CN114663223A - Credit risk assessment method, device and related equipment based on artificial intelligence - Google Patents
Credit risk assessment method, device and related equipment based on artificial intelligence Download PDFInfo
- Publication number
- CN114663223A CN114663223A CN202210367992.6A CN202210367992A CN114663223A CN 114663223 A CN114663223 A CN 114663223A CN 202210367992 A CN202210367992 A CN 202210367992A CN 114663223 A CN114663223 A CN 114663223A
- Authority
- CN
- China
- Prior art keywords
- credit risk
- training sample
- index
- enterprise
- sample set
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, and provides a credit risk assessment method, a credit risk assessment device and related equipment based on artificial intelligence, wherein the method comprises the following steps: determining a first credit risk level for each business based on the metrics for each business; performing first class labeling on the initialized training sample set to obtain a first target training sample set; performing first preprocessing on the first target training sample set to obtain a second target training sample set; training a preset neural network model based on a second target training sample set to obtain a credit risk assessment model; and inputting the target data set into a credit risk assessment model to obtain a credit risk assessment result. According to the method, the second target training sample set obtained by performing the first pretreatment on the first target training sample set is adopted to train the credit risk assessment model, so that the accuracy of the credit risk assessment model is improved, and the accuracy of a credit risk prediction result is improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a credit risk assessment method and device based on artificial intelligence and related equipment.
Background
Currently, some financial institutions use machine learning or deep learning methods to perform credit risk assessment when enterprises perform credit risk assessment.
However, since a large amount of labeled data is needed for machine learning or deep learning, enterprises cannot provide a large amount of labeled credit risk data, and if millions of credit risk data are labeled manually, efficiency is low, and thus accuracy of credit risk assessment is low.
Disclosure of Invention
In view of the above, there is a need for a credit risk assessment method, apparatus and related device based on artificial intelligence, in which a second target training sample set obtained by performing a first preprocessing on a first target training sample set is used to train a credit risk assessment model, so that the accuracy of the credit risk assessment model is improved, and the accuracy of a credit risk prediction result is improved.
A first aspect of the present invention provides a credit risk assessment method based on artificial intelligence, the method comprising:
analyzing the obtained training sample set to obtain enterprises and indexes of each enterprise;
determining a first credit risk level for each of the businesses based on the metrics for each of the businesses;
initializing the training sample set, and performing first class marking on the initialized training sample set according to the first credit risk level of each enterprise to obtain a first target training sample set;
performing first preprocessing on the first target training sample set to obtain a second target training sample set;
training a preset neural network model based on the second target training sample set to obtain a credit risk assessment model;
and when a credit risk assessment request of the enterprise to be assessed is received, carrying out second preprocessing on the credit risk assessment request of the enterprise to be assessed to obtain a target data set, and inputting the target data set into the credit risk assessment model to obtain a credit risk assessment result of the enterprise to be assessed.
Optionally, the determining a first credit risk level for each of the businesses based on the metrics for each of the businesses comprises:
identifying a label of the index of each enterprise, and dividing the index of each enterprise into a first-level index data set, a second-level index data set and a third-level index data set according to the label;
calculating an enterprise credit risk value for each of the enterprises based on the primary index dataset, the secondary index dataset, and the tertiary index dataset;
and determining a first credit risk level of each enterprise according to the calculated enterprise credit risk value of each enterprise.
Optionally, the calculating an enterprise credit risk value for each of the enterprises based on the primary index dataset, the secondary index dataset, and the tertiary index dataset comprises:
acquiring the credit score of each primary index of each enterprise, the credit score of each secondary index corresponding to each primary index, and the credit score and the weight value of each tertiary index corresponding to each secondary index from a preset database;
and calculating the sum of the credit value of each primary index, the credit value of each secondary index corresponding to each primary index and the product of the credit value of each tertiary index corresponding to each secondary index and the weight value to obtain the credit risk value of each enterprise.
Optionally, the initializing the training sample set comprises:
obtaining a plurality of three-level indexes in the training sample set;
identifying whether the index value of each tertiary index meets the normalization requirement;
according to a preset normalization processing rule, performing normalization processing on the index value of each three-level index meeting the normalization processing to obtain a new index value of each three-level index;
and updating the training sample set based on the new index value of each three-level index to obtain an initialized training sample set.
Optionally, the performing a first preprocessing on the first target training sample set to obtain a second target training sample set includes:
inputting the first target training sample set into a pre-trained LGBT model to obtain a weight factor set;
dividing the weight factor set into a strong factor set and a weak factor set according to a preset weight threshold;
randomly acquiring a plurality of combined sample sets from the strong factor set and the weak factor set according to a preset acquisition proportion by adopting a resampling method;
clustering the plurality of combined sample sets to obtain an optimal weight factor set;
and performing second class labeling on the initialized training sample set based on the optimal weight factor set to obtain a second target training sample set.
Optionally, the performing a second class labeling on the initialized training sample set based on the optimal weight factor set to obtain a second target training sample set includes:
acquiring a target training sample set of each enterprise according to the optimal weight factor set;
dividing a target training sample set of each enterprise into a plurality of cluster classes;
calculating the average value of the credit risk values of all the training samples of each cluster class to obtain the credit risk value of each cluster class;
calculating an average value of a plurality of credit risk values of the plurality of groups to obtain a cluster credit risk value of each enterprise;
determining a second credit risk level of each enterprise according to the calculated cluster credit risk value of each enterprise;
and performing second category labeling on the initialized training sample set according to the second credit risk level of each enterprise to obtain a second target training sample set.
Optionally, the calculating an average value of the credit risk values of all training samples of each cluster class, and obtaining the credit risk value of each cluster class includes:
obtaining the credit score of each primary index, the credit score of each secondary index corresponding to each primary index, and the credit score and the weight value of each tertiary index corresponding to each secondary index of each training sample of each family from a preset database;
calculating the sum of the credit value of each primary index, the credit value of each secondary index corresponding to each primary index and the product of the credit value of each tertiary index corresponding to each secondary index and the weight value to obtain the credit risk value of each training sample of each cluster;
and determining the average value of the credit risk values of all the training samples of each cluster class as the credit risk value of each cluster class.
A second aspect of the invention provides an artificial intelligence based credit risk assessment apparatus, the apparatus comprising:
the analysis and acquisition module is used for analyzing the acquired training sample set to acquire enterprises and indexes of each enterprise;
a determination module to determine a first credit risk level for each of the businesses based on the metrics for each of the businesses;
the marking module is used for initializing the training sample set and carrying out primary category marking on the initialized training sample set according to the first credit risk level of each enterprise to obtain a first target training sample set;
the first preprocessing module is used for performing first preprocessing on the first target training sample set to obtain a second target training sample set;
the training module is used for training a preset neural network model based on the second target training sample set to obtain a credit risk assessment model;
and the second preprocessing module is used for performing second preprocessing on the credit risk assessment request of the enterprise to be assessed to obtain a target data set when the credit risk assessment request of the enterprise to be assessed is received, and inputting the target data set into the credit risk assessment model to obtain a credit risk assessment result of the enterprise to be assessed.
A third aspect of the invention provides an electronic device comprising a processor and a memory, the processor being configured to implement the artificial intelligence based credit risk assessment method when executing a computer program stored in the memory.
A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the artificial intelligence based credit risk assessment method.
In summary, the artificial intelligence based credit risk assessment method, apparatus and related device of the present invention, by initializing the training sample set, increase the convergence rate of the subsequent models, and performing a first class labeling on the initialized training sample set according to a first credit risk level of each enterprise, perform a first preprocessing on the obtained first target training sample set to obtain a second target training sample set, break through a fixed mode of expert scoring, determine the second target training sample set according to an optimal weight factor set obtained by the first preprocessing, extract an optimal weight factor labeled training sample, increase the accuracy of the second target training sample set, train a preset neural network model based on the second target training sample set to obtain a credit risk assessment model, and predict the credit risk of the enterprise to be assessed by using the credit risk assessment model, the accuracy of the credit risk prediction result of the enterprise is improved.
Drawings
Fig. 1 is a flowchart of a credit risk assessment method based on artificial intelligence according to an embodiment of the present invention.
Fig. 2 is a block diagram of a credit risk assessment apparatus based on artificial intelligence according to a second embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a detailed description of the present invention will be given below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and features of the embodiments may be combined with each other without conflict.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
Example one
Fig. 1 is a flowchart of a credit risk assessment method based on artificial intelligence according to an embodiment of the present invention.
In this embodiment, the credit risk assessment method based on artificial intelligence may be applied to an electronic device, and for an electronic device that needs to perform the credit risk assessment method based on artificial intelligence, the functions of the credit risk assessment method based on artificial intelligence provided by the method of the present invention may be directly integrated on the electronic device, or may be run in the electronic device in the form of a Software Development Kit (SDK).
The embodiment of the invention can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning, deep learning and the like.
As shown in FIG. 1, the credit risk assessment method based on artificial intelligence specifically includes the following steps, and the sequence of the steps in the flowchart can be changed and some steps can be omitted according to different requirements.
And S11, analyzing the obtained training sample set to obtain the enterprises and the indexes of each enterprise.
In this embodiment, when performing enterprise credit risk assessment, a training sample set of an enterprise is obtained from a system of the enterprise or a third-party platform connected to the enterprise system, and the training sample set is analyzed to obtain an index of each enterprise, where the index includes a primary index, a secondary index, and a tertiary index of each enterprise, each primary index corresponds to at least one secondary index, and each secondary index corresponds to at least one tertiary index, for example, enterprise a, the primary index: enterprise basic attribute information and enterprise dynamic information; the second-level indexes corresponding to the first-level index enterprise basic attribute information are as follows: enterprise size, enterprise age, and enterprise background; and the enterprise model of the second-level indexes corresponds to the third-level indexes: registered capital, corporate shareholder numbers, outinvesting enterprise numbers, and branch numbers.
S12, a first credit risk level for each of the businesses is determined based on the metrics for each of the businesses.
In this embodiment, the first credit risk level may include four categories, a (no risk), B (low risk), C (medium risk), and D (high risk).
In an alternative embodiment, the determining a first credit risk level for each of the businesses based on the metrics for each of the businesses comprises:
identifying a label of the index of each enterprise, and dividing the index of each enterprise into a first-level index data set, a second-level index data set and a third-level index data set according to the label;
calculating an enterprise credit risk value for each of the enterprises based on the primary index dataset, the secondary index dataset, and the tertiary index dataset;
and determining a first credit risk level of each enterprise according to the calculated enterprise credit risk value of each enterprise.
In this embodiment, when determining the credit risk level of an enterprise, a database may be created in advance, where the credit score of the primary index and the primary index of each enterprise, the credit score of each secondary index and the secondary index corresponding to the primary index, the credit score of the tertiary index and the tertiary index corresponding to each secondary index, and the weight value of each tertiary index are stored in the database.
In this embodiment, the first credit risk level of each enterprise is determined by comparing the calculated enterprise credit risk value with a preset credit risk level threshold.
Further, the calculating an enterprise credit risk value for each of the enterprises based on the primary, secondary, and tertiary index datasets includes:
acquiring the credit score of each primary index of each enterprise, the credit score of each secondary index corresponding to each primary index, and the credit score and the weight value of each tertiary index corresponding to each secondary index from a preset database;
and calculating the sum of the credit value of each primary index, the credit value of each secondary index corresponding to each primary index and the product of the credit value of each tertiary index corresponding to each secondary index and the weight value to obtain the credit risk value of each enterprise.
In this embodiment, a database may be created in advance, in which the credit score of the primary index and the primary index of each enterprise, the credit score of each secondary index and the secondary index corresponding to the primary index, the credit score of each tertiary index and the tertiary index corresponding to each secondary index, and the weight value of each tertiary index are stored, where the credit score is obtained by the expert according to the historical experience.
In the embodiment, in the process of calculating the credit risk value of the enterprise, the influence weight values of the first-level index, the second-level index, the third-level index and the third-level index on the risk prediction evaluation result are comprehensively considered, so that the calculated credit risk value is more accurate.
S13, initializing the training sample set, and performing first class labeling on the initialized training sample set according to the first credit risk level of each enterprise to obtain a first target training sample set.
In this embodiment, in order to improve the convergence speed of a subsequent model, a training sample set is initialized, specifically, the initialization is to normalize an index value of a third index that needs to be normalized in the training sample set, where the model may include an LGBT model and a preset neural network model.
In this embodiment, the first category labeling is to label the category of each enterprise, and if the first credit risk level of the enterprise is risk-free, the risk-free identifier a is determined as the category of the enterprise.
In this embodiment, the first target training sample set includes the third index of each business, the index value of the third index, and the category of each business.
In an optional embodiment, the initializing the training sample set comprises:
obtaining a plurality of three-level indexes in the training sample set;
identifying whether the index value of each tertiary index meets the normalization requirement;
according to a preset normalization processing rule, performing normalization processing on the index value of each three-level index meeting the normalization processing to obtain a new index value of each three-level index;
and updating the training sample set based on the new index value of each three-level index to obtain an initialized training sample set.
In this embodiment, the initialization is to update the index value of each of the three-level indexes in the training sample set to a new normalized index value.
In an optional embodiment, the performing, for the first time, class labeling on the initialized training sample set according to the first credit risk level of each enterprise to obtain a first target training sample set includes:
and according to the first credit risk level of each enterprise, performing first category marking on the corresponding enterprise in the initialized training sample set by adopting a pre-marking model to obtain the initialized training sample set.
In this embodiment, in order to increase the labeling speed, a pre-labeling model may be used to perform the first category labeling on each enterprise in the initialization training set.
And S14, performing first preprocessing on the first target training sample set to obtain a second target training sample set.
In this embodiment, in order to break a fixed mode of expert scoring, a first preprocessing is performed on the first target training sample set, specifically, the first preprocessing adopts a resampling clustering method, the influence of strong factors and weak factors is comprehensively considered, the strong factors are emphasized, an optimal weight factor set is determined, a second target training sample set is determined according to the optimal weight factor set, the optimal weight factors are extracted to mark training samples, the accuracy of the second target training sample set is improved, and then a credit risk prediction result of an enterprise is improved.
In an optional embodiment, the performing the first preprocessing on the first target training sample set to obtain the second target training sample set includes:
inputting the first target training sample set into a pre-trained LGBT model to obtain a weight factor set;
dividing the weight factor set into a strong factor set and a weak factor set according to a preset weight threshold;
randomly acquiring a plurality of combined sample sets from the strong factor set and the weak factor set according to a preset acquisition proportion by adopting a resampling method;
clustering the plurality of combined sample sets to obtain an optimal weight factor set;
and performing second class labeling on the initialized training sample set based on the optimal weight factor set to obtain a second target training sample set.
In this embodiment, the LGBT model may be trained in advance, and when the first target training sample set is obtained, the first target training sample set is input into the pre-trained LGBT model, so as to obtain an influence weight of each third index on the classification result, and the weight factor set is divided into a strong factor set and a weak factor set by a preset weight threshold.
In this embodiment, the collection ratios of the strong factor and the weak factor may be preset, for example, the collection ratios of the strong factor and the weak factor are preset to be 8 to 2, and the strong factor and the weak factor are collected from the strong factor set and the weak factor set randomly according to the ratio of 8 to 2.
In this embodiment, the multiple combined sample sets are clustered, a quotient between an inter-class distance and an intra-class distance of each combined sample is calculated, and the combined sample set corresponding to the largest quotient is determined as the optimal weight factor set.
Further, the performing a second class labeling on the initialized training sample set based on the optimal weight factor set to obtain a second target training sample set includes:
acquiring a target training sample set of each enterprise according to the optimal weight factor set;
dividing a target training sample set of each enterprise into a plurality of cluster classes;
calculating the average value of the credit risk values of all the training samples of each cluster class to obtain the credit risk value of each cluster class;
calculating an average value of a plurality of credit risk values of the plurality of groups to obtain a cluster credit risk value of each enterprise;
determining a second credit risk level of each enterprise according to the calculated cluster credit risk value of each enterprise;
and performing second category labeling on the initialized training sample set according to the second credit risk level of each enterprise to obtain a second target training sample set.
In this embodiment, the target training sample set of each enterprise is obtained through the optimal weight factor set obtained through the first preprocessing, so that indexes of the training sample set of each enterprise are reduced, and further training efficiency of a subsequent credit risk assessment model is improved.
Further, the calculating an average value of the credit risk values of all training samples of each cluster class, and obtaining the credit risk value of each cluster class includes:
obtaining the credit score of each primary index, the credit score of each secondary index corresponding to each primary index, and the credit score and the weight value of each tertiary index corresponding to each secondary index of each training sample of each family from a preset database;
calculating the sum of the credit value of each primary index, the credit value of each secondary index corresponding to each primary index and the product of the credit value of each tertiary index corresponding to each secondary index and the weight value to obtain the credit risk value of each training sample of each cluster;
and determining the average value of the credit risk values of all the training samples of each cluster class as the credit risk value of each cluster class.
In the embodiment, in order to further improve the accuracy of enterprise risk prediction, the target training sample set is divided into a plurality of clusters, and the credit risk values of the plurality of clusters are calculated to obtain an average value, so that the accuracy of the credit risk values of the clusters of the enterprise is improved, and the accuracy of the category marking for the second time is improved.
And S15, training a preset neural network model based on the second target training sample set to obtain a credit risk assessment model.
In this embodiment, the preset neural network model may be an unsupervised neural network model, specifically, the unsupervised neural network model is the prior art, and details thereof are not described herein.
S16, when a credit risk assessment request of the enterprise to be assessed is received, carrying out second preprocessing on the credit risk assessment request of the enterprise to be assessed to obtain a target data set, and inputting the target data set into the credit risk assessment model to obtain a credit risk assessment result of the enterprise to be assessed.
In this embodiment, the second preprocessing refers to performing normalization processing on the three-level target indexes in the credit risk assessment request that require normalization processing.
In an optional embodiment, the second preprocessing is performed on the credit risk assessment request of the enterprise to be assessed, and obtaining the target data set includes:
analyzing the credit risk assessment request of the enterprise to be assessed to obtain a target index of the enterprise to be assessed;
obtaining a plurality of three-level target indexes from the target indexes;
identifying whether the index value of each three-level target index meets the normalization requirement;
according to a preset normalization processing rule, performing normalization processing on the index value of each three-level target index meeting the normalization processing to obtain a new index value of each three-level target index;
and updating the target indexes based on the new index values of each three-level target index to obtain a target data set.
In this embodiment, the credit risk assessment model is obtained by training through a second target training sample set, category labels in the second target training sample set are obtained by selecting an optimal weight factor set in order to overcome an inherent mode of expert scoring, and a credit risk assessment result of the enterprise to be assessed is obtained by inputting the target data set into the credit risk assessment model, so that accuracy of the credit risk assessment result is improved.
In summary, in the credit risk assessment method based on artificial intelligence according to this embodiment, the training sample set is initialized, the convergence rate of subsequent models is increased, the initialized training sample set is subjected to the first class labeling according to the first credit risk level of each enterprise, the obtained first target training sample set is subjected to the first preprocessing to obtain the second target training sample set, the fixed mode of expert scoring is broken through, the second target training sample set is determined according to the optimal weight factor set obtained by the first preprocessing, the optimal weight factor labeling training sample is extracted, the accuracy of the second target training sample set is improved, the preset neural network model is trained based on the second target training sample set to obtain the credit risk assessment model, and the credit risk assessment model is adopted to predict the credit risk of the enterprise to be assessed, the accuracy of the credit risk prediction result of the enterprise is improved.
Example two
Fig. 2 is a block diagram of a credit risk assessment apparatus based on artificial intelligence according to a second embodiment of the present invention.
In some embodiments, the credit risk assessment device 20 based on artificial intelligence may comprise a plurality of functional modules composed of program code segments. The program code of the various program segments of the artificial intelligence based credit risk assessment apparatus 20 may be stored in a memory of the electronic device and executed by the at least one processor to perform the functions of the artificial intelligence based credit risk assessment method (described in detail with reference to fig. 1).
In this embodiment, the credit risk assessment apparatus 20 based on artificial intelligence may be divided into a plurality of functional modules according to the functions performed by the apparatus. The functional module may include: the system comprises a parsing and obtaining module 201, a determining module 202, an annotation module 203, a first preprocessing module 204, a training module 205 and a second preprocessing module 206. The module referred to herein is a series of computer readable instruction segments stored in a memory that can be executed by at least one processor and that can perform a fixed function. In the present embodiment, the functions of the modules will be described in detail in the following embodiments.
And the analyzing and acquiring module 201 is configured to analyze the acquired training sample set to acquire the enterprises and the indexes of each enterprise.
In this embodiment, when performing enterprise credit risk assessment, a training sample set of an enterprise is obtained from a system of the enterprise or a third-party platform connected to the enterprise system, and the training sample set is analyzed to obtain the enterprise and each index of the enterprise, where the index includes a primary index, a secondary index, and a tertiary index of each enterprise, each primary index corresponds to at least one secondary index, and each secondary index corresponds to at least one tertiary index, for example, enterprise a, the primary index: enterprise basic attribute information and enterprise dynamic information; the second-level indexes corresponding to the first-level index enterprise basic attribute information are as follows: enterprise size, enterprise age, and enterprise background; and the enterprise model of the second-level indexes corresponds to the third-level indexes: registered capital, corporate shareholder numbers, outinvesting enterprise numbers, and branch numbers.
A determination module 202 for determining a first credit risk level for each of the businesses based on the metrics for each of the businesses.
In this embodiment, the first credit risk level may include four categories, a (no risk), B (low risk), C (medium risk), and D (high risk).
In an alternative embodiment, the determining module 202 determines the first credit risk level for each of the businesses based on the metrics for each of the businesses comprises:
identifying a label of the index of each enterprise, and dividing the index of each enterprise into a first-level index data set, a second-level index data set and a third-level index data set according to the label;
calculating an enterprise credit risk value for each of the enterprises based on the primary index dataset, the secondary index dataset, and the tertiary index dataset;
and determining a first credit risk level of each enterprise according to the calculated enterprise credit risk value of each enterprise.
In this embodiment, when determining the credit risk level of an enterprise, a database may be created in advance, where the credit values of the first-level index and the first-level index of each enterprise, the credit values of each second-level index and the second-level index corresponding to the first-level index, the credit values of the third-level index and the third-level index corresponding to each second-level index, and the weight values of each third-level index are stored in the database.
In this embodiment, the first credit risk level of each enterprise is determined by comparing the calculated enterprise credit risk value with a preset credit risk level threshold.
Further, the calculating an enterprise credit risk value for each of the enterprises based on the primary, secondary, and tertiary index datasets includes:
acquiring the credit score of each primary index of each enterprise, the credit score of each secondary index corresponding to each primary index, and the credit score and the weight value of each tertiary index corresponding to each secondary index from a preset database;
and calculating the sum of the credit value of each primary index, the credit value of each secondary index corresponding to each primary index and the product of the credit value of each tertiary index corresponding to each secondary index and the weight value to obtain the credit risk value of each enterprise.
In this embodiment, a database may be created in advance, in which the credit score of the primary index and the primary index of each enterprise, the credit score of each secondary index and the secondary index corresponding to the primary index, the credit score of each tertiary index and the tertiary index corresponding to each secondary index, and the weight value of each tertiary index are stored, where the credit score is obtained by the expert according to the historical experience.
In the embodiment, in the process of calculating the credit risk value of the enterprise, the influence weight values of the primary index, the secondary index, the tertiary index and the tertiary index on the risk prediction evaluation result are comprehensively considered, so that the calculated credit risk value is more accurate.
And the labeling module 203 is configured to initialize the training sample set, and perform a first class labeling on the initialized training sample set according to the first credit risk level of each enterprise to obtain a first target training sample set.
In this embodiment, in order to improve the convergence speed of a subsequent model, a training sample set is initialized, specifically, the initialization is to normalize an index value of a third index that needs to be normalized in the training sample set, where the model may include an LGBT model and a preset neural network model.
In this embodiment, the first category labeling is to label the category of each enterprise, and if the first credit risk level of the enterprise is risk-free, the risk-free identifier a is determined as the category of the enterprise.
In this embodiment, the first target training sample set includes the third index of each business, the index value of the third index, and the category of each business.
In an alternative embodiment, the labeling module 203 initializes the training sample set including:
obtaining a plurality of three-level indexes in the training sample set;
identifying whether the index value of each tertiary index meets the normalization requirement;
according to a preset normalization processing rule, performing normalization processing on the index value of each three-level index meeting the normalization processing to obtain a new index value of each three-level index;
and updating the training sample set based on the new index value of each three-level index to obtain an initialized training sample set.
In this embodiment, the initialization is to update the index value of each of the three-level indexes in the training sample set to a new normalized index value.
In an optional embodiment, the labeling module 203 performs a first class labeling on the initialized training sample set according to the first credit risk level of each of the enterprises, and obtaining a first target training sample set includes:
and according to the first credit risk level of each enterprise, carrying out first class marking on the corresponding enterprise in the initialized training sample set by adopting a pre-marking model to obtain the initialized training sample set.
In this embodiment, in order to increase the labeling speed, a pre-labeling model may be used to perform the first category labeling on each enterprise in the initialization training set.
The first preprocessing module 204 performs first preprocessing on the first target training sample set to obtain a second target training sample set.
In this embodiment, in order to break a fixed mode of expert scoring, a first preprocessing is performed on the first target training sample set, specifically, the first preprocessing adopts a resampling clustering method, the influence of strong factors and weak factors is comprehensively considered, the strong factors are emphasized, an optimal weight factor set is determined, a second target training sample set is determined according to the optimal weight factor set, the optimal weight factors are extracted to mark training samples, the accuracy of the second target training sample set is improved, and then a credit risk prediction result of an enterprise is improved.
In an optional embodiment, the first preprocessing module 204 performs the first preprocessing on the first target training sample set to obtain the second target training sample set, including:
inputting the first target training sample set into a pre-trained LGBT model to obtain a weight factor set;
dividing the weight factor set into a strong factor set and a weak factor set according to a preset weight threshold;
randomly acquiring a plurality of combined sample sets from the strong factor set and the weak factor set according to a preset acquisition proportion by adopting a resampling method;
clustering the plurality of combined sample sets to obtain an optimal weight factor set;
and performing second class labeling on the initialized training sample set based on the optimal weight factor set to obtain a second target training sample set.
In this embodiment, the LGBT model may be trained in advance, and when the first target training sample set is obtained, the first target training sample set is input into the pre-trained LGBT model, so as to obtain an influence weight of each third index on the classification result, and the weight factor set is divided into a strong factor set and a weak factor set by a preset weight threshold.
In this embodiment, the collection ratios of the strong factor and the weak factor may be preset, for example, the collection ratios of the strong factor and the weak factor are preset to be 8 to 2, and the strong factor and the weak factor are collected from the strong factor set and the weak factor set randomly according to the ratio of 8 to 2.
In this embodiment, the multiple combined sample sets are clustered, a quotient between the inter-class distance and the intra-class distance of each combined sample is calculated, and the combined sample set corresponding to the largest quotient is determined as the optimal weight factor set.
Further, the performing a second class labeling on the initialized training sample set based on the optimal weight factor set to obtain a second target training sample set includes:
acquiring a target training sample set of each enterprise according to the optimal weight factor set;
dividing a target training sample set of each enterprise into a plurality of cluster classes;
calculating the average value of the credit risk values of all the training samples of each cluster class to obtain the credit risk value of each cluster class;
calculating an average value of a plurality of credit risk values of the plurality of groups to obtain a cluster credit risk value of each enterprise;
determining a second credit risk level of each enterprise according to the calculated cluster credit risk value of each enterprise;
and performing second category labeling on the initialized training sample set according to the second credit risk level of each enterprise to obtain a second target training sample set.
In this embodiment, the target training sample set of each enterprise is obtained through the optimal weight factor set obtained through the first preprocessing, so that indexes of the training sample set of each enterprise are reduced, and further training efficiency of a subsequent credit risk assessment model is improved.
Further, the calculating an average value of the credit risk values of all training samples of each cluster class, and obtaining the credit risk value of each cluster class includes:
obtaining the credit score of each primary index, the credit score of each secondary index corresponding to each primary index, and the credit score and the weight value of each tertiary index corresponding to each secondary index of each training sample of each family from a preset database;
calculating the sum of the credit value of each primary index, the credit value of each secondary index corresponding to each primary index and the product of the credit value of each tertiary index corresponding to each secondary index and the weight value to obtain the credit risk value of each training sample of each cluster;
and determining the average value of the credit risk values of all the training samples of each cluster class as the credit risk value of each cluster class.
In the embodiment, in order to further improve the accuracy of enterprise risk prediction, the target training sample set is divided into a plurality of clusters, and the credit risk values of the plurality of clusters are calculated to obtain an average value, so that the accuracy of the credit risk values of the clusters of the enterprise is improved, and the accuracy of the category marking for the second time is improved.
A training module 205, configured to train a preset neural network model based on the second target training sample set to obtain a credit risk assessment model.
In this embodiment, the preset neural network model may be an unsupervised neural network model, specifically, the unsupervised neural network model is the prior art, and details thereof are not described herein.
The second preprocessing module 206 is configured to, when a credit risk assessment request of an enterprise to be assessed is received, perform second preprocessing on the credit risk assessment request of the enterprise to be assessed to obtain a target data set, and input the target data set into the credit risk assessment model to obtain a credit risk assessment result of the enterprise to be assessed.
In this embodiment, the second preprocessing refers to performing normalization processing on the three-level target indexes in the credit risk assessment request that require normalization processing.
In an optional embodiment, the second preprocessing module 206 performs second preprocessing on the credit risk assessment request of the enterprise to be assessed to obtain the target data set, including:
analyzing the credit risk assessment request of the enterprise to be assessed to obtain a target index of the enterprise to be assessed;
obtaining a plurality of three-level target indexes from the target indexes;
identifying whether the index value of each three-level target index meets the normalization requirement;
according to a preset normalization processing rule, performing normalization processing on the index value of each three-level target index meeting the normalization processing to obtain a new index value of each three-level target index;
and updating the target indexes based on the new index values of each three-level target index to obtain a target data set.
In this embodiment, the credit risk assessment model is obtained by training through a second target training sample set, category labels in the second target training sample set are obtained by selecting an optimal weight factor set in order to overcome an inherent mode of expert scoring, and a credit risk assessment result of the enterprise to be assessed is obtained by inputting the target data set into the credit risk assessment model, so that accuracy of the credit risk assessment result is improved.
In summary, in the credit risk assessment apparatus based on artificial intelligence according to this embodiment, the training sample set is initialized, the convergence rate of subsequent models is increased, the initialized training sample set is subjected to the first category labeling according to the first credit risk level of each enterprise, the obtained first target training sample set is subjected to the first preprocessing to obtain the second target training sample set, the fixed mode of expert scoring is broken through, the second target training sample set is determined according to the optimal weight factor set obtained by the first preprocessing, the optimal weight factor labeling training sample is extracted, the accuracy of the second target training sample set is improved, the preset neural network model is trained based on the second target training sample set to obtain the credit risk assessment model, and the credit risk assessment model is used to predict the credit risk of the enterprise to be assessed, the accuracy of the credit risk prediction result of the enterprise is improved.
EXAMPLE III
Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention. In the preferred embodiment of the present invention, the electronic device 3 comprises a memory 31, at least one processor 32, at least one communication bus 33 and a transceiver 34.
It will be appreciated by those skilled in the art that the configuration of the electronic device shown in fig. 3 does not constitute a limitation of the embodiment of the present invention, and may be a bus-type configuration or a star-type configuration, and the electronic device 3 may include more or less hardware or software than those shown in the figures, or different component arrangements.
In some embodiments, the electronic device 3 is an electronic device capable of automatically performing numerical calculation and/or information processing according to instructions set or stored in advance, and the hardware thereof includes but is not limited to a microprocessor, an application specific integrated circuit, a programmable gate array, a digital processor, an embedded device, and the like. The electronic device 3 may also include a client device, which includes, but is not limited to, any electronic product that can interact with a client through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device, for example, a personal computer, a tablet computer, a smart phone, a digital camera, and the like.
It should be noted that the electronic device 3 is only an example, and other existing or future electronic products, such as those that can be adapted to the present invention, should also be included in the scope of the present invention, and are included herein by reference.
In some embodiments, the memory 31 is used for storing program codes and various data, such as the credit risk assessment device 20 based on artificial intelligence installed in the electronic equipment 3, and realizes high-speed and automatic access to programs or data during the operation of the electronic equipment 3. The Memory 31 includes a Read-Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an electronically Erasable rewritable Read-Only Memory (Electrically-Erasable Programmable Read-Only Memory (EEPROM)), an optical Read-Only disk (CD-ROM) or other optical disk Memory, a magnetic disk Memory, a tape Memory, or any other medium readable by a computer capable of carrying or storing data.
In some embodiments, the at least one processor 32 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The at least one processor 32 is a Control Unit (Control Unit) of the electronic device 3, connects various components of the electronic device 3 by using various interfaces and lines, and executes various functions and processes data of the electronic device 3 by running or executing programs or modules stored in the memory 31 and calling data stored in the memory 31.
In some embodiments, the at least one communication bus 33 is arranged to enable connection communication between the memory 31 and the at least one processor 32 or the like.
Although not shown, the electronic device 3 may further include a power supply (such as a battery) for supplying power to each component, and optionally, the power supply may be logically connected to the at least one processor 32 through a power management device, so as to implement functions of managing charging, discharging, and power consumption through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 3 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
It is to be understood that the embodiments described are illustrative only and are not to be construed as limiting the scope of the claims.
The integrated unit implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, an electronic device, or a network device) or a processor (processor) to execute parts of the methods according to the embodiments of the present invention.
In a further embodiment, in conjunction with fig. 2, the at least one processor 32 may execute operating means of the electronic device 3 and various installed applications (such as the artificial intelligence based credit risk assessment apparatus 20), program code, and the like, such as the various modules described above.
The memory 31 has program code stored therein, and the at least one processor 32 can call the program code stored in the memory 31 to perform related functions. For example, the modules illustrated in fig. 2 are program codes stored in the memory 31 and executed by the at least one processor 32, so as to implement the functions of the modules for the purpose of the credit risk assessment method based on artificial intelligence.
Illustratively, the program code may be partitioned into one or more modules/units that are stored in the memory 31 and executed by the processor 32 to accomplish the present application. The one or more modules/units may be a series of computer readable instruction segments capable of performing certain functions, which are used for describing the execution process of the program code in the electronic device 3. For example, the program code may be partitioned into a parsing and acquisition module 201, a determination module 202, an annotation module 203, a first pre-processing module 204, a training module 205, and a second pre-processing module 206.
In one embodiment of the present invention, the memory 31 stores a plurality of computer-readable instructions that are executed by the at least one processor 32 to implement the functionality of the artificial intelligence based credit risk assessment method.
Specifically, the at least one processor 32 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, and details are not repeated here.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or that the singular does not exclude the plural. A plurality of units or means recited in the present invention may also be implemented by one unit or means through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A credit risk assessment method based on artificial intelligence, the method comprising:
analyzing the obtained training sample set to obtain enterprises and indexes of each enterprise;
determining a first credit risk level for each of the businesses based on the metrics for each of the businesses;
initializing the training sample set, and performing first class marking on the initialized training sample set according to the first credit risk level of each enterprise to obtain a first target training sample set;
performing first preprocessing on the first target training sample set to obtain a second target training sample set;
training a preset neural network model based on the second target training sample set to obtain a credit risk assessment model;
and when a credit risk assessment request of the enterprise to be assessed is received, carrying out second preprocessing on the credit risk assessment request of the enterprise to be assessed to obtain a target data set, and inputting the target data set into the credit risk assessment model to obtain a credit risk assessment result of the enterprise to be assessed.
2. The artificial intelligence-based credit risk assessment method of claim 1, wherein said determining a first credit risk level for each of said businesses based on said metrics for each of said businesses comprises:
identifying a label of the index of each enterprise, and dividing the index of each enterprise into a first-level index data set, a second-level index data set and a third-level index data set according to the label;
calculating an enterprise credit risk value for each of the enterprises based on the primary index dataset, the secondary index dataset, and the tertiary index dataset;
and determining a first credit risk level of each enterprise according to the calculated enterprise credit risk value of each enterprise.
3. The artificial intelligence-based credit risk assessment method of claim 2, wherein said calculating an enterprise credit risk value for each of said enterprises based on said primary, secondary and tertiary index datasets comprises:
acquiring the credit score of each primary index of each enterprise, the credit score of each secondary index corresponding to each primary index, and the credit score and the weight value of each tertiary index corresponding to each secondary index from a preset database;
and calculating the sum of the credit value of each primary index, the credit value of each secondary index corresponding to each primary index and the product of the credit value of each tertiary index corresponding to each secondary index and the weight value to obtain the credit risk value of each enterprise.
4. The artificial intelligence-based credit risk assessment method of claim 1, wherein said initializing the training sample set comprises:
obtaining a plurality of three-level indexes in the training sample set;
identifying whether the index value of each three-level index meets the normalization requirement;
according to a preset normalization processing rule, performing normalization processing on the index value of each three-level index meeting the normalization processing to obtain a new index value of each three-level index;
and updating the training sample set based on the new index value of each three-level index to obtain an initialized training sample set.
5. The artificial intelligence-based credit risk assessment method of claim 1, wherein said first preprocessing the first set of target training samples to obtain a second set of target training samples comprises:
inputting the first target training sample set into a pre-trained LGBT model to obtain a weight factor set;
dividing the weight factor set into a strong factor set and a weak factor set according to a preset weight threshold;
randomly acquiring a plurality of combined sample sets from the strong factor set and the weak factor set according to a preset acquisition proportion by adopting a resampling method;
clustering the plurality of combined sample sets to obtain an optimal weight factor set;
and performing second class labeling on the initialized training sample set based on the optimal weight factor set to obtain a second target training sample set.
6. The artificial intelligence-based credit risk assessment method according to claim 5, wherein said performing a second class labeling on the initialized training sample set based on the optimal weight factor set to obtain a second target training sample set comprises:
acquiring a target training sample set of each enterprise according to the optimal weight factor set;
dividing a target training sample set of each enterprise into a plurality of cluster classes;
calculating the average value of the credit risk values of all the training samples of each cluster class to obtain the credit risk value of each cluster class;
calculating an average value of a plurality of credit risk values of the plurality of groups to obtain a cluster credit risk value of each enterprise;
determining a second credit risk level of each enterprise according to the calculated cluster credit risk value of each enterprise;
and performing second category labeling on the initialized training sample set according to the second credit risk level of each enterprise to obtain a second target training sample set.
7. The artificial intelligence based credit risk assessment method of claim 6, wherein said calculating an average of the credit risk values of all training samples of each of said clusters, obtaining the credit risk value of each of said clusters comprises:
obtaining the credit score of each primary index, the credit score of each secondary index corresponding to each primary index, and the credit score and the weight value of each tertiary index corresponding to each secondary index of each training sample of each family from a preset database;
calculating the sum of the credit value of each primary index, the credit value of each secondary index corresponding to each primary index and the product of the credit value of each tertiary index corresponding to each secondary index and the weight value to obtain the credit risk value of each training sample of each cluster;
and determining the average value of the credit risk values of all the training samples of each cluster class as the credit risk value of each cluster class.
8. An artificial intelligence based credit risk assessment apparatus, the apparatus comprising:
the analysis and acquisition module is used for analyzing the acquired training sample set to acquire enterprises and indexes of each enterprise;
a determination module to determine a first credit risk level for each of the businesses based on the metrics for each of the businesses;
the marking module is used for initializing the training sample set and carrying out primary category marking on the initialized training sample set according to the first credit risk level of each enterprise to obtain a first target training sample set;
the first preprocessing module is used for performing first preprocessing on the first target training sample set to obtain a second target training sample set;
the training module is used for training a preset neural network model based on the second target training sample set to obtain a credit risk assessment model;
and the second preprocessing module is used for performing second preprocessing on the credit risk assessment request of the enterprise to be assessed to obtain a target data set when the credit risk assessment request of the enterprise to be assessed is received, and inputting the target data set into the credit risk assessment model to obtain a credit risk assessment result of the enterprise to be assessed.
9. An electronic device, characterized in that the electronic device comprises a processor and a memory, the processor being configured to implement the artificial intelligence based credit risk assessment method according to any one of claims 1 to 7 when executing a computer program stored in the memory.
10. A computer-readable storage medium, having stored thereon a computer program, which, when being executed by a processor, carries out the artificial intelligence based credit risk assessment method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210367992.6A CN114663223A (en) | 2022-04-08 | 2022-04-08 | Credit risk assessment method, device and related equipment based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210367992.6A CN114663223A (en) | 2022-04-08 | 2022-04-08 | Credit risk assessment method, device and related equipment based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114663223A true CN114663223A (en) | 2022-06-24 |
Family
ID=82036098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210367992.6A Pending CN114663223A (en) | 2022-04-08 | 2022-04-08 | Credit risk assessment method, device and related equipment based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114663223A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109131A (en) * | 2022-11-12 | 2023-05-12 | 珠海易立方软件有限公司 | Information system risk assessment method, system, medium and equipment |
| CN116805266A (en) * | 2023-08-25 | 2023-09-26 | 山东华创远智信息科技有限公司 | Enterprise financial credit risk intelligent assessment method based on big data |
| CN117556264A (en) * | 2024-01-11 | 2024-02-13 | 浙江同花顺智能科技有限公司 | Training method and device for evaluation model and electronic equipment |
| CN117573814A (en) * | 2024-01-17 | 2024-02-20 | 中电科大数据研究院有限公司 | Public opinion situation assessment method, device and system and storage medium |
-
2022
- 2022-04-08 CN CN202210367992.6A patent/CN114663223A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109131A (en) * | 2022-11-12 | 2023-05-12 | 珠海易立方软件有限公司 | Information system risk assessment method, system, medium and equipment |
| CN116805266A (en) * | 2023-08-25 | 2023-09-26 | 山东华创远智信息科技有限公司 | Enterprise financial credit risk intelligent assessment method based on big data |
| CN117556264A (en) * | 2024-01-11 | 2024-02-13 | 浙江同花顺智能科技有限公司 | Training method and device for evaluation model and electronic equipment |
| CN117556264B (en) * | 2024-01-11 | 2024-05-07 | 浙江同花顺智能科技有限公司 | Training method and device for evaluation model and electronic equipment |
| CN117573814A (en) * | 2024-01-17 | 2024-02-20 | 中电科大数据研究院有限公司 | Public opinion situation assessment method, device and system and storage medium |
| CN117573814B (en) * | 2024-01-17 | 2024-05-10 | 中电科大数据研究院有限公司 | Public opinion situation assessment method, device and system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114663223A (en) | Credit risk assessment method, device and related equipment based on artificial intelligence | |
| CN112183101A (en) | Text intention recognition method and device, electronic equipment and storage medium | |
| CN113435582B (en) | Text processing method and related equipment based on sentence vector pre-training model | |
| CN115146865A (en) | Task optimization method based on artificial intelligence and related equipment | |
| CN112614578A (en) | Doctor intelligent recommendation method and device, electronic equipment and storage medium | |
| CN113190372A (en) | Fault processing method and device for multi-source data, electronic equipment and storage medium | |
| CN113256108A (en) | Human resource allocation method, device, electronic equipment and storage medium | |
| CN113435998A (en) | Loan overdue prediction method and device, electronic equipment and storage medium | |
| CN114201328A (en) | Fault processing method and device based on artificial intelligence, electronic equipment and medium | |
| CN114880449A (en) | Reply generation method and device of intelligent question answering, electronic equipment and storage medium | |
| CN114201212A (en) | Configuration file processing method and device, computer equipment and storage medium | |
| CN114020892A (en) | Answer selection method and device based on artificial intelligence, electronic equipment and medium | |
| CN113792146A (en) | Text classification method and device based on artificial intelligence, electronic equipment and medium | |
| CN116108276A (en) | Information recommendation method and device based on artificial intelligence and related equipment | |
| CN113674065B (en) | Service contact-based service recommendation method and device, electronic equipment and medium | |
| CN113570286B (en) | Resource allocation method and device based on artificial intelligence, electronic equipment and medium | |
| CN114925674A (en) | File compliance checking method and device, electronic equipment and storage medium | |
| CN114881313A (en) | Behavior prediction method and device based on artificial intelligence and related equipment | |
| CN114968336A (en) | Application gray level publishing method and device, computer equipment and storage medium | |
| CN114817449A (en) | Text search ordering method and device based on artificial intelligence and related equipment | |
| CN115658858A (en) | Dialog recommendation method based on artificial intelligence and related equipment | |
| CN115146064A (en) | Intention recognition model optimization method, device, equipment and storage medium | |
| CN114742061A (en) | Text processing method and device, electronic equipment and storage medium | |
| CN114239538A (en) | Assertion processing method and device, computer equipment and storage medium | |
| CN113987351A (en) | Artificial intelligence based intelligent recommendation method and device, electronic equipment and 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 |