CN116342300B - Method, device and equipment for analyzing characteristics of insurance claim settlement personnel - Google Patents
Method, device and equipment for analyzing characteristics of insurance claim settlement personnel Download PDFInfo
- Publication number
- CN116342300B CN116342300B CN202310601138.6A CN202310601138A CN116342300B CN 116342300 B CN116342300 B CN 116342300B CN 202310601138 A CN202310601138 A CN 202310601138A CN 116342300 B CN116342300 B CN 116342300B
- Authority
- CN
- China
- Prior art keywords
- analysis
- insurance
- characteristic
- feature
- main body
- 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
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
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
Abstract
The invention provides a method, a device and equipment for analyzing characteristics of insurance claim settlement personnel, which relate to the technical field of data processing and comprise the following steps: obtaining a target insurance claim data set, including an insurance claim type identifier, obtaining a multi-stage claim personnel analysis dimension, including an insurance claim feature analysis main body and an insurance claim feature analysis auxiliary body, performing data mining, constructing a claim personnel feature distribution model, performing deep learning, building a first claim personnel feature analysis model, performing incremental learning, generating a second claim personnel feature analysis model, performing principal component analysis, obtaining a target insurance claim data set, inputting the second claim personnel feature analysis model, and obtaining a target insurance claim personnel feature analysis result. The invention solves the technical problems of poor accuracy and efficiency of a large-scale data set due to higher calculation complexity mainly based on statistical analysis and experience judgment in the traditional insurance claim settlement personnel feature analysis method.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method, a device and equipment for analyzing characteristics of insurance claim settlement personnel.
Background
The insurance claim is the action of paying the compensation or paying the responsibility according to the contract rule by the insurance company when the insurance accident happens and the property of the insured person is lost or the life of the person is damaged or other insurance accidents agreed by the insurance policy occur and the insurance price needs to be paid, and is the work of directly showing the insurance function and fulfilling the insurance responsibility, which is a very important ring in the insurance law system and is the main form of the insurer to fulfill the obligation. The traditional insurance claim settlement personnel feature analysis method mainly aims at solving the technical problems that the accuracy and the efficiency of a large-scale data set are poor due to high calculation complexity mainly based on statistical analysis and experience judgment.
Disclosure of Invention
The embodiment of the application provides an insurance claim settlement personnel feature analysis method, device and equipment, which are used for solving the technical problems that the traditional insurance claim settlement personnel feature analysis method is mainly based on statistical analysis and experience judgment, and has higher calculation complexity for a large-scale data set, so that the accuracy and efficiency are poor.
In view of the above problems, embodiments of the present application provide a method, an apparatus, and a device for analyzing characteristics of insurance claims.
In a first aspect, embodiments of the present application provide a method for analyzing characteristics of an insurance claim settlement person, the method including: obtaining a target insurance claim data set of a target user, wherein the target insurance claim data set comprises an insurance claim type identifier; obtaining a multi-stage claimant analysis dimension, wherein the multi-stage claimant analysis dimension comprises an insurance claimant feature analysis main body and an insurance claimant feature analysis auxiliary body; performing data mining based on the insurance claim type identifier and the multi-stage claim settlement personnel analysis dimension, and constructing a claim settlement personnel feature distribution model; deep learning is carried out based on the characteristic distribution model of the claim settlement personnel, and a first characteristic analysis model of the claim settlement personnel is built; performing incremental learning based on the first claim personnel feature analysis model to generate a second claim personnel feature analysis model; performing principal component analysis based on the target insurance claim data set to obtain a target insurance claim data set; and inputting the target insurance claim data set into the second claim settlement personnel feature analysis model to obtain a target insurance claim settlement personnel feature analysis result.
In a second aspect, embodiments of the present application provide an insurance claim personnel feature analysis apparatus, the apparatus including: the system comprises a target claim data acquisition module, a target claim data processing module and a target claim data processing module, wherein the target claim data acquisition module is used for acquiring a target insurance claim data set of a target user, and the target insurance claim data set comprises an insurance claim type identifier; the system comprises a multi-stage analysis dimension acquisition module, a storage module and a storage module, wherein the multi-stage analysis dimension acquisition module is used for acquiring multi-stage analysis dimensions of the claimant, wherein the multi-stage analysis dimensions of the claimant comprise an insurance claimant characteristic analysis main body and an insurance claimant characteristic analysis auxiliary body; the data mining module is used for carrying out data mining based on the insurance claim type identification and the multi-stage claim settlement personnel analysis dimension, and constructing a claim settlement personnel feature distribution model; the deep learning module is used for carrying out deep learning based on the characteristic distribution model of the claimant and building a characteristic analysis model of the first claimant; the incremental learning module is used for performing incremental learning based on the first claim personnel characteristic analysis model and generating a second claim personnel characteristic analysis model; the principal component analysis module is used for carrying out principal component analysis based on the target insurance claim data set to obtain the target insurance claim data set; and the analysis result acquisition module is used for inputting the target insurance claim data set into the second claim settlement personnel characteristic analysis model to obtain a target insurance claim settlement personnel characteristic analysis result.
In a third aspect, the present application further provides an electronic device, including: a memory for storing executable instructions; and the processor is used for realizing the insurance claim settlement personnel characteristic analysis method provided by the application when executing the executable instructions stored in the memory.
In a fourth aspect, the present application further provides a computer readable storage medium storing a computer program, which when executed by a processor, implements an insurance claim settlement personnel feature analysis method provided by the present application.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
obtaining a target insurance claim data set, including an insurance claim type identifier, obtaining a multi-stage claim personnel analysis dimension, including an insurance claim feature analysis main body and an insurance claim feature analysis auxiliary body, performing data mining, constructing a claim personnel feature distribution model, performing deep learning, building a first claim personnel feature analysis model, performing incremental learning, generating a second claim personnel feature analysis model, performing principal component analysis, obtaining a target insurance claim data set, inputting the second claim personnel feature analysis model, and obtaining a target insurance claim personnel feature analysis result. The method solves the technical problems of poor accuracy and efficiency of the traditional insurance claim settlement personnel feature analysis method which is mainly based on statistical analysis and experience judgment and has higher calculation complexity for a large-scale data set, realizes automatic learning and feature extraction, reduces the requirement of manual feature engineering, is further suitable for the feature analysis and prediction tasks of the large-scale data set, and achieves the technical effects of improving the feature representation capability and the prediction accuracy.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly described below. It is apparent that the figures in the following description relate only to some embodiments of the present disclosure and are not limiting of the present disclosure.
FIG. 1 is a schematic flow chart of a method for analyzing characteristics of an insurance claim settlement personnel according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a feature distribution model of an claimant obtained in an insurance claimant feature analysis method according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a device for analyzing characteristics of insurance claim settlement personnel according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an exemplary electronic device of the present application.
Reference numerals illustrate: the system comprises a target claim data acquisition module 10, a multi-stage analysis dimension acquisition module 20, a data mining module 30, a deep learning module 40, an incremental learning module 50, a principal component analysis module 60, an analysis result acquisition module 70, a processor 31, a memory 32, an input device 33 and an output device 34.
Detailed Description
According to the embodiment of the application, the technical problems of high calculation complexity and poor accuracy and efficiency of a large-scale data set are solved by providing the characteristic analysis method for the insurance claim settlement personnel, wherein the characteristic analysis method is mainly based on statistical analysis and experience judgment, the automatic learning and feature extraction are realized, the requirement of artificial characteristic engineering is reduced, the characteristic analysis and prediction tasks of the large-scale data set are further applicable, and the technical effects of improving the characteristic representation capability and the prediction precision are achieved.
Example 1
As shown in fig. 1, an embodiment of the present application provides a method for analyzing characteristics of an insurance claim settlement person, where the method includes:
step S100: obtaining a target insurance claim data set of a target user, wherein the target insurance claim data set comprises an insurance claim type identifier;
specifically, insurance claim data, including customer information, insurance product type, claim application time, claim amount, claim reason, etc., is collected from an internal system, external data source, or partner of the insurance company, while the data collection process ensures compliance with relevant regulations and protection of user privacy. And classifying the records based on the factors such as the reason of the claim, the amount of the claim, the time of the claim, and the like, and distributing an insurance claim type identifier to each claim record, for example, classifying the reason of the claim into the types such as traffic accidents, natural disasters, and the like, so as to better determine the characteristics of different types of claims in subsequent analysis.
Step S200: obtaining a multi-stage claimant analysis dimension, wherein the multi-stage claimant analysis dimension comprises an insurance claimant feature analysis main body and an insurance claimant feature analysis auxiliary body;
specifically, the multi-level claimant analysis dimension includes an insurance claimant feature analysis main body and an insurance claimant feature analysis auxiliary body, wherein the insurance claimant feature analysis main body refers to a person in an insurance accident, including an insured person, a third party victim, a driver and the like, and among the persons, the insured person is the main body in the main body, and has insurance compensation rights due to the fact that the insured person signs an insurance contract with an insurance company; the auxiliary body of the insurance claim feature analysis refers to articles in the insurance accident, including vehicles, property, goods and the like, and among the articles, the vehicles are the most common auxiliary bodies, because the vehicles are one of the most common damaged articles in the insurance accident and are also important objects for reimbursement of an insurance company.
After the principal and subordinate analysis of the insurance claim characteristics are determined, they are integrated into a multi-level analysis dimension framework that integrates relationships and weights between dimensions to provide a comprehensive view in subsequent analysis.
Step S300: performing data mining based on the insurance claim type identifier and the multi-stage claim settlement personnel analysis dimension, and constructing a claim settlement personnel feature distribution model;
further, as shown in fig. 2, step S300 of the present application further includes:
step S310: performing data mining based on the insurance claim type identifier and the insurance claim feature analysis main body to generate a main body feature distribution model of the claim settlement personnel;
further, step S310 of the present application further includes:
step S311: obtaining a plurality of groups of analysis records of the claim settlement main body with the same data volume based on the insurance claim settlement type identification and the insurance claim settlement characteristic analysis main body;
step S312: traversing the multiple groups of claim main analysis records to perform factor extraction to obtain multiple preparation main feature analysis factors;
step S313: traversing the plurality of preparation main body characteristic analysis factors to perform optimizing screening to obtain a plurality of winning main body characteristic analysis factors;
step S314: and generating the main body characteristic distribution model of the claimant based on the plurality of winning main body characteristic analysis factors.
Specifically, the target insurance claim data set is divided into different categories, such as traffic accidents, natural disasters, and the like, according to the insurance claim type identification. The same number of records are randomly extracted from each category to form a plurality of groups of claim main analysis records with the same data volume, so that the consistency and comparability of the data are ensured.
The main analysis records of each group of claim are processed by adopting a dimension reduction technology, such as a main component analysis method, a small number of preparation main characteristic analysis factors are extracted, the factors can effectively represent information in original characteristics, the calculation complexity is reduced, and the extracted preparation main characteristic analysis factors are interpreted so as to understand the meaning of the preparation main characteristic analysis factors in the original characteristic space. And traversing a plurality of groups of claim main analysis records to perform factor extraction, and obtaining a plurality of preparation main characteristic analysis factors.
By calculating indexes such as correlation and importance among the prepared main body characteristic analysis factors, the contribution of the prepared main body characteristic analysis factors in the aspect of representing the original characteristic information is evaluated, and the winning main body characteristic analysis factors with better performance are screened according to a preset evaluation index threshold, wherein the factors have higher interpretation ability and distinguishing ability, and can effectively represent the behaviors and characteristics of claimants in key characteristic dimensions.
Based on the machine learning method, a model describing the main body characteristic distribution of the claimant is constructed according to the screened winning main body characteristic analysis factors, so that the behavior and the characteristics of the claimant in the main characteristic dimension are definitely realized, and more information about the claimant process is provided for an insurance company.
Further, step S313 of the present application further includes:
step S3131: traversing the plurality of preparation main body characteristic analysis factors to perform lifting fitness analysis to obtain a plurality of factor lifting fitness;
step S3132: traversing the plurality of preparation main body characteristic analysis factors to perform insurance claim impact analysis to obtain a plurality of factor impact fitness;
specifically, a target variable, such as an amount of claim to be resolved, a length of claim to be resolved, etc., is obtained, the plurality of preliminary subject feature analysis factors are traversed, a pearson correlation coefficient between the preliminary subject feature analysis factors and the target variable is calculated to measure a linear relation between the factors and the target variable, the factors are ranked according to the absolute value of the correlation coefficient, and the ranked results are used as the lifting fitness of the factors to obtain a plurality of factor lifting fitness
Traversing the preliminary subject feature analysis factors, determining the importance of the features by constructing a predictive model and observing the change in model performance after removing a certain feature using a feature selection method, such as Recursive Feature Elimination (RFE), thereby evaluating the impact of each factor on the insurance claim process, ranking the factors according to the feature selection result, taking the ranked result as the impact fitness of the factors, and obtaining a plurality of factor impact fitness.
Step S3133: weighting fusion is carried out based on the multiple factor lifting fitness and the multiple factor influence fitness, so that multiple factor characteristic fitness is obtained;
step S3134: judging whether the plurality of factor characteristic fitness meets preset characteristic fitness or not, and obtaining a plurality of fitness judging results;
step S3135: and screening a plurality of preparation subject feature analysis factors based on the plurality of fitness judging results to obtain a plurality of winning subject feature analysis factors.
And carrying out normalization processing on the lifting fitness and the influence fitness to ensure that the values are between 0 and 1, distributing weights for the lifting fitness and the influence fitness according to service requirements and practical conditions, for example, the weights are respectively 0.6 and 0.4 of the lifting fitness, multiplying the normalized lifting fitness and the influence fitness by corresponding weights, and adding the weighted lifting fitness and the weighted influence fitness to obtain the comprehensive characteristic fitness.
Setting a feature fitness threshold according to service requirements and actual conditions, for example, setting the threshold to 0.7, traversing a plurality of factor feature fitness, judging whether the comprehensive feature fitness of each factor is greater than or equal to a preset threshold, if so, indicating that the feature fitness of the factor meets the preset feature fitness, and if not, indicating that the feature fitness of the factor does not meet the preset feature fitness, and obtaining a plurality of fitness judging results.
Traversing all the preparation main body characteristic analysis factors and the corresponding adaptability judgment results, if the adaptability judgment result of one preparation main body characteristic analysis factor meets the preset characteristic adaptability, adding the factor into a winning main body characteristic analysis factor list, and continuing traversing other preparation main body characteristic analysis factors until all the factors are screened, wherein the finally obtained winning main body characteristic analysis factor list is a plurality of required winning main body characteristic analysis factors.
Further, step S313 of the present application further includes:
step S3136: traversing the plurality of preliminary subject feature analysis factors to obtain a first preliminary subject feature analysis factor;
step S3137: based on the multiple groups of claim main body analysis records, carrying out support degree analysis on the first preparation main body characteristic analysis factors to obtain first factor support degree;
step S3138: traversing the plurality of preparation subject feature analysis factors to perform support degree analysis based on the plurality of groups of claim subject analysis records to obtain factor feature support degree;
step S3139: and carrying out lifting calculation based on the first factor support degree and the factor characteristic support degree to obtain a first factor lifting fitness, and adding the first factor lifting fitness to the plurality of factor lifting fitness.
Specifically, a plurality of preliminary main body feature analysis factors are traversed, one analysis factor is randomly selected as a first preliminary main body feature analysis factor, the number of times that the first preliminary main body feature analysis factor appears in a plurality of groups of claim main body analysis records is counted, the number of times that the feature factor appears is divided by the total number of the claim main body analysis records to obtain a support degree value which is used as a first factor support degree, so that the frequency of the feature factor appearing in the claim main body analysis records is measured, and the prevalence degree of the factor in the whole data set is clear.
Traversing the plurality of preparation main body feature analysis factors, calculating the sum of the occurrence times of the plurality of preparation main body feature analysis factors, and carrying out support degree analysis to obtain the factor feature support degree. And calculating the ratio between the first factor support degree and the factor characteristic support degree, and taking the ratio as the first factor to promote the fitness degree to represent the relative importance of the first factor. The boost fitness of the first factor is added to a list of multiple factor boost fitness values, and the preliminary subject feature analysis factors are evaluated and screened using the boost fitness values to identify optimal subject feature analysis factors.
Step S320: performing data mining on the basis of the insurance claim type identifier and the insurance claim feature analysis auxiliary body to generate a claim settlement personnel auxiliary body feature distribution model;
step S330: and obtaining the characteristic distribution model of the claimant based on the main characteristic distribution model of the claimant and the auxiliary characteristic distribution model of the claimant.
Specifically, the method exactly the same as step S310 is adopted to construct the auxiliary body feature distribution model of the claimant, and for brevity of the description, details are not repeated here. And integrating the main body characteristic distribution model of the claimant and the auxiliary body characteristic distribution model of the claimant to obtain the characteristic distribution model of the claimant.
Step S400: deep learning is carried out based on the characteristic distribution model of the claim settlement personnel, and a first characteristic analysis model of the claim settlement personnel is built;
further, step S400 of the present application further includes:
step S410: the claimant feature distribution model comprises a claimant main feature distribution model and a claimant auxiliary feature distribution model;
step S420: carrying out main body characteristic association analysis based on the main body characteristic distribution model of the claim settlement personnel to obtain main body characteristic association relation;
Step S430: performing auxiliary body characteristic association analysis based on the auxiliary body characteristic distribution model of the claim settlement personnel to obtain an auxiliary body characteristic association relation;
step S440: acquiring a binary feature association relationship based on the main feature association relationship and the auxiliary body feature association relationship;
step S450: obtaining a constructed data sequence based on the binary characteristic association relation;
step S460: based on the BP neural network, training is carried out according to the constructed data sequence, and the first claim settlement personnel characteristic analysis model is obtained.
Specifically, the claimant feature distribution model comprises a claimant main feature distribution model and a claimant auxiliary feature distribution model, wherein the claimant main feature distribution model pays attention to features related to people; the clan staff accessory feature distribution model focuses on features related to the vehicle.
And collecting data in the main body characteristic distribution model of the claimant, and preprocessing the data, including data cleaning, normalization, missing value processing and the like, so as to facilitate the performance of association analysis. And acquiring association rules among the features by searching frequent item sets by adopting an association analysis algorithm, such as an Apriori algorithm, so as to perform association analysis on main body features of the claimant, acquiring association relations among the main body features by calculating indexes such as supporting degree, confidence degree, lifting degree and the like, and finishing analysis results to obtain main body feature association relations, wherein the association relations are used for representing how core features in an insurance claimant process are mutually influenced, so that basis is provided for optimizing claimant flow and improving claimant efficiency.
The auxiliary body characteristic association relationship is obtained by adopting the same method, and is not repeated here for the sake of simplicity of the description.
And integrating the main body characteristic association relationship and the auxiliary body characteristic association relationship, further analyzing to find out an association rule between the main body characteristic and the auxiliary body characteristic, wherein an analysis result is a binary characteristic association relationship between the main body characteristic and the auxiliary body characteristic.
And generating an input data sequence and an output data sequence according to the characteristic association relation, wherein the input data sequence comprises main body characteristics and auxiliary body characteristics, and the output data sequence is a claim settlement result, such as claim settlement amount, claim settlement period and the like.
Dividing input and output data sequences into a training set and a testing set, initializing a BP neural network, acquiring a network structure, an activation function and a loss function, inputting training set data into the BP neural network, training the network, calculating a predicted value through forward propagation and updating weights and biases through backward propagation in the training process, and minimizing the loss function. And setting a certain iteration number, or stopping training when the loss function reaches a preset threshold value, and evaluating the performance of the model through a verification set, such as indexes of accuracy, recall rate and the like. After model training is completed, the model is applied to the feature analysis of insurance claims settlement personnel, and the result of the claims settlement is predicted by inputting new feature data of the claims settlement personnel, so that basis and optimization advice are provided for actual insurance claims settlement business.
Step S500: performing incremental learning based on the first claim personnel feature analysis model to generate a second claim personnel feature analysis model;
further, step S500 of the present application further includes:
step S510: based on the insurance claim type identifier, obtaining a test data sequence meeting a preset data amount;
step S520: based on the test data sequence, testing the first claimant characteristic analysis model to obtain a test loss data sequence;
step S530: and based on the test loss data sequence, performing incremental learning on the first claim staff feature analysis model to obtain the second claim staff feature analysis model.
Specifically, according to the insurance claim type identifier, corresponding insurance claim data is screened from a database or other data sources, and according to the requirement of the preset data amount, a certain amount of data is randomly extracted from the screened data to serve as a test data sequence, for example, 100 data, wherein the test data sequence comprises characteristic data of claim settlement personnel and actual claim settlement results.
The test data sequence is input into a first claimant characteristic analysis model, the model predicts the claimant result according to the input characteristic data, the predicted result is compared with the actual claimant result, and the loss of the model on the test data, such as mean square error, is calculated. The lower the loss value, the better the predicted performance of the model, and the loss value of the whole test data sequence is summarized into a test loss data sequence for evaluating the performance of the model.
And performing incremental learning by using the test data sequence and the loss data sequence and adjusting the weight and the bias of the model, so that the model is gradually improved to adapt to new data on the basis of keeping the performance of the original model, and a second claim settlement personnel characteristic analysis model is generated through the incremental learning. The model has better performance and adaptability, can more accurately analyze the relation between the characteristics of insurance claimant and the claimant result, and provides more accurate decision support and business optimization suggestion for insurance companies.
Step S600: performing principal component analysis based on the target insurance claim data set to obtain a target insurance claim data set;
specifically, a Principal Component Analysis (PCA) is performed on the target insurance claim dataset to reduce the data dimension while retaining as much information as possible of the original data. Principal component analysis is a commonly used statistical method aimed at achieving dimension reduction by converting raw data into a new coordinate system, and maximizing the variance of the data under the new coordinate system. Specifically, the target insurance claim data set is subjected to standardized processing, so that the data has zero mean and unit variance, a covariance matrix of the target insurance claim data set is calculated, eigenvalues and eigenvectors of the covariance matrix are calculated, eigenvectors corresponding to the first k largest eigenvalues are selected, k is the dimension of the new data set, for example, k=5 is taken, and the original data set is multiplied by the selected eigenvectors to obtain the target insurance claim data set after dimension reduction. Through principal component analysis, a target insurance claim data set with reduced dimension is obtained, and the data dimension is reduced while most of information of the original data is reserved, so that the efficiency of subsequent data analysis is improved.
Step S700: and inputting the target insurance claim data set into the second claim settlement personnel feature analysis model to obtain a target insurance claim settlement personnel feature analysis result.
Specifically, the target insurance claim data set is used as input, the characteristic analysis is carried out through a second claim settlement personnel characteristic analysis model, the target insurance claim data set is classified and predicted, and the characteristic analysis result of the target insurance claim personnel is obtained.
In summary, the method, the device and the equipment for analyzing the characteristics of the insurance claim settlement personnel provided by the embodiment of the application have the following technical effects:
obtaining a target insurance claim data set, including an insurance claim type identifier, obtaining a multi-stage claim personnel analysis dimension, including an insurance claim feature analysis main body and an insurance claim feature analysis auxiliary body, performing data mining, constructing a claim personnel feature distribution model, performing deep learning, building a first claim personnel feature analysis model, performing incremental learning, generating a second claim personnel feature analysis model, performing principal component analysis, obtaining a target insurance claim data set, inputting the second claim personnel feature analysis model, and obtaining a target insurance claim personnel feature analysis result. The method solves the technical problems of poor accuracy and efficiency of the traditional insurance claim settlement personnel feature analysis method which is mainly based on statistical analysis and experience judgment and has higher calculation complexity for a large-scale data set, realizes automatic learning and feature extraction, reduces the requirement of manual feature engineering, is further suitable for the feature analysis and prediction tasks of the large-scale data set, and achieves the technical effects of improving the feature representation capability and the prediction accuracy.
Example two
Based on the same inventive concept as an insurance claim staff feature analysis method in the foregoing embodiments, as shown in fig. 3, the present application provides an insurance claim staff feature analysis device, the device including:
the target claim data acquisition module 10 is used for acquiring a target insurance claim data set of a target user, wherein the target insurance claim data set comprises an insurance claim type identifier;
the multi-stage analysis dimension acquisition module 20 is used for acquiring multi-stage analysis dimensions of the claimant, wherein the multi-stage analysis dimensions of the claimant comprise an insurance claim feature analysis main body and an insurance claim feature analysis auxiliary body;
the data mining module 30 is used for carrying out data mining based on the insurance claim type identification and the multi-stage claim settlement personnel analysis dimension, and constructing a claim settlement personnel characteristic distribution model;
the deep learning module 40 is configured to perform deep learning based on the characteristic distribution model of the claimant, and build a first characteristic analysis model of the claimant;
the incremental learning module 50 is configured to perform incremental learning based on the first claim personnel feature analysis model, and generate a second claim personnel feature analysis model;
The principal component analysis module 60, wherein the principal component analysis module 60 is configured to perform principal component analysis based on the target insurance claim data set, so as to obtain a target insurance claim data set;
the analysis result obtaining module 70 is configured to input the target insurance claim data set into the second claim personnel feature analysis model, and obtain a target insurance claim personnel feature analysis result.
Further, the device further comprises:
the main body characteristic model acquisition module is used for carrying out data mining based on the insurance claim type identifier and the insurance claim characteristic analysis main body to generate a claim settlement personnel main body characteristic distribution model;
the auxiliary body characteristic model acquisition module is used for carrying out data mining on the basis of the insurance claim type identifier and the insurance claim characteristic analysis auxiliary body to generate a claim settlement personnel auxiliary body characteristic distribution model;
and the characteristic distribution model acquisition module is used for acquiring the characteristic distribution model of the claimant based on the main characteristic distribution model of the claimant and the auxiliary characteristic distribution model of the claimant.
Further, the device further comprises:
the feature analysis main body module is used for obtaining a plurality of groups of analysis records of the claim main body with the same data volume based on the insurance claim type identification and the insurance claim feature analysis main body;
The factor extraction module is used for traversing the multiple groups of claim main analysis records to extract factors and obtain multiple preparation main feature analysis factors;
the optimizing and screening module is used for traversing the plurality of preparation main body characteristic analysis factors to perform optimizing and screening so as to obtain a plurality of winning main body characteristic analysis factors;
and the characteristic distribution model generation module is used for generating the main characteristic distribution model of the claimant based on the plurality of winning main characteristic analysis factors.
Further, the device further comprises:
the boost fitness analysis module is used for traversing the plurality of preparation main body characteristic analysis factors to carry out boost fitness analysis and obtaining a plurality of factor boost fitness;
the influence analysis module is used for traversing the plurality of preparation main body characteristic analysis factors to perform insurance claim impact analysis and obtain a plurality of factor impact fitness;
the weighting fusion module is used for carrying out weighting fusion on the basis of the multiple factor lifting fitness and the multiple factor influence fitness to obtain multiple factor characteristic fitness;
the fitness judging module is used for judging whether the fitness of the plurality of factor features meets the preset feature fitness or not, and obtaining a plurality of fitness judging results;
And the screening module is used for screening the plurality of preparation main body characteristic analysis factors based on the plurality of fitness judging results to obtain the plurality of winning main body characteristic analysis factors.
Further, the device further comprises:
the first preparation analysis factor acquisition module is used for traversing the plurality of preparation main body characteristic analysis factors to acquire a first preparation main body characteristic analysis factor;
the first support degree analysis module is used for carrying out support degree analysis on the first preparation main body characteristic analysis factors based on the multiple groups of claim main body analysis records to obtain first factor support degree;
the second support degree analysis module is used for traversing the plurality of preparation main body characteristic analysis factors to carry out support degree analysis based on the plurality of groups of claim main body analysis records so as to obtain factor characteristic support degree;
and the lifting calculation module is used for carrying out lifting calculation based on the first factor support degree and the factor characteristic support degree, obtaining first factor lifting fitness, and adding the first factor lifting fitness to the plurality of factor lifting fitness.
Further, the device further comprises:
the claimant feature distribution model comprises a claimant main feature distribution model and a claimant auxiliary feature distribution model;
The main body characteristic association analysis module is used for carrying out main body characteristic association analysis based on the main body characteristic distribution model of the claimant to obtain a main body characteristic association relation;
the auxiliary body characteristic association analysis module is used for carrying out auxiliary body characteristic association analysis based on the auxiliary body characteristic distribution model of the claimant to obtain an auxiliary body characteristic association relation;
the binary characteristic association relation acquisition module is used for acquiring a binary characteristic association relation based on the main characteristic association relation and the auxiliary body characteristic association relation;
the constructed data sequence acquisition module is used for acquiring a constructed data sequence based on the binary characteristic association relation;
and the constructed data sequence training module is used for training according to the constructed data sequence based on the BP neural network to obtain the first claim settlement personnel characteristic analysis model.
Further, the device further comprises:
the test data sequence acquisition module is used for acquiring a test data sequence meeting preset data quantity based on the insurance claim type identifier;
the analysis model test module is used for testing the first claim settlement personnel characteristic analysis model based on the test data sequence to obtain a test loss data sequence;
And the second incremental learning module is used for performing incremental learning on the first claim staff feature analysis model based on the test loss data sequence to obtain the second claim staff feature analysis model.
The insurance claim personnel feature analysis device provided by the embodiment of the application can execute the insurance claim personnel feature analysis method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
All the included modules are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be realized; in addition, the specific names of the functional modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present invention.
Example III
Fig. 4 is a schematic structural diagram of an electronic device provided in a third embodiment of the present invention, and shows a block diagram of an exemplary electronic device suitable for implementing an embodiment of the present invention. The electronic device shown in fig. 4 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention. As shown in fig. 4, the electronic device includes a processor 31, a memory 32, an input device 33, and an output device 34; the number of processors 31 in the electronic device may be one or more, in fig. 4, one processor 31 is taken as an example, and the processors 31, the memory 32, the input device 33 and the output device 34 in the electronic device may be connected by a bus or other means, in fig. 4, by bus connection is taken as an example.
The memory 32 is used as a computer readable storage medium for storing software programs, computer executable programs and modules, such as program instructions/modules corresponding to an insurance claim personnel feature analysis method in an embodiment of the present invention. The processor 31 executes various functional applications of the computer device and data processing by running software programs, instructions and modules stored in the memory 32, i.e., implements an insurance claim personnel feature analysis method as described above.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (4)
1. A method of analyzing characteristics of an insurance claim settlement person, the method comprising:
Obtaining a target insurance claim data set of a target user, wherein the target insurance claim data set comprises an insurance claim type identifier;
obtaining a multi-stage claimant analysis dimension, wherein the multi-stage claimant analysis dimension comprises an insurance claimant feature analysis main body and an insurance claimant feature analysis auxiliary body;
performing data mining based on the insurance claim type identifier and the multi-stage claim settlement personnel analysis dimension, and constructing a claim settlement personnel feature distribution model;
deep learning is carried out based on the characteristic distribution model of the claim settlement personnel, and a first characteristic analysis model of the claim settlement personnel is built;
performing incremental learning based on the first claim personnel feature analysis model to generate a second claim personnel feature analysis model;
performing principal component analysis based on the target insurance claim data set to obtain a target insurance claim data set;
inputting the target insurance claim data set into the second claim settlement personnel feature analysis model to obtain a target insurance claim settlement personnel feature analysis result;
and carrying out data mining based on the insurance claim type identifier and the multi-stage claim settlement personnel analysis dimension, and constructing a claim settlement personnel feature distribution model, wherein the method comprises the following steps of:
Performing data mining based on the insurance claim type identifier and the insurance claim feature analysis main body to generate a main body feature distribution model of the claim settlement personnel;
performing data mining on the basis of the insurance claim type identifier and the insurance claim feature analysis auxiliary body to generate a claim settlement personnel auxiliary body feature distribution model;
obtaining the characteristic distribution model of the claimant based on the main characteristic distribution model of the claimant and the auxiliary characteristic distribution model of the claimant;
and carrying out data mining based on the insurance claim type identifier and the insurance claim feature analysis main body to generate a claim settlement personnel main body feature distribution model, wherein the method comprises the following steps of:
obtaining a plurality of groups of analysis records of the claim settlement main body with the same data volume based on the insurance claim settlement type identification and the insurance claim settlement characteristic analysis main body;
traversing the multiple groups of claim main analysis records to perform factor extraction to obtain multiple preparation main feature analysis factors;
traversing the plurality of preparation main body characteristic analysis factors to perform optimizing screening to obtain a plurality of winning main body characteristic analysis factors;
generating the claimant subject feature distribution model based on the plurality of winning subject feature analysis factors;
Traversing the plurality of preliminary principal feature analysis factors for optimizing and screening to obtain a plurality of winning principal feature analysis factors, including:
traversing the plurality of preparation main body characteristic analysis factors to perform lifting fitness analysis to obtain a plurality of factor lifting fitness;
traversing the plurality of preparation main body characteristic analysis factors to perform insurance claim impact analysis to obtain a plurality of factor impact fitness;
weighting fusion is carried out based on the multiple factor lifting fitness and the multiple factor influence fitness, so that multiple factor characteristic fitness is obtained;
judging whether the plurality of factor characteristic fitness meets preset characteristic fitness or not, and obtaining a plurality of fitness judging results;
screening a plurality of preparation subject feature analysis factors based on the plurality of fitness judgment results to obtain a plurality of winning subject feature analysis factors;
wherein the method comprises the following steps:
traversing the plurality of preliminary subject feature analysis factors to obtain a first preliminary subject feature analysis factor;
based on the multiple groups of claim main body analysis records, carrying out support degree analysis on the first preparation main body characteristic analysis factors to obtain first factor support degree;
traversing the plurality of preparation subject feature analysis factors to perform support degree analysis based on the plurality of groups of claim subject analysis records to obtain factor feature support degree;
Lifting calculation is carried out based on the first factor support degree and the factor characteristic support degree, so that first factor lifting fitness is obtained, and the first factor lifting fitness is added to the plurality of factor lifting fitness;
deep learning is carried out based on the characteristic distribution model of the claim settlement personnel, and a first characteristic analysis model of the claim settlement personnel is built, which comprises the following steps:
the claimant feature distribution model comprises a claimant main feature distribution model and a claimant auxiliary feature distribution model;
carrying out main body characteristic association analysis based on the main body characteristic distribution model of the claim settlement personnel to obtain main body characteristic association relation;
performing auxiliary body characteristic association analysis based on the auxiliary body characteristic distribution model of the claim settlement personnel to obtain an auxiliary body characteristic association relation;
acquiring a binary feature association relationship based on the main feature association relationship and the auxiliary body feature association relationship;
obtaining a constructed data sequence based on the binary characteristic association relation;
training according to the constructed data sequence based on a BP neural network to obtain the first claim settlement personnel characteristic analysis model;
performing incremental learning based on the first claim personnel feature analysis model to generate a second claim personnel feature analysis model, including:
Based on the insurance claim type identifier, obtaining a test data sequence meeting a preset data amount;
based on the test data sequence, testing the first claimant characteristic analysis model to obtain a test loss data sequence;
and based on the test loss data sequence, performing incremental learning on the first claim staff feature analysis model to obtain the second claim staff feature analysis model.
2. An insurance claim personnel feature analysis device for performing the method of claim 1, the device comprising:
the system comprises a target claim data acquisition module, a target claim data processing module and a target claim data processing module, wherein the target claim data acquisition module is used for acquiring a target insurance claim data set of a target user, and the target insurance claim data set comprises an insurance claim type identifier;
the system comprises a multi-stage analysis dimension acquisition module, a storage module and a storage module, wherein the multi-stage analysis dimension acquisition module is used for acquiring multi-stage analysis dimensions of the claimant, wherein the multi-stage analysis dimensions of the claimant comprise an insurance claimant characteristic analysis main body and an insurance claimant characteristic analysis auxiliary body;
the data mining module is used for carrying out data mining based on the insurance claim type identification and the multi-stage claim settlement personnel analysis dimension, and constructing a claim settlement personnel feature distribution model;
The deep learning module is used for carrying out deep learning based on the characteristic distribution model of the claimant and building a characteristic analysis model of the first claimant;
the incremental learning module is used for performing incremental learning based on the first claim personnel characteristic analysis model and generating a second claim personnel characteristic analysis model;
the principal component analysis module is used for carrying out principal component analysis based on the target insurance claim data set to obtain the target insurance claim data set;
the analysis result acquisition module is used for inputting the target insurance claim data set into the second claim settlement personnel characteristic analysis model to obtain a target insurance claim settlement personnel characteristic analysis result;
the main body characteristic model acquisition module is used for carrying out data mining based on the insurance claim type identifier and the insurance claim characteristic analysis main body to generate a claim settlement personnel main body characteristic distribution model;
the auxiliary body characteristic model acquisition module is used for carrying out data mining on the basis of the insurance claim type identifier and the insurance claim characteristic analysis auxiliary body to generate a claim settlement personnel auxiliary body characteristic distribution model;
The characteristic distribution model acquisition module is used for acquiring the characteristic distribution model of the claimant based on the main characteristic distribution model of the claimant and the auxiliary characteristic distribution model of the claimant;
the feature analysis main body module is used for obtaining a plurality of groups of analysis records of the claim main body with the same data volume based on the insurance claim type identification and the insurance claim feature analysis main body;
the factor extraction module is used for traversing the multiple groups of claim main analysis records to extract factors and obtain multiple preparation main feature analysis factors;
the optimizing and screening module is used for traversing the plurality of preparation main body characteristic analysis factors to perform optimizing and screening so as to obtain a plurality of winning main body characteristic analysis factors;
the feature distribution model generation module is used for generating the main feature distribution model of the claimant based on the plurality of winning main feature analysis factors;
the boost fitness analysis module is used for traversing the plurality of preparation main body characteristic analysis factors to carry out boost fitness analysis and obtaining a plurality of factor boost fitness;
the influence analysis module is used for traversing the plurality of preparation main body characteristic analysis factors to perform insurance claim impact analysis and obtain a plurality of factor impact fitness;
The weighting fusion module is used for carrying out weighting fusion on the basis of the multiple factor lifting fitness and the multiple factor influence fitness to obtain multiple factor characteristic fitness;
the fitness judging module is used for judging whether the fitness of the plurality of factor features meets the preset feature fitness or not, and obtaining a plurality of fitness judging results;
the screening module is used for screening a plurality of preparation main body characteristic analysis factors based on the plurality of fitness judging results to obtain a plurality of winning main body characteristic analysis factors;
the first preparation analysis factor acquisition module is used for traversing the plurality of preparation main body characteristic analysis factors to acquire a first preparation main body characteristic analysis factor;
the first support degree analysis module is used for carrying out support degree analysis on the first preparation main body characteristic analysis factors based on the multiple groups of claim main body analysis records to obtain first factor support degree;
the second support degree analysis module is used for traversing the plurality of preparation main body characteristic analysis factors to carry out support degree analysis based on the plurality of groups of claim main body analysis records so as to obtain factor characteristic support degree;
the lifting calculation module is used for carrying out lifting calculation based on the first factor support degree and the factor characteristic support degree, obtaining first factor lifting fitness, and adding the first factor lifting fitness to the plurality of factor lifting fitness;
The claimant feature distribution model comprises a claimant main feature distribution model and a claimant auxiliary feature distribution model;
the main body characteristic association analysis module is used for carrying out main body characteristic association analysis based on the main body characteristic distribution model of the claimant to obtain a main body characteristic association relation;
the auxiliary body characteristic association analysis module is used for carrying out auxiliary body characteristic association analysis based on the auxiliary body characteristic distribution model of the claimant to obtain an auxiliary body characteristic association relation;
the binary characteristic association relation acquisition module is used for acquiring a binary characteristic association relation based on the main characteristic association relation and the auxiliary body characteristic association relation;
the constructed data sequence acquisition module is used for acquiring a constructed data sequence based on the binary characteristic association relation;
the building data sequence training module is used for training according to the building data sequence based on the BP neural network to obtain the first claim settlement personnel characteristic analysis model;
the test data sequence acquisition module is used for acquiring a test data sequence meeting preset data quantity based on the insurance claim type identifier;
the analysis model test module is used for testing the first claim settlement personnel characteristic analysis model based on the test data sequence to obtain a test loss data sequence;
And the second incremental learning module is used for performing incremental learning on the first claim staff feature analysis model based on the test loss data sequence to obtain the second claim staff feature analysis model.
3. An electronic device, the electronic device comprising:
a memory for storing executable instructions;
a processor for implementing an insurance claim settlement personnel feature analysis method of claim 1 when executing the executable instructions stored in the memory.
4. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements an insurance claim personnel feature analysis method as claimed in claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310601138.6A CN116342300B (en) | 2023-05-26 | 2023-05-26 | Method, device and equipment for analyzing characteristics of insurance claim settlement personnel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310601138.6A CN116342300B (en) | 2023-05-26 | 2023-05-26 | Method, device and equipment for analyzing characteristics of insurance claim settlement personnel |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116342300A CN116342300A (en) | 2023-06-27 |
| CN116342300B true CN116342300B (en) | 2023-08-01 |
Family
ID=86884367
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310601138.6A Active CN116342300B (en) | 2023-05-26 | 2023-05-26 | Method, device and equipment for analyzing characteristics of insurance claim settlement personnel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116342300B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993661A (en) * | 2019-04-04 | 2019-07-09 | 凯泰铭科技（北京）有限公司 | A kind of settlement of insurance claim data analysing method and system |
| CN115222549A (en) * | 2022-08-04 | 2022-10-21 | 中国平安财产保险股份有限公司 | Risk assessment processing method and device, computer equipment and storage medium |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8352292B2 (en) * | 2009-12-31 | 2013-01-08 | Hampton Thurman B | Personal injury valuation systems and method |
| CN109285075B (en) * | 2017-07-19 | 2022-03-01 | 腾讯科技（深圳）有限公司 | Claims risk assessment method and device and server |
| CN108256720A (en) * | 2017-11-07 | 2018-07-06 | 中国平安财产保险股份有限公司 | A kind of settlement of insurance claim methods of risk assessment and terminal device |
| CN107909299B (en) * | 2017-12-11 | 2018-09-18 | 凯泰铭科技（北京）有限公司 | People hinders Claims Resolution data risk checking method and system |
| CN108846766A (en) * | 2018-06-25 | 2018-11-20 | 江苏汉德天坤数字技术有限公司 | The self-service Claims Resolution success rate prediction technique of vehicle insurance based on deep learning |
| CN109903172A (en) * | 2019-01-31 | 2019-06-18 | 阿里巴巴集团控股有限公司 | Claims Resolution information extracting method and device, electronic equipment |
| CN111553803A (en) * | 2020-06-04 | 2020-08-18 | 上海燕汐软件信息科技有限公司 | Claims processing method and device |
| CN113379555A (en) * | 2021-06-07 | 2021-09-10 | 北京车与车科技有限公司 | Deep learning-based vehicle insurance wind control pricing model method |
| CN114862597A (en) * | 2022-05-11 | 2022-08-05 | 好人生（上海）健康科技有限公司 | Health insurance claim settlement risk prediction method and system based on medical big data |
| CN114998041A (en) * | 2022-06-28 | 2022-09-02 | 中国平安人寿保险股份有限公司 | Method and device for training claim settlement prediction model, electronic equipment and storage medium |
| CN115952216A (en) * | 2022-12-12 | 2023-04-11 | 北京易华录信息技术股份有限公司 | Aging insurance data mining method and device, storage medium and electronic equipment |
-
2023
- 2023-05-26 CN CN202310601138.6A patent/CN116342300B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993661A (en) * | 2019-04-04 | 2019-07-09 | 凯泰铭科技（北京）有限公司 | A kind of settlement of insurance claim data analysing method and system |
| CN115222549A (en) * | 2022-08-04 | 2022-10-21 | 中国平安财产保险股份有限公司 | Risk assessment processing method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116342300A (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110928764B (en) | Automated evaluation method for crowdsourcing test report of mobile application and computer storage medium | |
| Sohrabinejad et al. | Risk determination, prioritization, and classifying in construction project case study: gharb tehran commercial-administrative complex | |
| CN114048436A (en) | Construction method and construction device for forecasting enterprise financial data model | |
| CN113450004A (en) | Power credit report generation method and device, electronic equipment and readable storage medium | |
| CN113837578A (en) | Gridding supervision and management evaluation method for power supervision enterprise | |
| CN112184495B (en) | Stock low-efficiency land monitoring system and analysis platform using same | |
| CN116342300B (en) | Method, device and equipment for analyzing characteristics of insurance claim settlement personnel | |
| CN111798057A (en) | Charging station site selection method based on fuzzy level profit analysis | |
| CN107093018A (en) | Communication engineering project information method for visualizing and device based on health model | |
| CN116861331A (en) | Expert model decision-fused data identification method and system | |
| CN115796665A (en) | Multi-index carbon efficiency grading evaluation method and device for green energy power generation project | |
| CN115147091A (en) | Intelligent salary query method and system | |
| KR102543211B1 (en) | Company's growth potential prediction system using unstructured data | |
| Qiang et al. | Relationship model between human resource management activities and performance based on LMBP algorithm | |
| CN114548494A (en) | Visual cost data prediction intelligent analysis system | |
| CN114626940A (en) | Data analysis method and device and electronic equipment | |
| CN113537759A (en) | User experience measurement model based on weight self-adaptation | |
| CN113807587A (en) | Integral early warning method and system based on multi-ladder-core deep neural network model | |
| CN112418600A (en) | Enterprise policy scoring method and system based on index set | |
| CN111461524A (en) | Judicial agency reputation evaluation method, system, equipment and storage medium | |
| CN113064962B (en) | Environment complaint reporting event similarity analysis method | |
| CN113537734B (en) | Energy data application catalog extraction method based on maximum correlation minimum redundancy | |
| CN115237970A (en) | Data prediction method, device, equipment, storage medium and program product | |
| CN116993480A (en) | Method and system for creating risk level model and evaluating risk level | |
| CN116797010A (en) | Work number identification method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |