Business evaluation method, device and equipment and storage medium thereof

Abstract

The embodiment of the invention belongs to the technical field of financial science and technology, is applied to a claim settlement business scene, and relates to a business evaluation method, device and equipment and a storage medium thereof. Carrying out complexity calculation on the multi-dimensional data by adopting an improved Halstep method; according to a complexity calculation result, determining a complexity level corresponding to the multi-dimensional data; based on the complexity level, screening out a pre-trained business evaluation model corresponding to the corresponding level; and inputting the multi-dimensional data into the business evaluation model to obtain a business evaluation result. By calculating the complexity of the multi-dimensional data to be subjected to target business evaluation, the business evaluation models corresponding to different complexity levels are selected to perform business evaluation, graded processing and refinement are performed on the business evaluation, and the business evaluation efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology and is applied in claims settlement business scenarios, and in particular to a business assessment method, device, equipment and storage medium thereof. Background Art

[0002] Traditional complex claims analysis algorithms require a lot of manpower and time, and are prone to misjudgment. Traditional complex claims analysis is mainly based on expert experience and case analysis, which is inefficient and inaccurate.

[0003] In order to solve the above problems, existing claims assessment is mainly based on expert experience and case analysis to train large assessment models. However, the training of larger assessment models often involves a large amount of data. Moreover, in terms of claims cases, the data dimensions involved in different claims cases often vary greatly, which will cause the overall complexity of the assessment model to be high. When the model complexity is too high, it is easy to cause slow program execution and low assessment efficiency. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a business evaluation method, device, equipment and storage medium thereof to solve the problems that the existing business evaluation methods have certain limitations, resulting in a high overall complexity of the evaluation model, which easily leads to slow program execution and low evaluation efficiency.

[0005] In order to solve the above technical problems, the embodiment of the present application provides a service evaluation method, which adopts the following technical solution:

[0006] A business evaluation method comprises the following steps:

[0007] Obtain multi-dimensional data for target business evaluation;

[0008] Using an improved Halstead method to perform complexity calculation on the multi-dimensional data;

[0009] Determining the complexity level corresponding to the multi-dimensional data according to the complexity calculation result;

[0010] Based on the complexity level, selecting a pre-trained business evaluation model corresponding to the corresponding level;

[0011] The multi-dimensional data is input into the business evaluation model to obtain a business evaluation result.

[0012] Furthermore, the target business includes claims settlement business, and the step of obtaining multi-dimensional data to be evaluated for the target business specifically includes:

[0013] Acquire multi-dimensional data uploaded in advance by a user from a preset cache space, wherein the multi-dimensional data includes picture data, text data, and video data;

[0014] Calculating the data volume of the multi-dimensional data according to a preset data volume statistical rule;

[0015] The step of using the improved Halstead method to calculate the complexity of the multi-dimensional data specifically includes:

[0016] According to the preset improved Halstead method: Vol=L×V×σ, the complexity of the multidimensional data is calculated, wherein Vol represents the complexity of the multidimensional data, L represents the data volume of the multidimensional data, V represents the number of operation instructions involved in the multidimensional data, and σ represents a positive correlation adjustment factor. The larger the data volume of the multidimensional data, the greater the number of operation instructions involved in the multidimensional data, and L, V and σ are all greater than 0.

[0017] Furthermore, the step of calculating the data volume of the multi-dimensional data according to a preset data volume statistical rule specifically includes:

[0018] If the multi-dimensional data includes picture data, all picture data are filtered out;

[0019] Using the Haar detection algorithm, the claim damage areas respectively included in all the image data are detected, the total area of ​​the claim damage areas included in all the image data is counted, and the total area of ​​the claim damage areas is set as the data volume of all the image data;

[0020] If the multi-dimensional data includes text data, all text data are filtered out;

[0021] Performing word segmentation processing on all the text data according to a preset vocabulary form, and counting the total amount of the word segments, and setting the total amount of the word segments as the data amount of all the text data;

[0022] If the multi-dimensional data includes video data, all video data are filtered out;

[0023] Performing frame processing on all video data according to a preset frame interval, counting the total number of pictures after the frame processing, and taking the total number of pictures as the data amount of all video data;

[0024] Obtaining the data volume summary weights pre-set for the image data, text data, and video data, respectively;

[0025] According to the data volume aggregation weights corresponding to the image data, text data and video data respectively, the data volume of all the image data, the data volume of all the text data and the data volume of all the video data are cumulatively added and calculated to obtain the data volume corresponding to the multi-dimensional data.

[0026] Furthermore, before executing the step of determining the complexity level corresponding to the multi-dimensional data according to the complexity calculation result, the method further includes:

[0027] Different complexity levels are pre-set for different complexity intervals, wherein when setting, the greater the complexity value corresponding to the complexity interval, the higher the corresponding complexity level.

[0028] Furthermore, before executing the step of screening out the pre-trained business evaluation model corresponding to the corresponding level based on the complexity level, the method further includes:

[0029] Obtain multi-dimensional data uploaded by historical batch claims users for claims assessment as training sample data;

[0030] Performing complexity calculation on the multi-dimensional data corresponding to each claim settlement user in the training sample data;

[0031] Determine the complexity level corresponding to each claims user based on the complexity calculation results;

[0032] Summarize and organize the multi-dimensional data of claim users with the same complexity level to obtain training sub-sample data corresponding to all complexity levels;

[0033] Constructing claims business assessment models to be trained in a number equal to the number of complexity levels, wherein the model structures of all claims business assessment models to be trained are the same;

[0034] The training sub-sample data corresponding to different complexity levels are input into different claims business assessment models to be trained, and model training is performed to obtain pre-trained claims business assessment models corresponding to different complexity levels.

[0035] Furthermore, before executing the step of constructing a number of claims business assessment models to be trained equal to the number of complexity levels, the method further includes:

[0036] Obtain the claim result data of the historical batch claim users;

[0037] Summarize and organize the claim result data of claim users with the same complexity level to obtain the claim result summary data corresponding to all complexity levels;

[0038] After executing the step of constructing the claims business assessment models to be trained in a number equal to the number of complexity levels, the method further includes:

[0039] Establish a mapping relationship between the complexity level and the claims business assessment model to be trained.

[0040] Furthermore, the step of inputting the training sub-sample data corresponding to different complexity levels into different claims business assessment models to be trained, performing model training, and obtaining pre-trained claims business assessment models corresponding to different complexity levels specifically includes:

[0041] According to the mapping relationship between the complexity level and the claims business evaluation model to be trained, the training sub-sample data corresponding to different complexity levels are input into the corresponding claims business evaluation model to be trained;

[0042] According to the mapping relationship between the complexity level and the claims business evaluation model to be trained, the summary data of claims results corresponding to different complexity levels are input into the corresponding claims business evaluation model to be trained;

[0043] Through different claims business evaluation models to be trained, a comprehensive analysis method is used to construct the evaluation and prediction relationship between the training sub-sample data of different complexity levels and the claims result summary data;

[0044] The claims business evaluation model constructed with the evaluation prediction relationship is used as the claims business evaluation model pre-trained at the corresponding complexity level.

[0045] In order to solve the above technical problems, the embodiment of the present application also provides a service evaluation device, which adopts the following technical solution:

[0046] A service evaluation device, comprising:

[0047] A business evaluation data acquisition module is used to acquire multi-dimensional data to be evaluated on the target business;

[0048] A complexity calculation module, used for performing complexity calculation on the multi-dimensional data using an improved Halstead method;

[0049] A complexity level determination module, used to determine the complexity level corresponding to the multi-dimensional data according to the complexity calculation result;

[0050] A business evaluation model screening module, used to screen out pre-trained business evaluation models corresponding to the corresponding level based on the complexity level;

[0051] The business evaluation execution module is used to input the multi-dimensional data into the business evaluation model to obtain a business evaluation result.

[0052] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0053] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the above-mentioned business evaluation method when executing the computer-readable instructions.

[0054] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0055] A computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the business evaluation method described above are implemented.

[0056] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0057] The business evaluation method described in the embodiment of the present application is to obtain multi-dimensional data for target business evaluation; use the improved Halstead method to calculate the complexity of the multi-dimensional data; determine the complexity level corresponding to the multi-dimensional data according to the complexity calculation result; based on the complexity level, screen out the pre-trained business evaluation model corresponding to the corresponding level; input the multi-dimensional data into the business evaluation model to obtain the business evaluation result. By calculating the complexity of the multi-dimensional data for target business evaluation, the business evaluation model corresponding to different complexity levels is selected for business evaluation, and the business evaluation is graded and refined, which improves the efficiency of business evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. 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.

[0059] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0060] Figure 2 is a flow chart of an embodiment of a business evaluation method according to the present application;

[0061] Figure 3 yes Figure 2 A flowchart of a specific embodiment of step 201 is shown;

[0062] Figure 4 yes Figure 3 A flowchart of a specific embodiment of step 302 is shown;

[0063] Figure 5 It is a flowchart of a specific embodiment of processing the claims assessment data required for training the business assessment model in the business assessment method described in this application;

[0064] Figure 6 yes Figure 5 A flowchart of a specific embodiment of step 506 is shown;

[0065] Figure 7 is a structural diagram of an embodiment of a service evaluation device according to the present application;

[0066] Figure 8 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0067] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0068] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0069] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0070] like Figure 1As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0071] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0072] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0073] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0074] It should be noted that the service evaluation method provided in the embodiment of the present application is generally executed by a server, and accordingly, the service evaluation device is generally arranged in the server.

[0075] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0076] Continue to refer Figure 2 , shows a flow chart of an embodiment of a service evaluation method according to the present application. The service evaluation method comprises the following steps:

[0077] Step 201: Acquire multi-dimensional data for target business evaluation.

[0078] In this embodiment, the target business includes insurance claims business, such as car insurance claims business, and the multi-dimensional data includes text data, image data or video data provided by the parties involved in the car insurance accident.

[0079] In the auto insurance claims business, the more parties involved in the auto insurance accident, the more text data, image data or video data, the more factors that need to be considered in the claims, and the more complicated the claims processing.

[0080] By acquiring multi-dimensional data for the target business assessment to be conducted, it is possible to fully conduct a claims assessment in combination with the multi-dimensional data. At the same time, the multi-dimensional data can also be used to assess the complexity of the claims.

[0081] Step 202: Using an improved Halstead method to perform complexity calculation on the multi-dimensional data.

[0082] The Halstead method is used in software measurement to evaluate the complexity of a program, the workload of program development, and the difficulty of development. It can help developers optimize the code structure and improve the maintainability and readability of the code.

[0083] The Halstead method uses the operators and operands in a program to jointly characterize the complexity of the program. Generally speaking, the more operators and operands involved, the greater the complexity of the program. At this time, it is necessary to consider optimizing the program.

[0084] The improvement idea of ​​this application is to calculate the complexity of claim assessment by combining the amount of data and the number of operation instructions involved in the multi-dimensional data, and the Halstead method can be used for improvement, that is, the more the amount of data and the number of operation instructions involved in the multi-dimensional data, the higher the complexity of claim assessment. And correspondingly introduce positive correlation factors to ensure computer recognizability.

[0085] Step 203: Determine the complexity level corresponding to the multi-dimensional data according to the complexity calculation result.

[0086] Step 204: based on the complexity level, select the pre-trained business evaluation model corresponding to the corresponding level.

[0087] In this embodiment, business assessment models are trained separately for different complexity levels, so that when the multi-dimensional data corresponding to the target claims business is subsequently obtained, it is only necessary to first determine the complexity of the multi-dimensional data, and select the pre-trained claims assessment model corresponding to the corresponding level to perform claims assessment. Claims assessment is performed in a targeted manner based on the complexity of the data, thereby improving the efficiency of claims assessment.

[0088] Step 205: input the multi-dimensional data into the business evaluation model to obtain a business evaluation result.

[0089] In this embodiment, by obtaining multi-dimensional data to be evaluated for target business; using the improved Halstead method to calculate the complexity of the multi-dimensional data; determining the complexity level corresponding to the multi-dimensional data according to the complexity calculation result; based on the complexity level, screening out the pre-trained business evaluation model corresponding to the corresponding level; inputting the multi-dimensional data into the business evaluation model to obtain the business evaluation result. By calculating the complexity of the multi-dimensional data to be evaluated for target business, the business evaluation model corresponding to different complexity levels is selected for business evaluation, and the business evaluation is graded and refined, thereby improving the efficiency of business evaluation.

[0090] In this embodiment, the target business includes claims settlement business.

[0091] Continue to refer Figure 3 , in some optional implementations, Figure 3 yes Figure 2 The flowchart of a specific embodiment of step 201 shown includes the following steps:

[0092] Step 301, obtaining multi-dimensional data pre-uploaded by a user from a preset cache space, wherein the multi-dimensional data includes picture data, text data and video data;

[0093] Step 302: Calculate the data volume of the multi-dimensional data according to a preset data volume statistical rule.

[0094] By calculating the data volume of the multi-dimensional data according to a preset data volume statistical rule, it is convenient to calculate the complexity of the multi-dimensional data.

[0095] In this embodiment, the step of using the improved Halstead method to calculate the complexity of the multidimensional data specifically includes: calculating the complexity of the multidimensional data according to the preset improved Halstead method: Vol=L×V×σ, wherein Vol represents the complexity of the multidimensional data, L represents the data volume of the multidimensional data, V represents the number of operation instructions involved in the multidimensional data, σ represents a positive correlation adjustment factor, the larger the data volume of the multidimensional data, the greater the number of operation instructions involved in the multidimensional data, and L, V and σ are all greater than 0.

[0096] Specifically, the number of operation instructions involved in the multi-dimensional data can be obtained by counting the number of execution instructions in the program.

[0097] Continue to refer Figure 4, in some optional implementations, Figure 4 yes Figure 3 The flowchart of a specific embodiment of step 302 shown includes the following steps:

[0098] Step 401: If the multi-dimensional data includes picture data, all picture data are filtered out;

[0099] Step 402, using the Haar detection algorithm to detect the claim damage areas respectively contained in all the image data, counting the total area of ​​the claim damage areas contained in all the image data, and setting the total area of ​​the claim damage areas as the data volume of all the image data;

[0100] Step 403: If the multi-dimensional data includes text data, all text data are filtered out;

[0101] Step 404, performing word segmentation processing on all the text data according to a preset vocabulary form, and counting the total amount of the word segments, and setting the total amount of the word segments as the data amount of all the text data;

[0102] Step 405: If the multi-dimensional data includes video data, all video data are filtered out;

[0103] Step 406, performing frame processing on all video data according to a preset frame interval, counting the total number of pictures after the frame processing, and taking the total number of pictures as the data amount of all video data;

[0104] Step 407, obtaining the data volume summary weights pre-set for the image data, text data, and video data, respectively;

[0105] Step 408, according to the data volume aggregation weights corresponding to the image data, text data and video data respectively, the data volume of all the image data, the data volume of all the text data and the data volume of all the video data are cumulatively summed up to obtain the data volume corresponding to the multi-dimensional data.

[0106] By respectively calculating the data volumes of data in different formats and then performing cumulative sum operations, the data volumes corresponding to the multi-dimensional data are obtained, so as to obtain the complexity of the multi-dimensional data.

[0107] In this embodiment, before executing the step of determining the complexity level corresponding to the multidimensional data based on the complexity calculation result, the method also includes: pre-setting different complexity levels for different complexity intervals, wherein, when setting, the larger the complexity value corresponding to the complexity interval, the higher the corresponding complexity level.

[0108] Continue to refer Figure 5In some optional implementations, before step 204, a step of processing the claims assessment data required for training the business assessment model is also included. Figure 5 It is a flowchart of a specific embodiment of processing the claims assessment data required for training the business assessment model in the business assessment method described in the present application, comprising the following steps:

[0109] Step 501, obtaining multi-dimensional data uploaded by historical batch claim users for claim assessment as training sample data;

[0110] Step 502, performing complexity calculation on the multi-dimensional data corresponding to each claim settlement user in the training sample data;

[0111] Step 503, determining the complexity level corresponding to each claim settlement user according to the complexity calculation result;

[0112] Step 504, summarizing and arranging the multi-dimensional data of claim users with the same complexity level to obtain training sub-sample data corresponding to all complexity levels;

[0113] Step 505, constructing claims business assessment models to be trained in an amount equal to the number of complexity levels, wherein the model structures of all claims business assessment models to be trained are the same;

[0114] Step 506, input the training sub-sample data corresponding to different complexity levels into different claims business assessment models to be trained, perform model training, and obtain pre-trained claims business assessment models corresponding to different complexity levels.

[0115] By calculating the complexity of the multi-dimensional data uploaded by historical batch claims users for claims assessment, and aggregating the multi-dimensional data of the same complexity level together, we train pre-trained claims business assessment models corresponding to different complexity levels. This makes it easier to select the claims business assessment model of the corresponding level for the multi-dimensional data of different complexity levels uploaded by the claims users during the subsequent actual claims assessment.

[0116] In this embodiment, before executing the step of constructing a number of claims business assessment models to be trained that is equal to the number of complexity levels, the method also includes: obtaining the claims result data of the historical batch claims users; summarizing and collating the claims result data of claims users of the same complexity level to obtain the claims result summary data corresponding to all complexity levels.

[0117] By summarizing and organizing the claim result data of claim users with the same complexity level, we can obtain the claim result summary data corresponding to all complexity levels, so that when training the model, we can obtain the evaluation and prediction relationship between the multi-dimensional data of different complexity levels used for claim evaluation and the corresponding claim result summary data.

[0118] In this embodiment, after executing the step of constructing a number of claims business assessment models to be trained that is equal to the number of complexity levels, the method further includes: establishing a mapping relationship between the complexity levels and the claims business assessment models to be trained.

[0119] Specifically, the mapping relationship between the complexity level and the claims business assessment model to be trained is established by numbering different claims business assessment models to be trained so that each number corresponds to a complexity level.

[0120] Continue to refer Figure 6 , in some optional implementations, Figure 6 yes Figure 5 The flowchart of a specific embodiment of step 506 shown includes the following steps:

[0121] Step 601, according to the mapping relationship between the complexity level and the claims business evaluation model to be trained, the training sub-sample data corresponding to different complexity levels are input into the corresponding claims business evaluation model to be trained;

[0122] Step 602: according to the mapping relationship between the complexity level and the claims business evaluation model to be trained, the summary data of claims results corresponding to different complexity levels are input into the corresponding claims business evaluation model to be trained;

[0123] Step 603, using different claims business evaluation models to be trained, using a comprehensive analysis method to respectively construct evaluation prediction relationships between training sub-sample data of different complexity levels and claim result summary data;

[0124] Step 604: The claims business evaluation model constructed based on the evaluation prediction relationship is used as the claims business evaluation model pre-trained at the corresponding complexity level.

[0125] In this embodiment, the step of inputting the multi-dimensional data into the business evaluation model to obtain the business evaluation result specifically includes: performing claim evaluation and prediction on the multi-dimensional data according to the evaluation prediction relationship possessed by the business evaluation model to obtain the claim evaluation prediction result.

[0126] In this embodiment, business assessment models are trained separately for different complexity levels, so that when the multi-dimensional data corresponding to the target claims business is subsequently obtained, it is only necessary to first determine the complexity of the multi-dimensional data, and select the pre-trained claims assessment model corresponding to the corresponding level to perform claims assessment. Claims assessment is performed in a targeted manner based on the complexity of the data, thereby improving the efficiency of claims assessment.

[0127] This application obtains multi-dimensional data for target business evaluation; uses the improved Halstead method to calculate the complexity of the multi-dimensional data; determines the complexity level corresponding to the multi-dimensional data according to the complexity calculation result; based on the complexity level, screens out the pre-trained business evaluation model corresponding to the corresponding level; inputs the multi-dimensional data into the business evaluation model to obtain the business evaluation result. By calculating the complexity of the multi-dimensional data for target business evaluation, the business evaluation model corresponding to different complexity levels is selected for business evaluation, and the business evaluation is graded and refined, which improves the efficiency of business evaluation.

[0128] 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.

[0129] 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.

[0130] In an embodiment of the present application, multi-dimensional data for target business evaluation is obtained; the complexity of the multi-dimensional data is calculated using an improved Halstead method; the complexity level corresponding to the multi-dimensional data is determined according to the complexity calculation result; based on the complexity level, a pre-trained business evaluation model corresponding to the corresponding level is screened out; the multi-dimensional data is input into the business evaluation model to obtain a business evaluation result. By calculating the complexity of the multi-dimensional data for target business evaluation, business evaluation models corresponding to different complexity levels are selected for business evaluation, and hierarchical processing and refinement are performed on the business evaluation, thereby improving the efficiency of business evaluation.

[0131] Further references Figure 7 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a service evaluation device, and the embodiment of the device is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0132] like Figure 7 As shown, the service evaluation device 700 described in this embodiment includes: a service evaluation data acquisition module 701, a complexity calculation module 702, a complexity level determination module 703, a service evaluation model screening module 704 and a service evaluation execution module 705. Among them:

[0133] The business evaluation data acquisition module 701 is used to acquire multi-dimensional data to be evaluated on the target business;

[0134] A complexity calculation module 702, configured to perform complexity calculation on the multi-dimensional data using an improved Halstead method;

[0135] A complexity level determination module 703 is used to determine the complexity level corresponding to the multi-dimensional data according to the complexity calculation result;

[0136] A business evaluation model screening module 704 is used to screen out pre-trained business evaluation models corresponding to the corresponding level based on the complexity level;

[0137] The business evaluation execution module 705 is used to input the multi-dimensional data into the business evaluation model to obtain a business evaluation result.

[0138] This application obtains multi-dimensional data for target business evaluation; uses the improved Halstead method to calculate the complexity of the multi-dimensional data; determines the complexity level corresponding to the multi-dimensional data according to the complexity calculation result; based on the complexity level, screens out the pre-trained business evaluation model corresponding to the corresponding level; inputs the multi-dimensional data into the business evaluation model to obtain the business evaluation result. By calculating the complexity of the multi-dimensional data for target business evaluation, the business evaluation model corresponding to different complexity levels is selected for business evaluation, and the business evaluation is graded and refined, which improves the efficiency of business evaluation.

[0139] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0140] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0141] To solve the above technical problems, the present application also provides a computer device. Figure 8 , Figure 8 This is a basic structural block diagram of the computer device in this embodiment.

[0142] The computer device 8 includes a memory 8a, a processor 8b, and a network interface 8c which are interconnected through a system bus. It should be noted that: Figure 8 Only a computer device 8 having a component memory 8a, a processor 8b, and a network interface 8c is shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital processor (DSP), an embedded device, etc.

[0143] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0144] The memory 8a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 8a can be an internal storage unit of the computer device 8, such as a hard disk or memory of the computer device 8. In other embodiments, the memory 8a can also be an external storage device of the computer device 8, such as a plug-in hard disk equipped on the computer device 8, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 8a can also include both the internal storage unit of the computer device 8 and its external storage device. In this embodiment, the memory 8a is generally used to store the operating system and various application software installed on the computer device 8, such as a computer-readable instruction of a business evaluation method, etc. In addition, the memory 8a can also be used to temporarily store various types of data that have been output or are to be output.

[0145] The processor 8b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 8b is generally used to control the overall operation of the computer device 8. In this embodiment, the processor 8b is used to run the computer-readable instructions stored in the memory 8a or process data, such as computer-readable instructions for running the business evaluation method.

[0146] The network interface 8c may include a wireless network interface or a wired network interface. The network interface 8c is generally used to establish a communication connection between the computer device 8 and other electronic devices.

[0147] The computer device proposed in this embodiment belongs to the field of financial technology and is used in claims business scenarios. This application obtains multi-dimensional data for target business evaluation; uses the improved Halstead method to calculate the complexity of the multi-dimensional data; determines the complexity level corresponding to the multi-dimensional data according to the complexity calculation result; based on the complexity level, screens out the pre-trained business evaluation model corresponding to the corresponding level; inputs the multi-dimensional data into the business evaluation model to obtain the business evaluation result. By calculating the complexity of the multi-dimensional data for target business evaluation, the business evaluation model corresponding to different complexity levels is selected for business evaluation, and the business evaluation is graded and refined, which improves the efficiency of business evaluation.

[0148] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by a processor to enable the processor to perform the steps of the business evaluation method as described above.

[0149] The computer-readable storage medium proposed in this embodiment belongs to the field of financial technology and is applied to claims business scenarios. This application obtains multi-dimensional data for target business evaluation; uses the improved Halstead method to perform complexity calculation on the multi-dimensional data; determines the complexity level corresponding to the multi-dimensional data according to the complexity calculation result; based on the complexity level, screens out the pre-trained business evaluation model corresponding to the corresponding level; inputs the multi-dimensional data into the business evaluation model to obtain the business evaluation result. By calculating the complexity of the multi-dimensional data for target business evaluation, the business evaluation model corresponding to different complexity levels is selected for business evaluation, and the business evaluation is graded and refined, which improves the efficiency of business evaluation.

[0150] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0151] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A business evaluation method, characterized in that: The steps include: Obtain multi-dimensional data for target business evaluation; Using an improved Halstead method to perform complexity calculation on the multi-dimensional data; Determining the complexity level corresponding to the multi-dimensional data according to the complexity calculation result; Based on the complexity level, selecting a pre-trained business evaluation model corresponding to the corresponding level; The multi-dimensional data is input into the business evaluation model to obtain a business evaluation result.

2. The business evaluation method according to claim 1, characterized in that: The target business includes claims settlement business, and the step of obtaining multi-dimensional data to be evaluated for the target business specifically includes: Acquire multi-dimensional data uploaded in advance by a user from a preset cache space, wherein the multi-dimensional data includes picture data, text data, and video data; Calculating the data volume of the multi-dimensional data according to a preset data volume statistical rule; The step of using the improved Halstead method to calculate the complexity of the multi-dimensional data specifically includes: According to the preset improved Halstead method: Vol=L×V×σ, the complexity of the multidimensional data is calculated, wherein Vol represents the complexity of the multidimensional data, L represents the data volume of the multidimensional data, V represents the number of operation instructions involved in the multidimensional data, and σ represents a positive correlation adjustment factor. The larger the data volume of the multidimensional data, the greater the number of operation instructions involved in the multidimensional data, and L, V and σ are all greater than 0.

3. The business evaluation method according to claim 2, characterized in that: The step of calculating the data volume of the multi-dimensional data according to a preset data volume statistical rule specifically includes: If the multi-dimensional data includes picture data, all picture data are filtered out; Using the Haar detection algorithm, the claim damage areas respectively included in all the image data are detected, the total area of ​​the claim damage areas included in all the image data is counted, and the total area of ​​the claim damage areas is set as the data volume of all the image data; If the multi-dimensional data includes text data, all text data are filtered out; Performing word segmentation processing on all the text data according to a preset vocabulary form, and counting the total amount of the word segments, and setting the total amount of the word segments as the data amount of all the text data; If the multi-dimensional data includes video data, all video data are filtered out; Performing frame processing on all video data according to a preset frame interval, counting the total number of pictures after the frame processing, and taking the total number of pictures as the data amount of all video data; Obtaining the data volume summary weights pre-set for the image data, text data, and video data, respectively; According to the data volume aggregation weights corresponding to the image data, text data and video data respectively, the data volume of all the image data, the data volume of all the text data and the data volume of all the video data are cumulatively added and calculated to obtain the data volume corresponding to the multi-dimensional data.

4. The service evaluation method according to claim 1 or 2, characterized in that: Before executing the step of determining the complexity level corresponding to the multi-dimensional data according to the complexity calculation result, the method further includes: Different complexity levels are pre-set for different complexity intervals, wherein when setting, the greater the complexity value corresponding to the complexity interval, the higher the corresponding complexity level.

5. The service evaluation method according to claim 1 or 2, characterized in that: Before executing the step of selecting the pre-trained business evaluation model corresponding to the corresponding level based on the complexity level, the method further includes: Obtain multi-dimensional data uploaded by historical batch claims users for claims assessment as training sample data; Performing complexity calculation on the multi-dimensional data corresponding to each claim settlement user in the training sample data; Determine the complexity level corresponding to each claims user based on the complexity calculation results; Summarize and organize the multi-dimensional data of claim users with the same complexity level to obtain training sub-sample data corresponding to all complexity levels; Constructing claims business assessment models to be trained in a number equal to the number of complexity levels, wherein the model structures of all claims business assessment models to be trained are the same; The training sub-sample data corresponding to different complexity levels are input into different claims business assessment models to be trained, and model training is performed to obtain pre-trained claims business assessment models corresponding to different complexity levels.

6. The service evaluation method according to claim 5, characterized in that: Before executing the step of constructing a number of claims business assessment models to be trained equal to the number of complexity levels, the method further includes: Obtain the claim result data of the historical batch claim users; Summarize and organize the claim result data of claim users with the same complexity level to obtain the claim result summary data corresponding to all complexity levels; After executing the step of constructing the claims business assessment models to be trained in a number equal to the number of complexity levels, the method further includes: Establish a mapping relationship between the complexity level and the claims business assessment model to be trained.

7. The service evaluation method according to claim 6, characterized in that: The step of inputting the training sub-sample data corresponding to different complexity levels into different claims business assessment models to be trained, performing model training, and obtaining pre-trained claims business assessment models corresponding to different complexity levels specifically includes: According to the mapping relationship between the complexity level and the claims business evaluation model to be trained, the training sub-sample data corresponding to different complexity levels are input into the corresponding claims business evaluation model to be trained; According to the mapping relationship between the complexity level and the claims business evaluation model to be trained, the summary data of claims results corresponding to different complexity levels are input into the corresponding claims business evaluation model to be trained; Through different claims business evaluation models to be trained, a comprehensive analysis method is used to construct the evaluation and prediction relationship between the training sub-sample data of different complexity levels and the claims result summary data; The claims business evaluation model constructed with the evaluation prediction relationship is used as the claims business evaluation model pre-trained at the corresponding complexity level.

8. A service evaluation device, characterized in that: include: A business evaluation data acquisition module is used to acquire multi-dimensional data to be evaluated on the target business; A complexity calculation module, used for performing complexity calculation on the multi-dimensional data using an improved Halstead method; A complexity level determination module, used to determine the complexity level corresponding to the multi-dimensional data according to the complexity calculation result; A business evaluation model screening module, used to screen out pre-trained business evaluation models corresponding to the corresponding level based on the complexity level; The business evaluation execution module is used to input the multi-dimensional data into the business evaluation model to obtain a business evaluation result.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the business evaluation method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the service evaluation method according to any one of claims 1 to 7 are implemented.

Images