科技（深圳）有限公司 | Risk Identification Method, device, equipment based on micro- expression and medium |
| CN108596760A (en) * | 2018-05-14 | 2018-09-28 | 平安普惠企业管理有限公司 | loan risk evaluation method and server |
| CN108765131A (en) * | 2018-05-18 | 2018-11-06 | 深圳壹账通智能科技有限公司 | Credit authorization method, apparatus, terminal and readable storage medium storing program for executing based on micro- expression |
| CN108961031A (en) * | 2017-05-24 | 2018-12-07 | 腾讯科技（深圳）有限公司 | Realize information processing method, device and the computer readable storage medium of loan examination & approval |
| CN109472690A (en) * | 2018-10-25 | 2019-03-15 | 深圳壹账通智能科技有限公司 | The loan measures and procedures for the examination and approval, device, storage medium and electronic equipment based on block chain |
| CN109829358A (en) * | 2018-12-14 | 2019-05-31 | 深圳壹账通智能科技有限公司 | Micro- expression loan control method, device, computer equipment and storage medium |
| CN109949152A (en) * | 2019-04-15 | 2019-06-28 | 武汉理工大学 | A Personal Credit Default Prediction Method |
-
2018
- 2018-12-15 CN CN201811536534.0A patent/CN109767317A/en active Pending
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20040076152A (en) * | 2003-02-24 | 2004-08-31 | 조승호 | On-line loaning relay system using image communication and method thereof, and media that can record computer program sources for method thereof |
| KR20090030457A (en) * | 2007-09-20 | 2009-03-25 | 주식회사 트리플리치매니지먼트 | Loan product management system based on online network |
| CN102693508A (en) * | 2012-05-11 | 2012-09-26 | 杭州商友全球网信息技术有限公司 | Data processing method for bank loan application management |
| CN104715415A (en) * | 2013-12-13 | 2015-06-17 | 徐国良 | Loan Matching Platform System |
| WO2015106611A1 (en) * | 2014-01-16 | 2015-07-23 | 汉唐光电科技股份有限公司 | Loan marching platform system |
| US20150278941A1 (en) * | 2014-03-26 | 2015-10-01 | Wonga Technology Limited | Loan automation system |
| US20180005272A1 (en) * | 2016-06-30 | 2018-01-04 | Paypal, Inc. | Image data detection for micro-expression analysis and targeted data services |
| TWM547140U (en) * | 2016-11-17 | 2017-08-11 | 徐國良 | Apparatus for auditing loan platform members using data |
| CN106960387A (en) * | 2017-04-28 | 2017-07-18 | 浙江工商大学 | Individual credit risk appraisal procedure and system |
| CN108961031A (en) * | 2017-05-24 | 2018-12-07 | 腾讯科技（深圳）有限公司 | Realize information processing method, device and the computer readable storage medium of loan examination & approval |
| CN107392451A (en) * | 2017-07-11 | 2017-11-24 | 重庆卡西匚匚科技有限公司 | A kind of risk control system |
| CN107437223A (en) * | 2017-08-17 | 2017-12-05 | 重庆小雨点小额贷款有限公司 | Credit information checking method, device and equipment |
| CN107862598A (en) * | 2017-09-30 | 2018-03-30 | 平安普惠企业管理有限公司 | Long-range the interview measures and procedures for the examination and approval, server and readable storage medium storing program for executing |
| CN107704834A (en) * | 2017-10-13 | 2018-02-16 | 上海壹账通金融科技有限公司 | Householder method, device and storage medium are examined in micro- expression face |
| CN107919137A (en) * | 2017-10-25 | 2018-04-17 | 平安普惠企业管理有限公司 | The long-range measures and procedures for the examination and approval, device, equipment and readable storage medium storing program for executing |
| 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 |
| CN108537160A (en) * | 2018-03-30 | 2018-09-14 | 平安科技（深圳）有限公司 | Risk Identification Method, device, equipment based on micro- expression and medium |
| CN108596760A (en) * | 2018-05-14 | 2018-09-28 | 平安普惠企业管理有限公司 | loan risk evaluation method and server |
| CN108765131A (en) * | 2018-05-18 | 2018-11-06 | 深圳壹账通智能科技有限公司 | Credit authorization method, apparatus, terminal and readable storage medium storing program for executing based on micro- expression |
| CN109472690A (en) * | 2018-10-25 | 2019-03-15 | 深圳壹账通智能科技有限公司 | The loan measures and procedures for the examination and approval, device, storage medium and electronic equipment based on block chain |
| CN109829358A (en) * | 2018-12-14 | 2019-05-31 | 深圳壹账通智能科技有限公司 | Micro- expression loan control method, device, computer equipment and storage medium |
| CN109949152A (en) * | 2019-04-15 | 2019-06-28 | 武汉理工大学 | A Personal Credit Default Prediction Method |
Non-Patent Citations (3)
| Title |
|---|
| ADEL LABLACK ET AL.: "A Local Approach for Negative Emotion Detection", 《2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION》, 31 December 2014 (2014-12-31), pages 417 - 420 * |
| 洪旭: "网络借贷中贷款人 个人信息对借贷的影响 研究——基于拍拍贷平 台的实证分析", 《中国优秀硕士学位论文全 文数据库 经济与管理科学 辑》, vol. 2018, no. 07, 15 July 2018 (2018-07-15), pages 162 - 15 * |
| 韩修龙;: "基于XGBOOST的用户信用评分建模", 电脑知识与技术, no. 05, 12 March 2018 (2018-03-12) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114648344A (en) * | 2022-03-18 | 2022-06-21 | 中国建设银行股份有限公司 | Member registration method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109509087A (en) | Intelligentized loan checking method, device, equipment and medium | |
| CN107704834A (en) | Householder method, device and storage medium are examined in micro- expression face | |
| Giachetti et al. | Detecting the relationship between competitive intensity and firm product line length: Evidence from the worldwide mobile phone industry | |
| CN110020091B (en) | Medical search engine system based on block chain | |
| CN109461073A (en) | Risk management method, device, computer equipment and the storage medium of intelligent recognition | |
| CN112199575A (en) | Virtual bank account opening method, device, equipment and computer storage medium | |
| CN109345375A (en) | A kind of suspicious money laundering Activity recognition method and device | |
| CN109063977A (en) | A kind of no-induction transaction risk monitoring method and device | |
| CN109697666A (en) | Method for prewarning risk, device, computer equipment and storage medium | |
| CN109543442A (en) | Data safety processing method, device, computer equipment and storage medium | |
| CN109509088A (en) | Loan checking method, device, equipment and medium based on micro- Expression Recognition | |
| WO2024060951A1 (en) | Servicing method and apparatus for services | |
| CN109766772A (en) | Risk control method, device, computer equipment and storage medium | |
| CN112634017A (en) | Remote card opening activation method and device, electronic equipment and computer storage medium | |
| CN109785114A (en) | Credit data methods of exhibiting, device, equipment and medium for audit of providing a loan | |
| Arapakis et al. | A comparison of general vs personalised affective models for the prediction of topical relevance | |
| CN107392614A (en) | The implementation method and device of off-line transaction | |
| CN109858735A (en) | Consumer's risk scoring assessment method, device, computer equipment and storage medium | |
| CN107808297A (en) | Multi-medium data put-on method and device | |
| CN114219664B (en) | Product recommendation method, device, computer equipment and storage medium | |
| CN114037460B (en) | Comprehensive anti-fraud platform, method and storage medium | |
| CN109767317A (en) | Loan review method, device, equipment and medium based on membership rating | |
| EP4313330A1 (en) | Field rating and course adjusted strokes gained for global golf analysis | |
| CN113256368B (en) | Product push method, device, computer equipment and storage medium | |
| WO2023040155A1 (en) | Preset label-based policy generation method and apparatus, and storage medium |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190517 |