CN110443692B - Enterprise credit auditing method, device, equipment and computer readable storage medium - Google Patents
Enterprise credit auditing method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN110443692B CN110443692B CN201910600404.7A CN201910600404A CN110443692B CN 110443692 B CN110443692 B CN 110443692B CN 201910600404 A CN201910600404 A CN 201910600404A CN 110443692 B CN110443692 B CN 110443692B
- Authority
- CN
- China
- Prior art keywords
- enterprise
- multidimensional
- image data
- risk prediction
- target
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000007637 random forest analysis Methods 0.000 claims abstract description 110
- 230000008451 emotion Effects 0.000 claims abstract description 76
- 238000012795 verification Methods 0.000 claims abstract description 38
- 230000008909 emotion recognition Effects 0.000 claims abstract description 29
- 239000011159 matrix material Substances 0.000 claims description 37
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012550 audit Methods 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 7
- 238000000926 separation method Methods 0.000 claims description 7
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000012549 training Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 230000004397 blinking Effects 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Finance (AREA)
- Computational Linguistics (AREA)
- Accounting & Taxation (AREA)
- Biomedical Technology (AREA)
- Hospice & Palliative Care (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Psychiatry (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Child & Adolescent Psychology (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides an enterprise credit auditing method, device, equipment and computer readable storage medium, wherein the method comprises the following steps: when an enterprise credit auditing request is monitored, acquiring a credit auditing video of a target enterprise and enterprise multidimensional image data according to the enterprise credit auditing request; performing micro-expression recognition and voice emotion recognition on the credit auditing video to obtain a micro-expression type set and a voice emotion type; verifying the enterprise multidimensional image data according to the microexpressive type set and the voice emotion type; when the enterprise multidimensional image data passes the verification, analyzing the enterprise multidimensional image data through a plurality of random forests of each layer in a preset random forest model to obtain a multidimensional risk prediction result; and judging whether the target enterprise passes loan auditing according to the multidimensional risk prediction result. The application relates to data analysis and microexpressive recognition, which can improve the accuracy of loan auditing.
Description
Technical Field
The present application relates to the field of data analysis technologies, and in particular, to an enterprise credit auditing method, apparatus, device, and computer readable storage medium.
Background
The enterprise credit loan is a mortgage-free and guarantee-free loan which is issued by a bank to legal representatives or shareholders of small enterprises and is used for supplementing legal appointed purposes such as enterprise liquidity funds turnover. When an enterprise applies for credit to a bank, the enterprise related data such as an enterprise marketing license, a tax registration certificate, an organization code certificate, a value added tax of six months and the like are required to be provided, and then the bank is used for auditing to determine the loan amount of the enterprise applying for the credit.
At present, features can be extracted from enterprise related data and auditing is performed on loan application based on the features, however, the existing feature extraction algorithm only involves simple linear calculation, hidden information after space distortion cannot be extracted, the loan is audited only through the extracted linear features, and the accuracy of the auditing result of the enterprise credit loan cannot be ensured. Therefore, how to improve the auditing accuracy of the credit loan of the enterprise is a problem to be solved at present.
Disclosure of Invention
The application mainly aims to provide an enterprise credit auditing method, device, equipment and computer readable storage medium, aiming at improving auditing accuracy of enterprise credit loan.
In a first aspect, the present application provides an enterprise credit auditing method, comprising the steps of:
When an enterprise credit auditing request is monitored, acquiring a credit auditing video of a target enterprise and enterprise multidimensional image data according to the enterprise credit auditing request;
performing micro-expression recognition and voice emotion recognition on the credit auditing video to obtain a micro-expression type set and a voice emotion type;
Verifying the enterprise multidimensional image data according to the microexpressive type set and the voice emotion type;
when the enterprise multidimensional image data passes the verification, analyzing the enterprise multidimensional image data through a plurality of random forests of each layer in a preset random forest model to obtain a multidimensional risk prediction result;
and judging whether the target enterprise passes loan auditing according to the multidimensional risk prediction result.
In a second aspect, the present application also provides an enterprise credit auditing apparatus, the enterprise credit auditing apparatus comprising:
The acquisition module is used for acquiring a credit auditing video and enterprise multidimensional image data of a target enterprise according to the enterprise credit auditing request when the enterprise credit auditing request is monitored;
The recognition module is used for carrying out micro-expression recognition and voice emotion recognition on the credit auditing video to obtain a micro-expression type set and a voice emotion type;
The verification module is used for verifying the enterprise multidimensional image data according to the microexpressive type set and the voice emotion type;
The analysis module is used for analyzing the enterprise multidimensional image data through a plurality of random forests of each layer in a preset random forest model when the enterprise multidimensional image data passes the verification, so as to obtain a multidimensional risk prediction result;
And the judging module is used for judging whether the target enterprise passes loan audit or not according to the multidimensional risk prediction result.
In a third aspect, the present application also provides a computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program when executed by the processor implements the steps of an enterprise credit auditing method as described above.
In a fourth aspect, the present application also provides a computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of an enterprise credit auditing method as described above.
The application provides an enterprise credit auditing method, device, equipment and computer readable storage medium, which are characterized in that microexpressive recognition and speech emotion recognition are carried out on credit auditing videos to obtain microexpressive type sets and speech emotion types, then, according to the microexpressive type sets and the speech emotion types, enterprise multidimensional image data are verified, when the enterprise multidimensional image data pass the verification, the enterprise multidimensional image data are analyzed through a plurality of random forests in each layer in a preset random forest model, so that an accurate multidimensional risk prediction result can be obtained, finally, according to the multidimensional risk prediction result, whether a target enterprise passes loan auditing can be judged, and the authenticity of the multidimensional image data can be ensured to a certain extent through microexpressive recognition and speech emotion recognition loan, and meanwhile, by analyzing the multidimensional image data, the auditing result can be accurately obtained, and the auditing accuracy of the enterprise credit loan can be effectively improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an enterprise credit auditing method according to an embodiment of the present application;
FIG. 2 is a flow chart illustrating sub-steps of the enterprise credit auditing method of FIG. 1;
FIG. 3 is a flow chart of another method for auditing credit for an enterprise according to an embodiment of the present application;
FIG. 4 is a schematic block diagram of an enterprise credit auditing apparatus provided by an embodiment of the application;
FIG. 5 is a schematic block diagram of a sub-module of the enterprise credit auditing apparatus of FIG. 4;
FIG. 6 is a schematic block diagram of another enterprise credit auditing apparatus provided by an embodiment of the application;
Fig. 7 is a schematic block diagram of a computer device according to an embodiment of the present application.
The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations.
The embodiment of the application provides an enterprise credit auditing method, an enterprise credit auditing device, computer equipment and a computer readable storage medium. The enterprise credit auditing method can be applied to a server, wherein the server can be a single server or a server cluster consisting of a plurality of servers.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a flowchart of an enterprise credit auditing method according to an embodiment of the present application.
As shown in fig. 1, the enterprise credit auditing method includes steps S101 through S105.
And step S101, when an enterprise credit auditing request is monitored, acquiring a credit auditing video and enterprise multidimensional image data of a target enterprise according to the enterprise credit auditing request.
The enterprise multidimensional image data comprises self image data submitted when the enterprise applies for credit, image data collected by internal banks and enterprise image data crawled on websites. The information comprises the information of enterprise scale, enterprise cooperation objects, enterprise annual business or financing conditions, enterprise establishment time, recent half-year ticket opening amount, enterprise marketing license, tax registration certificate, organization code certificate, recent certification of registered capital report, recent six month value-added tax or income tax payment evidence, recent one year financial statement, recent six month bank statement of the enterprise, enterprise liability rate, identity card of a stock holder with enterprise shares exceeding a set proportion, passport or other relevant enterprise credit collection data and the like.
When an enterprise applies for enterprise credit to a bank, bank staff can inquire corporate legal persons, stakeholders and/or main staff on site or remotely in a video inquiry mode, face data and voice data of inquired persons are collected through video equipment or terminal equipment in the inquiry process, so that corresponding credit auditing videos are generated, then the credit auditing videos are uploaded to a background server through the video equipment or the terminal equipment, the server stores the credit auditing videos based on enterprise tag association, and in addition, the server stores enterprise multidimensional image data based on the enterprise tag association. The enterprise tag is used for uniquely representing an enterprise applying for loans, and the terminal device can be electronic devices such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, a wearable device and the like.
When an enterprise credit auditing request is monitored, the server acquires a credit auditing video and enterprise multidimensional image data of a target enterprise according to the enterprise credit auditing request, namely, acquires an enterprise tag from the enterprise credit auditing request, and acquires the credit auditing video and the enterprise multidimensional image data associated with the enterprise tag.
The method comprises the steps that a target enterprise is an enterprise uniquely represented by an enterprise tag in an enterprise credit auditing request, the triggering mode of the enterprise credit auditing request comprises timing triggering and real-time triggering, the timing triggering is that a server queries whether an unverified loan auditing task exists in a loan auditing task queue through the timing task, and if the unverified loan auditing task exists in the loan auditing task queue, the enterprise credit auditing request is triggered according to the unverified loan auditing task; and the real-time triggering is to inquire whether an unverified loan auditing task exists in a loan auditing task queue when an auditing instruction input by an auditing person is monitored, and if the unverified loan auditing task exists in the loan auditing task queue, triggering an enterprise credit auditing request according to the unverified loan auditing task.
And step S102, performing micro-expression recognition and voice emotion recognition on the credit auditing video to obtain a micro-expression type set and a voice emotion type.
After the credit auditing video and the enterprise multidimensional image data are acquired, the enterprise multidimensional image data need to be checked based on the credit auditing video, specifically, the credit auditing video is subjected to micro-expression recognition and voice emotion recognition to obtain a micro-expression type set and a voice emotion type, and then the enterprise multidimensional image data are checked based on the micro-expression type set and the voice emotion type.
In the implementation, when corporate legal persons, stakeholders and/or main personnel can be queried through videos on site or remotely, the queried person is subjected to micro-expression recognition and voice emotion recognition through terminal equipment to obtain a micro-expression type set and a voice emotion type, the obtained micro-expression type set and the obtained voice emotion type are uploaded to a server, and the server stores the micro-expression type set and the voice emotion type based on the corporate label association.
In one embodiment, as shown in fig. 2, step S102 includes: substep S1021 to substep S1023.
And S1021, performing audio-video separation on the credit auditing video to obtain a target video and a target audio to be identified.
Specifically, the credit checking video is subjected to audio-video separation to obtain a target video and a target audio to be identified, optionally, a preset audio format is obtained, and the format of the credit checking video is converted into the preset audio format so as to realize audio-video separation, thereby obtaining the target video and the target audio to be identified. It should be noted that the preset audio format may be set based on practical situations, which is not particularly limited by the present application.
And step S1022, performing microexpressive recognition on the target video to obtain a microexpressive type set.
Specifically, a prestored micro-expression recognition model is obtained, and micro-expression recognition is carried out on the target video through the micro-expression recognition model, so that a micro-expression type set is obtained. The micro-expression recognition model can be selected as a micro-expression recognition model based on deep learning, and is obtained in a training mode.
The training mode is specifically as follows: preparing a data set, including video segment collection of micro expressions, video image normalization processing, training/verification/test set segmentation and the like; the method comprises the steps of designing a microexpressive recognition model to be trained based on a convolutional neural network and a cyclic neural network, training the microexpressive recognition model to be trained through a training set until the model converges, verifying and testing the converged microexpressive recognition model by utilizing a verification set and a test set, and solidifying the microexpressive recognition model after meeting the requirements.
The method for performing micro-expression recognition on the target video may specifically be: performing microexpressive recognition on each frame of image in the target video, determining the microexpressive type of each frame of image, and collecting the microexpressive type of each image frame to obtain a microexpressive type set. In the specific implementation, the situation that the micro-expression types are the same exists, so when the micro-expression types of each image frame are collected, if the micro-expression types of the image frames are the same, only the micro-expression type of one image frame is collected, and the micro-expression type in the micro-expression type set is ensured not to be repeated.
The micro expression type of each frame of image is determined in the following manner: splitting the target video into a plurality of frames of images, simultaneously extracting target feature vectors of each frame of images in the plurality of frames of images, acquiring a prestored micro-expression library, calculating similarity probability between the target feature vector of each image frame and feature vectors of each preset micro-expression in the micro-expression library, and determining a micro-expression type corresponding to the similarity probability larger than the preset similarity probability as the micro-expression type of the image frame. It should be noted that the preset similarity probability may be set based on practical situations, which is not particularly limited in the present application.
And step S1023, carrying out voice emotion recognition on the target audio to obtain a target emotion type of the target audio.
Specifically, feature extraction is performed on the target audio to obtain voice features, and the target emotion type of the target audio is determined through a preset voice emotion recognition model and the voice features. The speech features include, but are not limited to, duration-related features, fundamental frequency-related features, energy-related features, cepstral coefficients, and Mel-frequency cepstral coefficients.
It should be noted that, the speech emotion recognition model is obtained through training, and the training mode is specifically as follows: and establishing a voice feature training sample set and a voice emotion recognition model to be trained, and iteratively training the voice emotion recognition model by using the voice feature training sample set until the voice emotion recognition model converges. Optionally, the speech emotion recognition model includes a deep feature extraction neural network capable of extracting speech emotion features from the speech features and outputting the corresponding emotion classification.
And step 103, checking the enterprise multidimensional image data according to the microexpressive type set and the voice emotion type.
After the micro-expression type set and the voice emotion type are obtained, the multidimensional image data of the enterprise are verified according to the micro-expression type set and the voice emotion type. The method comprises the following steps: counting the number of the micro-expression types in the micro-expression type group, which is recorded as the same number of the types, judging whether the same number of the types is larger than or equal to the preset number, and judging whether the voice emotion type is the preset emotion type; if the same number of the types is greater than or equal to the preset number and the voice emotion type is not the preset emotion type, determining that the multidimensional image data of the enterprise passes the verification; if the same number of types is smaller than the preset number or the voice emotion type is the preset emotion type, determining that the multidimensional image data of the enterprise fails to pass the verification.
It should be noted that the preset number, the preset micro-expression type group and the preset emotion type can be set based on actual situations, which is not limited in particular by the present application, optionally, the pre-stored micro-expression type group stores micro-expression type labels for indicating whether the user lies, for example, micro-expression type labels for indicating continuous blinking, rapid back and forth movement of eyeballs, and speaking pause in mouth, and the preset emotion type is used for indicating whether the user lies.
And step S104, when the enterprise multidimensional image data passes the verification, analyzing the enterprise multidimensional image data through a plurality of random forests of each layer in a preset random forest model to obtain a multidimensional risk prediction result.
And when the multidimensional image data of the enterprise passes the verification, further performing loan audit on the target enterprise, specifically analyzing the multidimensional image data of the enterprise through a plurality of random forests of each layer in a preset random forest model, and obtaining a multidimensional risk prediction result. The preset random forest model is obtained based on training, the random forest model comprises a plurality of layers of random forest systems, and each layer of random forest system comprises a plurality of random forests.
In one embodiment, the method for analyzing the multidimensional image data of the enterprise specifically includes: converting the enterprise multidimensional portrait data into a multidimensional portrait matrix; analyzing the multidimensional portrait matrix through a plurality of random forests of each layer in a preset random forest model to obtain a multidimensional risk prediction result, wherein input data of each layer of the plurality of random forests in the random forest model comprises input data and output data of a plurality of random forests of the previous layer, the input data of a plurality of random forests of the first layer in the random forest model is the multidimensional portrait matrix, and the output data of the plurality of random forests of the first layer is a risk prediction sequence.
It should be noted that the number of random forests in different layers may be the same or different, and the number of layers of the random forest model may be set based on practical situations, which is not particularly limited in the present application, and the process of analyzing the multidimensional image matrix is explained in the following description with a random forest model including three layers of random forest systems, where the random forest numbers of the random forest systems in each layer are the same.
Analyzing the multidimensional image matrix through a plurality of random forests of a first layer of the random forest model to obtain a first risk prediction sequence; adding the first risk prediction sequence into the multidimensional image matrix to obtain a first dimension-expanded image matrix; analyzing the first dimension-expanding image matrix through a plurality of random forests of a second layer in the random forest model to obtain a second risk prediction sequence; adding the second risk prediction sequence into the first dimension-expanded image matrix to obtain a second dimension-expanded image matrix; analyzing the second dimension-expanding image matrix through a plurality of random forests of a third layer, namely the last layer, in the random forest model to obtain a third risk prediction sequence; and determining the third risk prediction sequence as a multidimensional risk prediction result of the target enterprise.
After each random forest analyzes the portrait matrix, 0 or 1 is output, if 0 is output, the enterprise is indicated to have no default risk, if 1 is output, the enterprise is indicated to have default risk, the risk prediction sequence is composed of 0 or 1 output by each random forest, the more 1 in the risk prediction sequence is, the higher the default risk of the enterprise is, and the more 0 in the risk prediction sequence is, the lower the default risk of the enterprise is.
And step 105, judging whether the target enterprise passes loan audit or not according to the multidimensional risk prediction result.
After a multidimensional risk prediction result is obtained, judging whether a target enterprise passes loan auditing, specifically: acquiring a risk prediction result output by each random forest from the multi-dimensional risk prediction results to form a risk prediction result group; counting risk prediction results in the risk prediction result group to be the number of preset results, and judging whether the number is larger than or equal to a preset threshold value; if the number is greater than or equal to a preset threshold, determining that the target enterprise passes loan audit; if the number is less than the preset threshold, determining that the target enterprise fails the loan audit. It should be noted that the preset threshold may be set based on practical situations, which is not particularly limited in the present application.
According to the enterprise credit auditing method provided by the embodiment, the authenticity of the multidimensional image data can be ensured to a certain extent through the microexpressive recognition and the voice emotion recognition, and meanwhile, the loan auditing result can be accurately obtained through analyzing the multidimensional image data, so that the auditing accuracy of the enterprise credit loan is effectively improved.
Referring to fig. 3, fig. 3 is a flowchart of another method for auditing credit of an enterprise according to an embodiment of the application.
As shown in fig. 3, the enterprise credit auditing method includes steps S201 through 207.
Step S201, when an enterprise credit auditing request is monitored, acquiring a credit auditing video and enterprise multidimensional image data of a target enterprise according to the enterprise credit auditing request.
When an enterprise credit auditing request is monitored, the server acquires a credit auditing video and enterprise multidimensional image data of a target enterprise according to the enterprise credit auditing request, namely, acquires an enterprise tag from the enterprise credit auditing request, and acquires the credit auditing video and the enterprise multidimensional image data associated with the enterprise tag.
And step S202, performing micro-expression recognition and voice emotion recognition on the credit auditing video to obtain a micro-expression type set and a voice emotion type.
After the credit auditing video and the enterprise multidimensional image data are acquired, the enterprise multidimensional image data need to be checked based on the credit auditing video, specifically, the credit auditing video is subjected to micro-expression recognition and voice emotion recognition to obtain a micro-expression type set and a voice emotion type, and then the enterprise multidimensional image data are checked based on the micro-expression type set and the voice emotion type.
And step 203, verifying the enterprise multidimensional image data according to the microexpressive type set and the voice emotion type.
After the micro-expression type set and the voice emotion type are obtained, the multidimensional image data of the enterprise are verified according to the micro-expression type set and the voice emotion type. The method comprises the following steps: counting the number of the micro-expression types in the micro-expression type group, which is recorded as the same number of the types, judging whether the same number of the types is larger than or equal to the preset number, and judging whether the voice emotion type is the preset emotion type; if the same number of the types is greater than or equal to the preset number and the voice emotion type is not the preset emotion type, determining that the multidimensional image data of the enterprise passes the verification; if the same number of types is smaller than the preset number or the voice emotion type is the preset emotion type, determining that the multidimensional image data of the enterprise fails to pass the verification.
And step 204, calculating a correlation coefficient between every two dimensions of the image data of the enterprise multidimensional image data when the enterprise multidimensional image data passes the verification.
When the enterprise multidimensional image data passes the verification, calculating a correlation coefficient between the image data of every two dimensions in the enterprise multidimensional image data. Wherein, the calculation formula of the correlation coefficient is as follows:
where r is a correlation coefficient, x i is the i-th group of data of image data of one of the two dimensions, For the mean value of each group of data of portrait data in one dimension, y i is the ith group of data of portrait data in the other dimension of two dimensions,/>And n is the total number of the data groups of the image data of any one of the two dimensions, and the total number of the data groups of the two dimensions is the same.
And step 205, screening the enterprise multidimensional image data according to the correlation coefficient between the image data of every two dimensions to obtain target multidimensional image data.
After the correlation coefficient between the portrait data of each two dimensions is obtained through calculation, the enterprise multidimensional portrait data is screened according to the correlation coefficient between the portrait data of each two dimensions, so as to obtain target multidimensional portrait data, namely, portrait data of two target dimensions, of which the absolute value of the correlation coefficient is larger than or equal to a preset correlation coefficient, are obtained, and portrait data of any one of the two target dimensions are deleted from the enterprise multidimensional portrait data, so that the target multidimensional portrait data are obtained. It should be noted that the preset correlation coefficient is a positive number, and may be set based on practical situations, which is not particularly limited in the present application.
And S206, analyzing the target multidimensional image data through a plurality of random forests in each layer of a preset random forest model to obtain a multidimensional risk prediction result.
After the multi-dimensional image data are obtained, analyzing the target multi-dimensional image data through a plurality of random forests of each layer in a preset random forest model to obtain a multi-dimensional risk prediction result, namely converting the target multi-dimensional image data into a multi-dimensional image matrix; and analyzing the multi-dimensional portrait matrix through a plurality of random forests of each layer in a preset random forest model to obtain a multi-dimensional risk prediction result.
The input data of each layer of multiple random forests in the random forest model comprises input data and output data of the previous layer of multiple random forests, the input data of the first layer of multiple random forests in the random forest model is a multidimensional image matrix, and the output data of the first layer of multiple random forests is a risk prediction sequence.
And step S207, judging whether the target enterprise passes loan audit or not according to the multidimensional risk prediction result.
After a multidimensional risk prediction result is obtained, judging whether a target enterprise passes loan auditing, specifically: acquiring a risk prediction result output by each random forest from the multi-dimensional risk prediction results to form a risk prediction result group; counting risk prediction results in the risk prediction result group to be the number of preset results, and judging whether the number is larger than or equal to a preset threshold value; if the number is greater than or equal to a preset threshold, determining that the target enterprise passes loan audit; if the number is less than the preset threshold, determining that the target enterprise fails the loan audit.
According to the enterprise credit auditing method provided by the embodiment, the data redundancy can be reduced by screening the enterprise multidimensional image data, and the data processing speed can be improved, so that the loan auditing efficiency is indirectly improved.
Referring to fig. 4, fig. 4 is a schematic block diagram of an enterprise credit auditing apparatus according to an embodiment of the application.
As shown in fig. 4, the enterprise credit auditing apparatus 300 includes: an acquisition module 301, an identification module 302, a verification module 303, an analysis module 304 and a judgment module 305.
The obtaining module 301 is configured to obtain, when an enterprise credit auditing request is detected, a credit auditing video and enterprise multidimensional image data of a target enterprise according to the enterprise credit auditing request.
The recognition module 302 is configured to perform micro-expression recognition and speech emotion recognition on the credit auditing video, so as to obtain a micro-expression type set and a speech emotion category.
In one embodiment, as shown in fig. 5, the identification module 302 includes:
and the separation submodule 3021 is used for carrying out audio-video separation on the credit checking video to obtain a target video and a target audio to be identified.
And the microexpressive recognition submodule 3022 is used for carrying out microexpressive recognition on the target video to obtain a microexpressive type set.
The emotion recognition sub-module 3023 performs speech emotion recognition on the target audio to obtain a target emotion category of the target audio.
And the verification module 303 is configured to verify the multidimensional image data of the enterprise according to the set of micro-expression types and the category of speech emotion.
In an embodiment, the verification module 303 is further configured to count the number of micro-expression types in the micro-expression type set, and determine whether the number is greater than or equal to a preset number, and determine whether the speech emotion type is a preset emotion type; if the number is greater than or equal to the preset number and the voice emotion type is not the preset emotion type, determining that the enterprise multidimensional image data passes verification; if the number is smaller than the preset number or the voice emotion type is the preset emotion type, determining that the enterprise multidimensional image data does not pass the verification.
And the analysis module 304 is configured to analyze the multidimensional image data of the enterprise through a plurality of random forests in each layer in a preset random forest model to obtain a multidimensional risk prediction result when the multidimensional image data of the enterprise passes the verification.
In one embodiment, the analysis module 304 is further configured to convert the enterprise multidimensional representation data into a multidimensional representation matrix; analyzing the multidimensional image matrix through a plurality of random forests of each layer in a preset random forest model to obtain a multidimensional risk prediction result, wherein input data of each layer of the plurality of random forests in the random forest model comprises input data and output data of a plurality of random forests of the previous layer, the input data of a first layer of the plurality of random forests in the random forest model is the multidimensional image matrix, and the output data of the first layer of the plurality of random forests is a risk prediction sequence.
And the judging module 305 is configured to judge whether the target enterprise passes the loan audit according to the multidimensional risk prediction result.
In one embodiment, the determining module 305 is further configured to obtain a risk prediction result output by each random forest from the multi-dimensional risk prediction results, so as to form a risk prediction result set; counting the risk prediction results in the risk prediction result group to be the number of preset results, and judging whether the number is larger than or equal to a preset threshold value; if the number is greater than or equal to a preset threshold, determining that the target enterprise passes loan auditing; and if the number is smaller than a preset threshold, determining that the target enterprise does not pass the loan audit.
Referring to FIG. 6, FIG. 6 is a schematic block diagram of another enterprise credit auditing apparatus according to an embodiment of the application.
As shown in fig. 6, the enterprise credit auditing apparatus 400 includes: an acquisition module 401, an identification module 402, a verification module 403, an analysis module 404 and a judgment module 405.
The obtaining module 401 is configured to obtain, when an enterprise credit auditing request is detected, a credit auditing video and enterprise multidimensional image data of a target enterprise according to the enterprise credit auditing request.
The recognition module 402 is configured to perform microexpressive recognition and speech emotion recognition on the credit auditing video to obtain a microexpressive type set and a speech emotion category.
And the verification module 403 is configured to verify the multidimensional image data of the enterprise according to the set of micro-expression types and the category of speech emotion.
And the analysis module 404 is configured to analyze the multidimensional image data of the enterprise through a plurality of random forests in each layer in a preset random forest model to obtain a multidimensional risk prediction result when the multidimensional image data of the enterprise passes the verification.
In one embodiment, as shown in fig. 6, the analysis module 404 includes:
and a calculating submodule 4041, configured to calculate a correlation coefficient between every two dimensions of the image data of the enterprise multidimensional image data when the enterprise multidimensional image data passes the verification.
And a screening submodule 4042, configured to screen the enterprise multidimensional image data according to the correlation coefficient between the image data of each two dimensions, so as to obtain target multidimensional image data.
And the analysis submodule 4043 is used for analyzing the target multidimensional image data through a plurality of random forests in each layer of the preset random forest model to obtain a multidimensional risk prediction result.
In an embodiment, the filtering submodule 4042 is further configured to obtain image data of two target dimensions with the correlation coefficient greater than or equal to a preset correlation coefficient; deleting the portrait data of any one of the two target dimensions from the enterprise multidimensional portrait data to obtain target multidimensional portrait data.
And the judging module 405 is configured to judge whether the target enterprise passes the loan audit according to the multidimensional risk prediction result.
It should be noted that, for convenience and brevity of description, specific working processes of the above-described apparatus and modules and units may refer to corresponding processes in the foregoing embodiments of the enterprise credit auditing method, and will not be described herein again.
The apparatus provided by the above embodiments may be implemented in the form of a computer program which may be run on a computer device as shown in fig. 7.
Referring to fig. 7, fig. 7 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device may be a server.
As shown in fig. 7, the computer device includes a processor, a memory, and a network interface connected by a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.
The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor to perform any of a variety of enterprise credit auditing methods.
The processor is used to provide computing and control capabilities to support the operation of the entire computer device.
The internal memory provides an environment for the execution of a computer program in a non-volatile storage medium that, when executed by a processor, causes the processor to perform any of a number of enterprise credit auditing methods.
The network interface is used for network communication such as transmitting assigned tasks and the like. It will be appreciated by those skilled in the art that the structure shown in FIG. 7 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
It should be appreciated that the Processor may be a central processing unit (Central Processing Unit, CPU), it may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATEARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein in one embodiment the processor is configured to run a computer program stored in the memory to implement the steps of:
When an enterprise credit auditing request is monitored, acquiring a credit auditing video of a target enterprise and enterprise multidimensional image data according to the enterprise credit auditing request;
performing micro-expression recognition and voice emotion recognition on the credit auditing video to obtain a micro-expression type set and a voice emotion type;
Verifying the enterprise multidimensional image data according to the microexpressive type set and the voice emotion type;
when the enterprise multidimensional image data passes the verification, analyzing the enterprise multidimensional image data through a plurality of random forests of each layer in a preset random forest model to obtain a multidimensional risk prediction result;
judging whether the target enterprise passes loan auditing according to the multidimensional risk prediction result
In one embodiment, the processor is configured to, when implementing micro-expression recognition and speech emotion recognition on the credit auditing video to obtain a micro-expression type set and a speech emotion category, implement:
performing audio-video separation on the credit auditing video to obtain a target video and a target audio to be identified;
performing microexpressive recognition on the target video to obtain a microexpressive type set;
and carrying out voice emotion recognition on the target audio to obtain a target emotion type of the target audio.
In one embodiment, the processor is configured to, when implementing verification of the enterprise multidimensional image data according to the set of micro-expression types and the class of speech emotion, implement:
counting the number of the micro-expression types in a micro-expression type group, judging whether the number is larger than or equal to the preset number, and judging whether the voice emotion type is a preset emotion type;
If the number is greater than or equal to the preset number and the voice emotion type is not the preset emotion type, determining that the enterprise multidimensional image data passes verification;
if the number is smaller than the preset number or the voice emotion type is the preset emotion type, determining that the enterprise multidimensional image data does not pass the verification.
In one embodiment, the processor is configured to, when implementing analysis of the multidimensional image data of the enterprise by a plurality of random forests in each layer of a preset random forest model, implement:
converting the enterprise multidimensional representation data into a multidimensional representation matrix;
Analyzing the multidimensional image matrix through a plurality of random forests of each layer in a preset random forest model to obtain a multidimensional risk prediction result, wherein input data of each layer of the plurality of random forests in the random forest model comprises input data and output data of a plurality of random forests of the previous layer, the input data of a first layer of the plurality of random forests in the random forest model is the multidimensional image matrix, and the output data of the first layer of the plurality of random forests is a risk prediction sequence.
In one embodiment, when the processor determines whether the target enterprise passes the loan audit according to the multidimensional risk prediction result, the processor is configured to implement:
Acquiring a risk prediction result output by each random forest from the multi-dimensional risk prediction results to form a risk prediction result group;
Counting the risk prediction results in the risk prediction result group to be the number of preset results, and judging whether the number is larger than or equal to a preset threshold value;
If the number is greater than or equal to a preset threshold, determining that the target enterprise passes loan auditing;
And if the number is smaller than a preset threshold, determining that the target enterprise does not pass the loan audit.
In another embodiment, the processor is configured to run a computer program stored in a memory, so as to implement, when the multidimensional image data of the enterprise passes the verification, analysis of the multidimensional image data of the enterprise through a plurality of random forests in each layer in a preset random forest model, and when a multidimensional risk prediction result is obtained, implementation:
When the enterprise multidimensional image data passes the verification, calculating a correlation coefficient between the image data of every two dimensions in the enterprise multidimensional image data;
Screening the enterprise multidimensional image data according to the correlation coefficient between the image data of every two dimensions to obtain target multidimensional image data;
And analyzing the target multidimensional image data through a plurality of random forests in each layer of a preset random forest model to obtain a multidimensional risk prediction result.
In one embodiment, the processor is configured to, when implementing screening the enterprise multidimensional image data according to a correlation coefficient between image data of every two dimensions to obtain target multidimensional image data, implement:
Acquiring portrait data of two target dimensions with the correlation coefficient larger than or equal to a preset correlation coefficient;
Deleting the portrait data of any one of the two target dimensions from the enterprise multidimensional portrait data to obtain target multidimensional portrait data.
Embodiments of the present application also provide a computer readable storage medium having a computer program stored thereon, the computer program comprising program instructions that when executed implement methods that can be referenced by various embodiments of the enterprise credit auditing method of the present application.
The computer readable storage medium may be an internal storage unit of the computer device according to the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like, which are provided on the computer device.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments. While the application has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (9)
1. An enterprise credit auditing method, comprising:
When an enterprise credit auditing request is monitored, acquiring a credit auditing video of a target enterprise and enterprise multidimensional image data according to the enterprise credit auditing request;
performing micro-expression recognition and voice emotion recognition on the credit auditing video to obtain a micro-expression type set and a voice emotion type;
Verifying the enterprise multidimensional image data according to the microexpressive type set and the voice emotion type;
when the enterprise multidimensional image data passes the verification, analyzing the enterprise multidimensional image data through a plurality of random forests of each layer in a preset random forest model to obtain a multidimensional risk prediction result;
judging whether the target enterprise passes loan auditing according to the multidimensional risk prediction result;
The analyzing the multi-dimensional image data of the enterprise through a plurality of random forests of each layer in a preset random forest model, and obtaining a multi-dimensional risk prediction result comprises the following steps: converting the enterprise multidimensional representation data into a multidimensional representation matrix; analyzing the multidimensional image matrix through a plurality of random forests of a first layer of the random forest model to obtain a first risk prediction sequence, and adding the first risk prediction sequence into the multidimensional image matrix to obtain a first dimension-expanding image matrix; analyzing the first dimension-expanding image matrix through a plurality of random forests of a second layer of the random forest model to obtain a second risk prediction sequence, and adding the second risk prediction sequence into the first dimension-expanding image matrix to obtain a second dimension-expanding image matrix; and analyzing the second dimension-expanding image matrix through a plurality of random forests of a third layer of the random forest model to obtain a third risk prediction sequence, and determining the third risk prediction sequence as a multidimensional risk prediction result of a target enterprise.
2. The method of enterprise credit auditing method of claim 1, wherein the performing microexpressive recognition and speech emotion recognition on the credit auditing video to obtain a microexpressive type set and a speech emotion category includes:
performing audio-video separation on the credit auditing video to obtain a target video and a target audio to be identified;
performing microexpressive recognition on the target video to obtain a microexpressive type set;
and carrying out voice emotion recognition on the target audio to obtain a target emotion type of the target audio.
3. The method of enterprise credit auditing of claim 1, wherein the verifying the enterprise multidimensional image data based on the collection of micro-expression types and the voice emotion classification comprises:
counting the number of the micro-expression types in a micro-expression type group, judging whether the number is larger than or equal to the preset number, and judging whether the voice emotion type is a preset emotion type;
If the number is greater than or equal to the preset number and the voice emotion type is not the preset emotion type, determining that the enterprise multidimensional image data passes verification;
if the number is smaller than the preset number or the voice emotion type is the preset emotion type, determining that the enterprise multidimensional image data does not pass the verification.
4. The method of any one of claims 1-3, wherein the determining whether the target business passes a loan audit based on the multi-dimensional risk prediction result comprises:
Acquiring a risk prediction result output by each random forest from the multi-dimensional risk prediction results to form a risk prediction result group;
Counting the risk prediction results in the risk prediction result group to be the number of preset results, and judging whether the number is larger than or equal to a preset threshold value;
If the number is greater than or equal to a preset threshold, determining that the target enterprise passes loan auditing;
And if the number is smaller than a preset threshold, determining that the target enterprise does not pass the loan audit.
5. The method for auditing enterprise credit according to any one of claims 1-3, wherein when the enterprise multidimensional image data passes verification, analyzing the enterprise multidimensional image data through a plurality of random forests of each layer in a preset random forest model to obtain a multidimensional risk prediction result, including:
When the enterprise multidimensional image data passes the verification, calculating a correlation coefficient between the image data of every two dimensions in the enterprise multidimensional image data;
Screening the enterprise multidimensional image data according to the correlation coefficient between the image data of every two dimensions to obtain target multidimensional image data;
And analyzing the target multidimensional image data through a plurality of random forests in each layer of a preset random forest model to obtain a multidimensional risk prediction result.
6. The method for auditing enterprise credit according to claim 5, wherein said screening the enterprise multidimensional image data based on correlation coefficients between the image data of each two dimensions to obtain target multidimensional image data comprises:
Acquiring portrait data of two target dimensions with the correlation coefficient larger than or equal to a preset correlation coefficient;
Deleting the portrait data of any one of the two target dimensions from the enterprise multidimensional portrait data to obtain target multidimensional portrait data.
7. An enterprise credit auditing apparatus, the enterprise credit auditing apparatus comprising:
The acquisition module is used for acquiring a credit auditing video and enterprise multidimensional image data of a target enterprise according to the enterprise credit auditing request when the enterprise credit auditing request is monitored;
The recognition module is used for carrying out micro-expression recognition and voice emotion recognition on the credit auditing video to obtain a micro-expression type set and a voice emotion type;
The verification module is used for verifying the enterprise multidimensional image data according to the microexpressive type set and the voice emotion type;
The analysis module is used for analyzing the enterprise multidimensional image data through a plurality of random forests of each layer in a preset random forest model when the enterprise multidimensional image data passes the verification, so as to obtain a multidimensional risk prediction result;
The judging module is used for judging whether the target enterprise passes loan auditing according to the multidimensional risk prediction result;
The analyzing the multi-dimensional image data of the enterprise through a plurality of random forests of each layer in a preset random forest model, and obtaining a multi-dimensional risk prediction result comprises the following steps: converting the enterprise multidimensional representation data into a multidimensional representation matrix; analyzing the multidimensional image matrix through a plurality of random forests of a first layer of the random forest model to obtain a first risk prediction sequence, and adding the first risk prediction sequence into the multidimensional image matrix to obtain a first dimension-expanding image matrix; analyzing the first dimension-expanding image matrix through a plurality of random forests of a second layer of the random forest model to obtain a second risk prediction sequence, and adding the second risk prediction sequence into the first dimension-expanding image matrix to obtain a second dimension-expanding image matrix; and analyzing the second dimension-expanding image matrix through a plurality of random forests of a third layer of the random forest model to obtain a third risk prediction sequence, and determining the third risk prediction sequence as a multidimensional risk prediction result of a target enterprise.
8. A computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program when executed by the processor implements the steps of the enterprise credit auditing method of any of claims 1 to 6.
9. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program, wherein the computer program, when executed by a processor, implements the steps of the enterprise credit auditing method of any one of claims 1 to 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910600404.7A CN110443692B (en) | 2019-07-04 | 2019-07-04 | Enterprise credit auditing method, device, equipment and computer readable storage medium |
| PCT/CN2020/093406 WO2021000678A1 (en) | 2019-07-04 | 2020-05-29 | Business credit review method, apparatus, and device, and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910600404.7A CN110443692B (en) | 2019-07-04 | 2019-07-04 | Enterprise credit auditing method, device, equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110443692A CN110443692A (en) | 2019-11-12 |
| CN110443692B true CN110443692B (en) | 2024-05-10 |
Family
ID=68428467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910600404.7A Active CN110443692B (en) | 2019-07-04 | 2019-07-04 | Enterprise credit auditing method, device, equipment and computer readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110443692B (en) |
| WO (1) | WO2021000678A1 (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443692B (en) * | 2019-07-04 | 2024-05-10 | 平安科技（深圳）有限公司 | Enterprise credit auditing method, device, equipment and computer readable storage medium |
| CN111583935A (en) * | 2020-04-02 | 2020-08-25 | 深圳壹账通智能科技有限公司 | Loan intelligent delivery method, device and storage medium |
| CN112258317B (en) * | 2020-10-30 | 2022-11-11 | 深圳壹账通智能科技有限公司 | Online credit method, device, computer equipment and medium based on artificial intelligence |
| CN112767131A (en) * | 2021-01-26 | 2021-05-07 | 福建卓融信息技术有限公司 | Loan approval-based risk control method and device |
| CN112884442B (en) * | 2021-03-01 | 2024-05-03 | 广东铭太信息科技有限公司 | Audit monitoring data acquisition method and system based on audit model |
| CN112907101A (en) * | 2021-03-09 | 2021-06-04 | 山大地纬软件股份有限公司 | Enterprise illegal funding behavior risk early warning method and system |
| CN113077346A (en) * | 2021-04-30 | 2021-07-06 | 平安信托有限责任公司 | Data processing method and device, computer equipment and storage medium |
| CN113506174A (en) * | 2021-08-19 | 2021-10-15 | 北京中数智汇科技股份有限公司 | Method, device and equipment for training risk early warning model of medium and small enterprises |
| CN113723811A (en) * | 2021-08-30 | 2021-11-30 | 平安国际智慧城市科技股份有限公司 | Equipment maintenance unit evaluation method and device based on machine learning and electronic equipment |
| CN113706300A (en) * | 2021-09-18 | 2021-11-26 | 中国银行股份有限公司 | Loan method and device for small and micro enterprises |
| CN114119201B (en) * | 2021-11-26 | 2024-01-23 | 天元大数据信用管理有限公司 | Enterprise credit investigation method, equipment and medium |
| CN114971532A (en) * | 2022-04-29 | 2022-08-30 | 北京国联视讯信息技术股份有限公司 | Enterprise full-channel member management method and system based on big data |
| CN116303688A (en) * | 2023-05-17 | 2023-06-23 | 北京德钧科技服务有限公司 | Digital analysis method, system, equipment and medium based on Internet |
| CN116934464A (en) * | 2023-07-26 | 2023-10-24 | 广东企企通科技有限公司 | Post-loan risk monitoring method, device, equipment and medium based on small micro-enterprises |
| CN117422547B (en) * | 2023-12-18 | 2024-04-02 | 湖南三湘银行股份有限公司 | Auditing device and method based on intelligent dialogue system and micro expression recognition |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106960387A (en) * | 2017-04-28 | 2017-07-18 | 浙江工商大学 | Individual credit risk appraisal procedure and system |
| 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 kind of personal credit's violation correction method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10515393B2 (en) * | 2016-06-30 | 2019-12-24 | Paypal, Inc. | Image data detection for micro-expression analysis and targeted data services |
| 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 |
| CN108765131B (en) * | 2018-05-18 | 2023-06-09 | 深圳壹账通智能科技有限公司 | Micro-expression-based credit auditing method, device, terminal and readable storage medium |
| CN110443692B (en) * | 2019-07-04 | 2024-05-10 | 平安科技（深圳）有限公司 | Enterprise credit auditing method, device, equipment and computer readable storage medium |
-
2019
- 2019-07-04 CN CN201910600404.7A patent/CN110443692B/en active Active
-
2020
- 2020-05-29 WO PCT/CN2020/093406 patent/WO2021000678A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106960387A (en) * | 2017-04-28 | 2017-07-18 | 浙江工商大学 | Individual credit risk appraisal procedure and system |
| 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 kind of personal credit's violation correction method |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021000678A1 (en) | 2021-01-07 |
| CN110443692A (en) | 2019-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110443692B (en) | Enterprise credit auditing method, device, equipment and computer readable storage medium | |
| WO2020077895A1 (en) | Signing intention determining method and apparatus, computer device, and storage medium | |
| CN110009475B (en) | Risk auditing and monitoring method and device, computer equipment and storage medium | |
| US11810070B2 (en) | Classifying digital documents in multi-document transactions based on embedded dates | |
| CN112613501A (en) | Information auditing classification model construction method and information auditing method | |
| US11769014B2 (en) | Classifying digital documents in multi-document transactions based on signatory role analysis | |
| CN115828112B (en) | Fault event response method and device, electronic equipment and storage medium | |
| CN113177700B (en) | Risk assessment method, system, electronic equipment and storage medium | |
| CN105138886B (en) | Robot biometric identification system | |
| CN113837151A (en) | Table image processing method and device, computer equipment and readable storage medium | |
| CN115376559A (en) | Emotion recognition method, device and equipment based on audio and video | |
| CN112861056A (en) | Enterprise website construction information display and release system and method | |
| CN116453125A (en) | Data input method, device, equipment and storage medium based on artificial intelligence | |
| CN114140649A (en) | Bill classification method, bill classification device, electronic apparatus, and storage medium | |
| CN116542783A (en) | Risk assessment method, device, equipment and storage medium based on artificial intelligence | |
| CN113723525B (en) | Product recommendation method, device, equipment and storage medium based on genetic algorithm | |
| CN116245630A (en) | Anti-fraud detection method and device, electronic equipment and medium | |
| CN114493853A (en) | Credit rating evaluation method, credit rating evaluation device, electronic device and storage medium | |
| CN113988223A (en) | Certificate image recognition method and device, computer equipment and storage medium | |
| CN117172632B (en) | Enterprise abnormal behavior detection method, device, equipment and storage medium | |
| US11645372B2 (en) | Multifactor handwritten signature verification | |
| CN117992925B (en) | Risk prediction method and device based on multi-source heterogeneous data and multi-mode data | |
| CN117912470A (en) | Voiceprint recognition method, voiceprint recognition device, computer equipment and storage medium | |
| CN117876137A (en) | Financial condition determining method and device and computing equipment | |
| CN116757851A (en) | Data configuration method, device, equipment and storage medium based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40016962 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |