Claim settlement data analysis method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a claim data analysis method and device, computer equipment and a readable storage medium, and relates to the field of artificial intelligence. The method comprises the steps of obtaining claim settlement data and a user analysis demand, and performing data cleaning processing on the claim settlement data to obtain target claim settlement data; analyzing the target claim settlement data to obtain claim settlement information, and determining associated claim settlement information according to the claim settlement information; determining a target data analysis model from a model database according to the claim settlement information and the corresponding associated claim settlement information; generating a data analysis code according to the user analysis demand, the claim settlement information and the corresponding associated claim settlement information; predicting the target claim settlement data according to the data analysis code to obtain claim settlement analysis data; and determining data features of the claim settlement analysis data, and generating an analysis report and an analysis feature graph corresponding to the claim settlement data according to the data features. The invention aims to solve the problems that the claim data analysis efficiency is low, the data utilization rate is low, and misjudgment is easy to occur.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a method for analyzing claims data, an apparatus for analyzing claims data, a computer device, and a computer-readable storage medium. Background Art

[0002] At present, in the financial field, such as the claim settlement scenario of property insurance, property insurance has accumulated a large amount of claim settlement data, which is distributed in multiple categories such as auto insurance, home property insurance, vehicle insurance, pet insurance, medical insurance, etc. For these claim settlement data, algorithm engineers are often required to analyze the claim settlement data to obtain the claim settlement analysis results.

[0003] However, analysis of claims data by algorithm engineers often relies too much on the engineers' own expertise, resulting in insufficient mining of claims data, lack of risk analysis and prediction of claims data, and in complex claims cases, human bias may lead to misjudgment and waste of resources, leading to low efficiency of claims data analysis, low data utilization, and easy misjudgment. Summary of the invention

[0004] The present application provides a claims data analysis method, a claims data analysis device, a computer device and a computer-readable storage medium, aiming to solve the problems of low efficiency in claims data analysis, low data utilization and easy misjudgment.

[0005] To achieve the above objectives, the present application provides a method for analyzing claims data, the method comprising:

[0006] Obtaining claims data and user analysis requirements, and performing data cleaning on the claims data to obtain target claims data;

[0007] Parsing the target claim data to obtain claim information, and determining related claim information based on the claim information;

[0008] Determining a target data analysis model from a model database according to the claim information and its corresponding associated claim information;

[0009] Based on the target data analysis model, generating data analysis code according to the user analysis requirements, the claim information and its corresponding associated claim information;

[0010] Based on the code interpreter, predicting the target claims data according to the data analysis code to obtain claims analysis data;

[0011] Determine data features of the claims analysis data, and generate analysis reports and analysis feature graphs corresponding to the claims data based on the data features.

[0012] To achieve the above-mentioned purpose, the present application provides a claim data analysis device, the claim data analysis device comprising:

[0013] A data cleaning module is used to obtain claim data and user analysis requirements, and perform data cleaning on the claim data to obtain target claim data;

[0014] A related information determination module, used for parsing the target claim data to obtain claim information, and determining related claim information according to the claim information;

[0015] A model determination module, used to determine a target data analysis model from a model database according to the claim information and its corresponding associated claim information;

[0016] A code generation module, for generating data analysis code based on the target data analysis model, according to the user analysis requirements, the claim information and its corresponding associated claim information;

[0017] A data prediction module, used for predicting the target claims data based on the data analysis code based on a code interpreter to obtain claims analysis data;

[0018] The data analysis module is used to determine the data characteristics of the claims analysis data, and generate an analysis report and an analysis characteristic diagram corresponding to the claims data according to the data characteristics.

[0019] To achieve the above-mentioned purpose, the present application provides a computer device, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the claim data analysis method as described above when executing the computer program.

[0020] To achieve the above objectives, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the claim data analysis method as described above.

[0021] The claim data analysis method, claim data analysis device, computer equipment and computer-readable storage medium disclosed in the embodiment of the present application obtain claim data and user analysis requirements, and perform data cleaning processing on the claim data to obtain target claim data; parse the target claim data to obtain claim information, and determine the associated claim information according to the claim information; determine the target data analysis model from the model database according to the claim information and its corresponding associated claim information; based on the target data analysis model, generate data analysis code according to the user analysis requirements, claim information and its corresponding associated claim information; based on the code interpreter, predict the target claim data according to the data analysis code to obtain claim analysis data; determine the data features of the claim analysis data, and generate the analysis report and analysis feature graph corresponding to the claim data according to the data features. This can greatly reduce manual operation and professional skill requirements, employees can complete data analysis tasks more efficiently, improve data analysis efficiency, and at the same time can deeply explore the value of claim data and improve data utilization, so as to better carry out risk management and claim pricing and other businesses, and can also provide a comprehensive analysis perspective to effectively avoid misjudgment and waste of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 It is a scenario diagram of a method for analyzing claims data provided in an embodiment of the present application;

[0024] Figure 2 It is a flowchart of a method for analyzing claims data provided in an embodiment of the present application;

[0025] Figure 3 is a schematic block diagram of a claim data analysis device provided in one embodiment of the present application;

[0026] Figure 4 It is a schematic block diagram of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor do they have to be executed in the order described. For example, some operations / steps can also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions. In addition, although the functional modules are divided in the device schematic, in some cases, the module division can be different from that in the device schematic.

[0029] The term "and / or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0030] In the case of property insurance claims, auto insurance and non-auto insurance are the main business scenarios. Existing claims data analysis methods already exist in the industry, but these methods generally have the following shortcomings and problems:

[0031] 1. Complex data analysis: Current claims data analysis methods mostly rely on professional data analysts, and ordinary employees find it difficult to master complex analysis techniques and tools. This results in limited in-depth data mining and utilization, and low overall work efficiency.

[0032] 2. Single analysis method: Existing methods usually preset fixed analysis models and methods, lack flexibility, and are difficult to adapt to different business needs and diversified analysis tasks. For example, in the field of auto insurance, it may be limited to simple accident frequency and loss amount statistics, while in non-auto insurance fields, such as property damage insurance, it may only provide basic loss assessments and lack in-depth risk analysis and prediction functions.

[0033] 3. Human bias: In traditional analysis methods, the subjective judgment and experience of analysts may lead to biased analysis results, which in turn affects the scientificity and objectivity of the company's decision-making. Especially in complex claims cases, human bias may lead to misjudgment and waste of resources.

[0034] To address the above-mentioned defects, the present application proposes a claims data analysis method, a claims data analysis device, a computer device and a computer-readable storage medium, which can greatly reduce manual operations and professional skill requirements, and employees can complete data analysis tasks more efficiently, thereby improving data analysis efficiency. At the same time, they can deeply explore the value of claims data and improve data utilization, thereby better performing risk management and claims pricing and other businesses. It can also provide a comprehensive analysis perspective to effectively avoid misjudgment and waste of resources.

[0035] The method can be applied to a server, and of course can also be applied to a terminal device, wherein the terminal device may include a fixed terminal such as a mobile phone, a tablet computer, a personal digital assistant (PDA), etc. The server may be, for example, a separate server or a server cluster. However, for ease of understanding, the following embodiment will be described in detail with the analysis method of the claims data applied to the server.

[0036] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0037] like Figure 1 As shown, the claim data analysis method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. The application environment includes a terminal device 110 and a server 120, wherein the terminal device 110 can communicate with the server 120 through a network. Specifically, the server 120 obtains the claim data and the user analysis requirements, and performs data cleaning processing on the claim data to obtain the target claim data; parses the target claim data to obtain the claim information, and determines the associated claim information based on the claim information; determines the target data analysis model from the model database based on the claim information and its corresponding associated claim information; based on the target data analysis model, generates data analysis code based on the user analysis requirements, the claim information and its corresponding associated claim information; based on the code interpreter, predicts the target claim data according to the data analysis code to obtain the claim analysis data; determines the data features of the claim analysis data, generates the analysis report and analysis feature graph corresponding to the claim data according to the data features, and sends the analysis report and analysis feature graph corresponding to the claim data to the terminal device 110. Among them, the server 120 can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. The terminal device 110 can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited to this. The terminal and the server can be directly or indirectly connected via wired or wireless communication, and this application does not limit this.

[0038] See also Figure 2 , Figure 2This is a schematic flow chart of a method for analyzing claims data provided by an embodiment of the present application. The method for analyzing claims data can significantly reduce manual operations and professional skills requirements, allowing employees to complete data analysis tasks more efficiently, improving data analysis efficiency, and at the same time deeply mining the value of claims data and improving data utilization, thereby better performing risk management and claims pricing and other businesses, and can also provide a comprehensive analysis perspective to effectively avoid misjudgments and waste of resources.

[0039] like Figure 2 As shown, the claim data analysis method includes steps S101 to S106.

[0040] S101. Obtain claims data and user analysis requirements, and perform data cleaning on the claims data to obtain target claims data.

[0041] The claim data may be insurance data such as auto insurance data, health insurance data, home property insurance data, etc. The target claim data is the claim data converted into a preset data format.

[0042] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0043] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0044] In some embodiments, data type conversion processing is performed on the claim data to obtain claim data that conforms to a preset data type; missing value processing is performed on the claim data that conforms to the preset data type to obtain target claim data. In this way, the claim data can be converted into target claim data, thereby ensuring the data quality of the claim data, so as to facilitate the subsequent determination of the target data analysis model.

[0045] The preset data type may include data corresponding to a CSV format or data corresponding to an Excel format, which is not specifically limited here.

[0046] Specifically, the data type of the claims data can be detected first to determine whether the data type of the claims data conforms to the preset data type. If the data type of the claims data conforms to the preset data type, the claims data is processed for missing values ​​to obtain target claims data; if the data type of the claims data does not conform to the preset data type, the claims data is converted for data type to obtain claims data that conforms to the preset data type; then the claims data that conforms to the preset data type is processed for missing values ​​to obtain target claims data, thereby ensuring the data quality of the claims data.

[0047] For example, data processing libraries such as pandas can be used to convert the format of the uploaded claims data to obtain claims data that conforms to a preset data type, and then missing value processing is performed on the claims data that conforms to the preset data type to obtain target claims data.

[0048] S102: Analyze the target claim data to obtain claim information, and determine related claim information based on the claim information.

[0049] Among them, the associated claim information is information associated with the claim information, which can be obtained by deeply mining the claim information.

[0050] In some embodiments, the claim type corresponding to the claim data is determined based on the claim information; the claim information is screened based on the claim type to obtain the associated information factor; the information database is traversed to determine the associated claim information based on the associated information factor. In this way, the associated claim information can be accurately determined, so that the data value can be deeply mined, so as to more accurately determine the data analysis model later.

[0051] Among them, the claim type can be determined by factors such as insurance type and insurance purpose, for example, the claim type can be a car insurance claim type, an accident insurance claim type, etc. The associated information factor is a factor used to determine the associated claim information, such as location information, person information, etc. The information database may include a large amount of information associated with various types of claim information.

[0052] Exemplarily, the claim type corresponding to the claim data can be determined as a motor insurance claim type based on the claim information, and the claim information is screened based on the claim type to obtain associated information factors that can be used to determine associated claim information; finally, the information database is traversed to determine the associated claim information based on the associated information factors.

[0053] For example, the Jiacaibao claim type is taken as an example, and its corresponding fields are recorded. A small number of fields are shown in Table 1.

[0054] Table 1

[0055]

[0056] For the claims data itself, the information that can be mined is limited. Existing analysis methods for claims data often use multiple statistical values, such as mean, variance, and quarter quantiles, to perform data analysis. These data can well reflect the characteristics of the data itself, but lack effective correlation with external factors. For the claims data, the corresponding claim type can be determined as the Jiacaibao claim type through claim information such as insurance number and insurance name, and then the claim information can be screened according to the claim type, and the associated information factors can be obtained as claim details and the address of the incident. Finally, the local news information database at that time can be combined to determine the associated claims information such as related events according to the associated information factors, so as to obtain deeper information.

[0057] S103. Determine a target data analysis model from a model database based on the claim information and its corresponding associated claim information.

[0058] The model database may include multiple different types of data analysis models, each of which corresponds to a different prediction purpose. The target data analysis model may be a data analysis model that corresponds to the claim data.

[0059] In some embodiments, the claim prediction type corresponding to the claim information and its corresponding associated claim information is determined; multiple preset data analysis models in the model database are obtained, and a target data analysis model is determined from the multiple preset data analysis models according to the claim prediction type. In this way, the target data analysis model can be accurately determined from the multiple preset data analysis models.

[0060] Among them, the claim prediction type may include claim amount prediction types such as risk prediction type, causal analysis prediction type, fraud prediction type and claim trend prediction type, etc. The preset data analysis model may be a data analysis model corresponding to different claim prediction types.

[0061] Specifically, the claim information and its corresponding associated claim information can be parsed and type predicted to obtain the claim prediction type of the claim information and its corresponding associated claim information; the model types of multiple preset data analysis models in the model database are obtained, and according to the claim prediction type of the claim information and its corresponding associated claim information, the model types of multiple preset data analysis models are matched to determine the target data analysis model.

[0062] In some embodiments, the model types of multiple preset data analysis models are obtained; the similarity between the model type of each preset data analysis model and the claim prediction type is determined; if the similarity between the model type of a preset data analysis model and the claim prediction type exceeds a preset similarity threshold, the preset data analysis model is used as the target data analysis model. In this way, the target data analysis model that best matches the claim data can be accurately determined.

[0063] The model types of the preset data analysis model may include risk prediction type, causal analysis prediction type, fraud prediction type, and claim trend prediction type, etc. The model type may be used to match the claim prediction type to determine the target data analysis model. The preset similarity threshold may be any similarity, such as 80%, which is not specifically limited here.

[0064] Exemplarily, the data analysis model corresponding to the risk prediction type can be a generalized linear (GLM) model, the data analysis model corresponding to the causal analysis prediction type can be a Bayesian network model, the data analysis model corresponding to the fraud prediction type can be a support vector machine (SVM) model, and the data analysis model corresponding to the claims trend prediction type can be a long short-term memory network (LSTM) model.

[0065] Specifically, determine the similarity between the model type of each preset data analysis model and the claim prediction type; if the similarity between the model type of a preset data analysis model and the claim prediction type exceeds the preset similarity threshold, use the preset data analysis model as the target data analysis model; if the similarity between the model type of each preset data analysis model and the claim prediction type does not exceed the preset similarity threshold, redetermine the claim information and related claim information.

[0066] Exemplarily, if the preset similarity threshold is 90%, and the similarities between the model type of the preset data analysis model A and the preset data analysis model B and the claim prediction type are 95% and 50% respectively, at this time the similarity between the model type of the preset data analysis model A and the claim prediction type exceeds the preset similarity threshold, then the preset data analysis model A is used as the target data analysis model.

[0067] S104. Based on the target data analysis model, generate data analysis code according to user analysis requirements, claim information and its corresponding associated claim information.

[0068] The user analysis requirements may be the user's analysis requirements for claims data, such as the need for analysis reports and analysis feature graphs corresponding to the displayed content.

[0069] In some embodiments, the claim prediction type corresponding to the claim information and its corresponding associated claim information is determined; a data analysis code template is determined according to the claim prediction type; word segmentation and word meaning prediction processing are performed on the user's analysis requirements to obtain standard word segmentation information; based on the data analysis code template, a data analysis code is generated according to the standard word segmentation information. In this way, the user's natural language input can be understood, and efficient and accurate analysis codes can be generated according to the preset analysis theory. The code can also be customized according to the user's specific analysis requirements to ensure the pertinence and effectiveness of the analysis.

[0070] The data analysis code template may be a data analysis code common to each claim prediction type. The standard word segmentation information may be word segmentation information obtained by analyzing user analysis requirements and used to generate data analysis codes.

[0071] Specifically, the claim information and its corresponding associated claim information can be parsed and the type can be predicted, so as to obtain the claim prediction type of the claim information and its corresponding associated claim information; determine the data analysis code template corresponding to the claim prediction type; the text information corresponding to the user's analysis needs can be segmented to obtain multiple segmentations, and then the multiple segmentations are predicted to obtain the meaning prediction results; then the multiple segmentations are matched with the meaning prediction results, and the similarity between each segmentation and the standard segmentation in the standard segmentation database is calculated, and each segmentation is sorted according to the similarity to obtain the sorting result; the segmentation result is screened based on the sorting result to obtain standard segmentation information, and finally the standard segmentation information is input into the data analysis code template to generate the data analysis code.

[0072] S105. Based on the code interpreter, the target claims data is predicted according to the data analysis code to obtain claims analysis data.

[0073] The code interpreter may be a translator, whose main function is to interpret source code into computer executable instructions and execute these instructions immediately.

[0074] Specifically, the code interpreter will first read the data analysis code and store it in the memory. The code interpreter will perform lexical analysis on the data analysis code and decompose the data analysis code into lexical units, such as keywords, identifiers, operators, etc.; then, the code interpreter will perform syntax analysis on the lexical units, check whether the code conforms to the syntax rules, and generate the corresponding syntax tree; the code interpreter will traverse the syntax tree, convert each syntax node into computer executable instructions, and execute these instructions immediately. This process will be repeated until the program ends.

[0075] It should be noted that the code interpreter can adopt an environment such as Jupyter Notebook, so as to dynamically execute data analysis code such as Python code.

[0076] S106: Determine data features of the claims analysis data, and generate analysis reports and analysis feature graphs corresponding to the claims data based on the data features.

[0077] The data features may be data change patterns, data diversity, etc. The analysis report may include different types of reports for displaying analysis results of the claims data, and the analysis feature graph may include different types of feature graphs for displaying analysis results of the claims data.

[0078] In some embodiments, the report type and chart type corresponding to the claim data are determined according to the data characteristics; the analysis report corresponding to the claim data is generated based on the report type and the data characteristics; and the analysis feature graph corresponding to the claim data is generated based on the chart type and the data characteristics. In this way, the analysis report and analysis feature graph that best match the data characteristics can be generated for users to view.

[0079] The report type may be different display types of analysis reports, such as text reports, graphic reports, etc. The chart type may be different display types of analysis feature charts, such as scatter charts, bar charts, line charts, heat maps, etc.

[0080] For example, if the data features need to show the law of data changes, such as the difference between the actual claim amount and the predicted claim amount, then you can use visualization libraries such as Matplotlib and Seaborn to determine the report type as a text report based on the data features, and determine the chart type as a scatter plot. Finally, generate a text report corresponding to the claim data based on the report type and data features; generate a scatter plot corresponding to the claim data based on the chart type and data features.

[0081] The analysis method of claims data disclosed in the embodiment of the present application obtains claims data and user analysis requirements, and performs data cleaning processing on the claims data to obtain target claims data; analyzes the target claims data to obtain claims information, and determines related claims information based on the claims information; determines the target data analysis model from the model database based on the claims information and its corresponding related claims information; based on the target data analysis model, generates data analysis code according to user analysis requirements, claims information and its corresponding related claims information; based on the code interpreter, predicts the target claims data according to the data analysis code to obtain claims analysis data; determines the data features of the claims analysis data, and generates analysis reports and analysis feature graphs corresponding to the claims data according to the data features. This can greatly reduce manual operations and professional skills requirements, employees can complete data analysis tasks more efficiently, improve data analysis efficiency, and at the same time can deeply explore the value of claims data and improve data utilization, so as to better perform risk management and claims pricing and other businesses, and can also provide a comprehensive analysis perspective to effectively avoid misjudgment and waste of resources.

[0082] See also Figure 3 , Figure 3 It is a schematic block diagram of a claim data analysis device provided in one embodiment of the present application. The claim data analysis device can be configured in a server to execute the aforementioned claim data analysis method.

[0083] like Figure 3As shown, the claim data analysis device 200 includes: a data cleaning module 201, a related information determination module, a model determination module 203, a code generation module 204, a data prediction module 205 and a data analysis module 206.

[0084] The data cleaning module 201 is used to obtain the claim data and user analysis requirements, and perform data cleaning on the claim data to obtain target claim data;

[0085] The associated information determination module 202 is used to parse the target claim data to obtain claim information, and determine associated claim information according to the claim information;

[0086] A model determination module 203, for determining a target data analysis model from a model database according to the claim information and its corresponding associated claim information;

[0087] A code generation module 204 is used to generate data analysis code based on the target data analysis model, according to the user analysis requirements, the claim information and its corresponding associated claim information;

[0088] A data prediction module 205 is used to predict the target claim data based on the data analysis code based on a code interpreter to obtain claim analysis data;

[0089] The data analysis module 206 is used to determine the data characteristics of the claim analysis data, and generate an analysis report and an analysis characteristic diagram corresponding to the claim data according to the data characteristics.

[0090] In some embodiments, the data cleaning module 201 is also used to perform data type conversion processing on the claim data to obtain claim data that conforms to a preset data type; and perform missing value processing on the claim data that conforms to the preset data type to obtain target claim data.

[0091] In some embodiments, the associated information determination module 202 is also used to determine the claim type corresponding to the claim data based on the claim information; filter the claim information according to the claim type to obtain the associated information factor; traverse the information database and determine the associated claim information based on the associated information factor.

[0092] In some embodiments, the model determination module 203 is also used to determine the claim prediction type corresponding to the claim information and its corresponding associated claim information; obtain multiple preset data analysis models in the model database, and determine the target data analysis model from the multiple preset data analysis models based on the claim prediction type.

[0093] In some embodiments, the model determination module 203 is also used to obtain the model types of the multiple preset data analysis models; determine the similarity between the model type of each of the preset data analysis models and the claim prediction type; if the similarity between the model type of the preset data analysis model and the claim prediction type exceeds a preset similarity threshold, the preset data analysis model is used as the target data analysis model.

[0094] In some embodiments, the code generation module 204 is also used to determine the claim prediction type corresponding to the claim information and its corresponding associated claim information; determine the data analysis code template according to the claim prediction type; perform word segmentation and word meaning prediction processing on the user analysis requirements to obtain standard word segmentation information; and generate data analysis code based on the standard word segmentation information based on the data analysis code template.

[0095] In some embodiments, the data analysis module is also used to determine the report type and chart type corresponding to the claim data based on the data characteristics; generate an analysis report corresponding to the claim data based on the report type and the data characteristics; and generate an analysis feature graph corresponding to the claim data based on the chart type and the data characteristics.

[0096] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, modules and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0097] The method and apparatus of the present application can be used in many general or special computing system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer terminal devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices.

[0098] Exemplarily, the above method and apparatus may be implemented in the form of a computer program. The computer program may be implemented in the form of a computer program. Figure 4 Runs on the computer device shown.

[0099] See also Figure 4 , Figure 4 1 is a schematic diagram of a computer device provided in an embodiment of the present application. The computer device may be a server.

[0100] like Figure 4 As shown, the computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory may include a volatile storage medium, a non-volatile storage medium and an internal memory.

[0101] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any one of the claim data analysis methods.

[0102] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0103] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any method for analyzing claims data.

[0104] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that the structure of the computer device is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0105] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0106] Among them, in some embodiments, the processor is used to run a computer program stored in a memory to implement the following steps: obtain claim data and user analysis requirements, and perform data cleaning processing on the claim data to obtain target claim data; parse the target claim data to obtain claim information, and determine related claim information based on the claim information; determine a target data analysis model from a model database based on the claim information and its corresponding related claim information; based on the target data analysis model, generate a data analysis code according to the user analysis requirements, the claim information and its corresponding related claim information; based on a code interpreter, predict the target claim data according to the data analysis code to obtain claim analysis data; determine data features of the claim analysis data, and generate an analysis report and an analysis feature graph corresponding to the claim data based on the data features.

[0107] In some embodiments, the processor is further used to perform data type conversion processing on the claim data to obtain claim data that conforms to a preset data type; and perform missing value processing on the claim data that conforms to the preset data type to obtain target claim data.

[0108] In some embodiments, the processor is further used to determine the claim type corresponding to the claim data based on the claim information; filter the claim information according to the claim type to obtain associated information factors; traverse the information database to determine associated claim information based on the associated information factors.

[0109] In some embodiments, the processor is also used to determine the claim prediction type corresponding to the claim information and its corresponding associated claim information; obtain multiple preset data analysis models in the model database, and determine the target data analysis model from the multiple preset data analysis models based on the claim prediction type.

[0110] In some embodiments, the processor is also used to obtain the model types of the multiple preset data analysis models; determine the similarity between the model type of each of the preset data analysis models and the claim prediction type; if the similarity between the model type of the preset data analysis model and the claim prediction type exceeds a preset similarity threshold, then use the preset data analysis model as the target data analysis model.

[0111] In some embodiments, the processor is also used to determine the claim prediction type corresponding to the claim information and its corresponding associated claim information; determine the data analysis code template based on the claim prediction type; perform word segmentation and word meaning prediction processing on the user analysis requirements to obtain standard word segmentation information; and generate data analysis code based on the standard word segmentation information based on the data analysis code template.

[0112] In some embodiments, the processor is also used to determine the report type and chart type corresponding to the claim data based on the data characteristics; generate an analysis report corresponding to the claim data based on the report type and the data characteristics; and generate an analysis feature graph corresponding to the claim data based on the chart type and the data characteristics.

[0113] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions, and when the program instructions are executed, any one of the claims data analysis methods provided in the embodiments of the present application is implemented.

[0114] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the computer device.

[0115] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0116] The present invention refers to a new application model of computer technologies such as storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. of the blockchain language model. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the blockchain underlying platform, platform product service layer, and application service layer.

[0117] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for analyzing claims data, characterized in that: The method comprises: Obtaining claims data and user analysis requirements, and performing data cleaning on the claims data to obtain target claims data; Parsing the target claim data to obtain claim information, and determining related claim information based on the claim information; Determining a target data analysis model from a model database according to the claim information and its corresponding associated claim information; Based on the target data analysis model, generating data analysis code according to the user analysis requirements, the claim information and its corresponding associated claim information; Based on the code interpreter, predicting the target claims data according to the data analysis code to obtain claims analysis data; Determine data features of the claims analysis data, and generate analysis reports and analysis feature graphs corresponding to the claims data based on the data features.

2. The method according to claim 1, characterized in that The data cleaning process is performed on the claims data to obtain target claims data, including: Performing data type conversion processing on the claim data to obtain claim data that conforms to a preset data type; The missing value processing is performed on the claim data that meets the preset data type to obtain the target claim data.

3. The method according to claim 1, characterized in that The determining of associated claim information according to the claim information includes: Determining the claim type corresponding to the claim data according to the claim information; Screening the claim information according to the claim type to obtain a correlation information factor; The information database is traversed, and the associated claim information is determined according to the associated information factors.

4. The method according to claim 1, characterized in that: Determining a target data analysis model from a model database according to the claim information and its corresponding associated claim information includes: Determine the claim prediction type corresponding to the claim information and its corresponding associated claim information; Acquire multiple preset data analysis models in the model database, and determine a target data analysis model from the multiple preset data analysis models according to the claim prediction type.

5. The method according to claim 4, characterized in that Determining a target data analysis model from the plurality of preset data analysis models according to the claim prediction type includes: Obtaining model types of the multiple preset data analysis models; Determining the similarity between the model type of each of the preset data analysis models and the claim prediction type; If the similarity between the model type of the preset data analysis model and the claim prediction type exceeds a preset similarity threshold, the preset data analysis model is used as the target data analysis model.

6. The method according to claim 1, characterized in that The generating of data analysis code based on the target data analysis model according to the user analysis requirements, the claim information and its corresponding associated claim information includes: Determine the claim prediction type corresponding to the claim information and its corresponding associated claim information; Determine a data analysis code template according to the claim prediction type; Performing word segmentation and word meaning prediction processing on the user analysis requirements to obtain standard word segmentation information; Based on the data analysis code template, a data analysis code is generated according to the standard word segmentation information.

7. The method according to claim 1, characterized in that Generating an analysis report and an analysis feature graph corresponding to the claim data according to the data features includes: Determining the report type and chart type corresponding to the claim data according to the data characteristics; Generate an analysis report corresponding to the claims data based on the report type and the data characteristics; An analysis feature graph corresponding to the claims data is generated based on the graph type and the data feature.

8. A claim data analysis device, characterized in that: The claim data analysis device comprises: A data cleaning module is used to obtain claim data and user analysis requirements, and perform data cleaning on the claim data to obtain target claim data; A related information determination module, used for parsing the target claim data to obtain claim information, and determining related claim information according to the claim information; A model determination module, used to determine a target data analysis model from a model database according to the claim information and its corresponding associated claim information; A code generation module, for generating data analysis code based on the target data analysis model, according to the user analysis requirements, the claim information and its corresponding associated claim information; A data prediction module, used for predicting the target claims data based on the data analysis code based on a code interpreter to obtain claims analysis data; The data analysis module is used to determine the data characteristics of the claims analysis data, and generate an analysis report and an analysis characteristic diagram corresponding to the claims data according to the data characteristics.

9. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is configured to execute the computer program and implement, when executing the computer program: A method for analyzing claims data as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the method for analyzing claims data according to any one of claims 1 to 7.

Images