Car insurance pricing method and device, computer equipment and storage medium
By receiving instructions to intercept and evaluate the information of the auto insurance pricing model, efficient model adjustment and batch pricing are achieved when insurance pricing scenarios change, solving the problems of complexity and workload of model debugging in the existing technology, and improving efficiency.
Patent Information
- Application Number
- CN202411017080.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-26
- Publication Date
- 2024-11-15
AI Technical Summary
Developers need to frequently rewrite modeling strategies and model training during model construction and debugging, resulting in high workload and low efficiency, especially when insurance pricing scenarios change, existing technologies are difficult to effectively deal with.
Provide a method of pricing for auto insurance, which intercepts pre-constructed adjustment model and initial model information by receiving instructions, and conducts risk assessment based on this information. When the risk assessment results meet expectations, the adjustment model is used as the target decision model to perform batch pricing tasks, which reduces the The complexity and workload of model debugging.
It solves the problem that developers need to retrain when the model fails to achieve the expected results, simplifies the model debugging process, improves work efficiency, and reduces the workload in the modeling process.
Smart Images

Figure CN118967333A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the fields of financial technology and data processing, and in particular to a method, device, computer equipment and storage medium for pricing automobile insurance. Background Art
[0002] In the financial field, insurance pricing has always been a key issue in the industry, and with the further development of the times, the factors affecting insurance pricing are also changing. Therefore, developers need to rebuild specific models or retrain the original models based on the changing factors.
[0003] However, rebuilding a specific model or retraining the existing model requires developers to rewrite the modeling strategy corresponding to the new business scenario in the system background, and the model needs to be re-debugged when it fails to achieve the expected results, which greatly increases the workload in the modeling process. Summary of the invention
[0004] The main purpose of the present invention is to provide a method, device, computer equipment and storage medium for pricing automobile insurance, aiming to solve the technical problem of complex model debugging when developers build models for different models.
[0005] To achieve the above object, the present invention provides a method for pricing automobile insurance, the method comprising:
[0006] receiving a first instruction, wherein the first instruction is used to intercept information of a pre-built adjustment model, wherein the adjustment model is a model obtained by adjusting the pre-built initial model;
[0007] In response to the first instruction, intercepting adjustment model information corresponding to the adjustment model and initial model information corresponding to the initial model;
[0008] Performing risk assessment on the adjustment model based on the adjustment model information and the initial model information to obtain a risk assessment result corresponding to the adjustment model;
[0009] When the risk assessment result meets the expected result, the adjustment model is used as the target decision model to execute the batch pricing task.
[0010] Optionally, intercepting the adjustment model information corresponding to the adjustment model and the initial model information corresponding to the initial model includes:
[0011] intercepting adjustment model information corresponding to the adjustment model, wherein the adjustment model information includes an adjustment factor, an adjustment calculation node, and a second execution relationship, wherein the second execution relationship is used to characterize an execution relationship between the adjustment calculation node and the adjustment factor;
[0012] Acquire initial model information corresponding to the initial model, wherein the initial model information includes an initial factor, an initial computing node, and a first execution relationship, wherein the first execution relationship is used to characterize an execution relationship between the initial computing node and the initial factor;
[0013] Determine a front-end rendering component based on the adjustment factor, the adjustment computing node, the second execution relationship, the initial factor, the initial computing node, and the first execution relationship;
[0014] The front-end rendering component is called to build a model adjustment page.
[0015] Optionally, performing risk assessment on the adjustment model based on the adjustment model information and the initial model information to obtain a risk assessment result corresponding to the adjustment model;
[0016] Obtaining a first weight value assigned to the initial factor in the first execution relationship and an initial probability value corresponding to the initial calculation node;
[0017] Perform risk assessment calculation based on the first weight value and the initial probability value to obtain an initial risk value corresponding to the initial model;
[0018] Acquire a second weight value assigned to the adjustment factor in the second execution relationship, and an adjustment probability value corresponding to the adjustment calculation node;
[0019] A risk assessment calculation is performed based on the second weight value and the adjusted probability value to obtain an adjusted risk value corresponding to the adjustment model.
[0020] Optionally, after performing risk assessment calculation based on the adjusted probability value of the second weight value to obtain the adjusted risk value corresponding to the adjustment model, the method further includes:
[0021] Obtaining a correlation interval corresponding to the initial probability value;
[0022] determining whether a difference between the adjusted risk value and the initial risk value exists within a relevant interval;
[0023] If so, determining that the adjustment factor corresponding to the adjustment model is related to the initial factor;
[0024] If it does not exist, the adjustment factor corresponding to the adjustment model will be deleted.
[0025] Optionally, after determining that the adjustment factor corresponding to the adjustment model is related to the initial factor, the method further comprises:
[0026] Obtain the preset risk object determination table;
[0027] Determine whether the difference between the initial risk result and the adjusted risk result is in the high risk interval of the risk determination object table;
[0028] If yes, then generate a high-risk verification workflow corresponding to the batch pricing task;
[0029] If not, a standard approval workflow corresponding to the batch pricing task is generated.
[0030] Optionally, before extracting and calling the front-end rendering component to build the model adjustment page, the method further includes:
[0031] The first design page includes a first design page for configuring parameters, and the first design page includes a first display part and a second display part
[0032] Acquire the initial model information and adjustment model information input by the user in the first display part;
[0033] The second display part is dynamically adjusted according to the initial model information and the adjustment model information.
[0034] In addition, to achieve the above-mentioned purpose, the present invention further provides a vehicle insurance pricing device, the vehicle insurance pricing adjustment device comprising:
[0035] An instruction receiving module, used for receiving a first instruction, wherein the first instruction is used for intercepting information of a pre-built adjustment model, wherein the adjustment model is a model obtained by adjusting the pre-built initial model;
[0036] a data interception module, configured to intercept, in response to the first instruction, adjustment model information corresponding to the adjustment model and initial model information corresponding to the initial model;
[0037] A risk assessment module, configured to perform risk assessment on the adjustment model based on the adjustment model information and the initial model information, and obtain a risk assessment result corresponding to the adjustment model;
[0038] The task execution module is used to execute the batch pricing task by using the adjustment model as the target decision model when the risk assessment result meets the expected result.
[0039] Optionally, the data interception module intercepts the subunit, obtains the subunit, determines the subunit and constructs the subunit, and the device includes:
[0040] The interception subunit is used to intercept the adjustment model information corresponding to the adjustment model, wherein the adjustment model information includes an adjustment factor, an adjustment calculation node, and a second execution relationship, and the second execution relationship is used to characterize the execution relationship between the adjustment calculation node and the adjustment factor;
[0041] The acquisition subunit is used to acquire initial model information corresponding to the initial model, wherein the initial model information includes initial factors, initial computing nodes, and a first execution relationship, and the first execution relationship is used to characterize the execution relationship between the initial computing nodes and the initial factors;
[0042] The determining subunit is used to determine the front-end rendering component based on the adjustment factor, the adjustment computing node, the second execution relationship, the initial factor, the initial computing node and the first execution relationship;
[0043] The construction subunit is used to call the front-end rendering component to build a model adjustment page.
[0044] 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:
[0045] The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods for adjusting vehicle insurance pricing proposed in the embodiments of the present application are implemented.
[0046] 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:
[0047] The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of any one of the methods for adjusting vehicle insurance pricing proposed in the embodiments of the present application are implemented.
[0048] Compared with the prior art, the embodiments of the present application have the following beneficial effects:
[0049] The present invention provides a method, device, computer equipment and storage medium for pricing auto insurance. The above-mentioned auto insurance pricing adjustment method includes: receiving a first instruction, the first instruction is used to intercept information of a pre-built adjustment model, the adjustment model is a model obtained after adjusting the pre-built initial model; in response to the first instruction, intercepting the adjustment model information corresponding to the adjustment model, and the initial model information corresponding to the initial model; based on the adjustment model information and the initial model information, the adjustment model is risk evaluated to obtain the risk evaluation result corresponding to the adjustment model; when the risk evaluation result meets the expected result, the adjustment model is used as the target decision model to perform the batch pricing task. It solves the problem that developers need to retrain when the model cannot achieve the expected effect, reduces the difficulty of debugging the model, and improves the debugging efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0050] 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.
[0051] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;
[0052] Figure 2 is a flow chart of a method for adjusting auto insurance pricing provided by an embodiment of the present invention;
[0053] Figure 3 is a schematic structural diagram of an embodiment of a computer device according to the present application;
[0054] Figure 4 This is a basic structural block diagram of the computer device in this embodiment. DETAILED DESCRIPTION
[0055] The method for determining the data format provided by the embodiment of the present invention is applied to a data processing system. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally 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" in the specification and claims of the present application and the above-mentioned drawings and any variations thereof 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.
[0056] 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.
[0057] 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.
[0058] like Figure 1As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.
[0059] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social online platform software, etc.
[0060] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.
[0061] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .
[0062] It should be noted that the auto insurance pricing adjustment method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the auto insurance pricing adjustment method is generally set in the server / terminal device.
[0063] 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.
[0064] Continue to refer Figure 2 , shows a flow chart of an embodiment of the method for adjusting the pricing of auto insurance proposed in the present application. The embodiment of the present application can acquire and process relevant data based on artificial intelligence technology, wherein the method for adjusting the pricing of auto insurance can be applied to the method for adjusting the pricing of auto insurance. The method for adjusting the pricing of auto insurance provided in the embodiment of the present invention includes the following steps:
[0065] S210, receiving a first instruction, where the first instruction is used to intercept information of a pre-built adjustment model, where the adjustment model is a model obtained by adjusting the pre-built initial model.
[0066] In this step, the initial model is a model for each purpose corresponding to the financial insurance scenario. The construction of the initial model is determined based on the acquired financial business scenario data. The above financial business scenario data can be a scenario that represents the auto insurance pricing scenario, the claim and loss assessment scenario, the image detection scenario based on the claim and loss assessment, and the anti-fraud scenario. Further, the basic task flow corresponding to the financial business scenario data is determined, that is, the basic task flow under the scenario is determined. It should be understood that different business scenarios correspond to different initial models. In this embodiment, the initial model is used to set prices in different scenarios. For example, in the auto insurance pricing scenario, the initial model is used to verify the insurance policy submitted by the insured in the auto insurance pricing scenario to complete the calculation of the insured's insurance premium.
[0067] In a feasible implementation manner of the present invention, the initial model may be a generalized linear mathematical model used for financial pricing, and the adjustment model refers to a model adjusted on the basis of the initial model.
[0068] S220: In response to the first instruction, intercept adjustment model information corresponding to the adjustment model and initial model information corresponding to the initial model.
[0069] In this step, in response to the first instruction, the adjustment model information of the adjustment model and the initial model information corresponding to the initial model are intercepted. It should be noted that the initial model corresponds to the initial factors for constructing the initial model. For example, the insurance pricing model constructed based on vehicle insurance in the financial scenario, the corresponding initial factors may be vehicle type, vehicle price, number of trips, number of historical accidents, driving area, etc. The above initial factors are the batch data information corresponding to the same type of users.
[0070] The adjustment model is adjusted on the basis of the initial model, including adjusting the initial factors, the connection relationship of the initial factors, etc. For the specific implementation of the adjustment model, please refer to the subsequent embodiments.
[0071] It should be understood that in this embodiment, when the first instruction is received, the initial model may be in a running state and the adjustment model has not yet been generated. Therefore, when targeting a new application scenario, intercepting the current parameters of the initial model and the adjustment parameters of the adjustment model is temporary. After intercepting the initial model information of the corresponding initial model, the generated adjustment model can be evaluated by adjusting the parameters of the initial model information. When the evaluation passes, the adjustment parameters can be directly added to the original initial model, which improves the applicability of the original model to the new scenario.
[0072] S230: Perform risk assessment on the adjustment model based on the adjustment model information and the initial model information to obtain a risk assessment result corresponding to the adjustment model.
[0073] In this step, the adjustment model information and the initial model information are respectively input into the adjustment model to obtain the corresponding model output results. In this step, the pricing scheme for financial insurance is implemented in large quantities for the generalized linear model, and the output results are scored using the following formula:
[0074] y=a1*v1+a2*v2+a3*v3....+intercept
[0075] Among them, y is a measure of risk, a represents the weight of each variable, v represents the grouping of each variable, intercept is the intercept term, and the score of y is between 1 and 100. The higher the corresponding score, the greater the risk and the higher the pricing.
[0076] S240, when the risk assessment result meets the expected result, the adjustment model is used as the target decision model to execute the batch pricing task.
[0077] In this step, when the current scenario meets the expected results, the adjustment model can be directly used as the target decision model to perform the batch pricing task, or the adjustment model parameters corresponding to the adjustment model can be extracted and replaced in the original initial model. The adjustment model parameters that meet the result requirements are replaced in the initial model information in the initial model to perform the batch pricing task as the target decision model.
[0078] Optionally, intercepting the adjustment model information corresponding to the adjustment model and the initial model information corresponding to the initial model includes:
[0079] In this step, a model adjustment page is constructed, and after receiving the first instruction, the adjustment model information corresponding to the adjustment model and the initial model information corresponding to the initial model are intercepted. The adjustment model information includes an adjustment factor, an adjustment calculation node, and a second execution relationship. The adjustment calculation node is used to characterize the weight corresponding to the adjustment factor of the adjustment model and the calculation node affecting the probability. The second execution relationship is used to characterize the execution relationship corresponding to the output of the adjustment calculation node selected by the corresponding adjustment factor.
[0080] Obtain initial model information corresponding to the target model, wherein the initial model information includes an initial factor, an initial computing node, and a first execution relationship, and the first execution relationship is used to characterize the execution relationship between the initial computing node and the initial factor; determine a front-end rendering component based on the adjustment factor, the adjustment computing node, the second execution relationship, and the initial model information including the initial factor, the initial computing node, and the first execution relationship; and construct a model adjustment page by calling the front-end rendering component.
[0081] Exemplarily, after receiving the financial business scenario data input by the user, a first design page is displayed, and a target decision model is automatically created based on the user input on the first design page, or a scoring page is generated for the acquired initial model information and intercepted model information on the scoring page. Developers do not need to rewrite the modeling strategy corresponding to the new business scenario in the system background, thereby reducing the workload in the modeling process.
[0082] Optionally, the performing risk assessment on the adjustment model based on the adjustment model information and the initial model information to obtain a risk assessment result corresponding to the adjustment model includes:
[0083] Obtain a first weight value assigned to the initial factor in the first execution relationship, and an initial probability value corresponding to the initial calculation node; perform risk assessment calculation based on the first weight value and the initial probability value to obtain an initial risk value corresponding to the initial model; obtain a second weight value assigned to the adjustment factor in the second execution relationship, and an adjusted probability value corresponding to the adjustment calculation node; perform risk assessment calculation based on the second weight value adjusted probability value to obtain an adjusted risk value corresponding to the adjusted model.
[0084] In another embodiment, the initial factors can also use those existing in the GBD database to group the initial factors of the same component. The specific factor component composition is not limited here. The initial factor coefficients, initial factors and initial factor distribution parameters are displayed on the modeling basic design page based on the front-end component to obtain the third display part; the initial factor coefficients, initial factors and initial factor distribution parameters are randomly intercepted to obtain interception item parameters; the weights of the interception item parameters based on the initial factor coefficients, initial factors and initial factor distribution parameters are calculated based on the influence operator to obtain the scoring parameters.
[0085] Optionally, after performing risk assessment calculation based on the adjusted probability value of the second weight value to obtain the adjusted risk value corresponding to the adjustment model, the method further includes:
[0086] Obtain the relevant interval corresponding to the initial probability value; determine whether the difference between the adjusted risk value and the initial risk value exists in the relevant interval; if so, determine that the adjustment factor corresponding to the adjustment model is related to the initial factor; if not, delete the adjustment factor corresponding to the adjustment model
[0087] Optionally, before the extraction call calls the front-end rendering component to build the model adjustment page, it also includes:
[0088] The first design page includes a first design page for configuring parameters, the first design page includes a first display part and a second display part; obtaining the initial model information and adjustment model information input by the user in the first display part; and dynamically adjusting the second display part according to the initial model information and the adjustment model information.
[0089] In this embodiment, the front-end component is determined based on the configuration information contained in the financial business scenario data, and then the front-end component is called to generate the first design page, wherein the above-mentioned front-end component can be json data, and the above-mentioned json data has a specific field type to display the corresponding component, which includes but is not limited to basic form components and custom complex components.
[0090] Optionally, a title field may be added to the json data to merge the front-end components through the title field during the generation of the first design page.
[0091] In this embodiment, in the process of obtaining the first design page, the initial model information and the adjustment model information in the first display part of the first design page are used to determine the dependency relationship between the front-end components in the first display part and the front-end components in the second display part, thereby dynamically adjusting the second display part of the first design page through the dependency relationship. Specifically, the first modeling configuration information in the first display part of the first design page is for determining the front-end rendering component based on the adjustment factor, the adjustment calculation node, the second execution relationship, the initial factor, the initial calculation node and the first execution relationship, and obtaining the dependency relationship between the front-end components in the first display part and the front-end components in the second display part, thereby dynamically adjusting the content displayed in the second display part, thereby realizing the linkage of different display parts in the first design page.
[0092] An optional implementation is to pre-set a database, which stores the mapping relationship between the financial business scenario data and the initial model information and the adjustment model information. It should be understood that one financial business scenario data corresponds to one initial model information and the adjustment model information, and it can be pre-set by the developer. After the user inputs the financial business scenario data, the financial business scenario data is queried in the database to obtain the model data corresponding to the financial business scenario data.
[0093] Compared with the prior art, the embodiments of the present application have the following beneficial effects:
[0094] The present invention provides a method, device, computer equipment and storage medium for pricing auto insurance. The above-mentioned auto insurance pricing adjustment method includes: receiving a first instruction, the first instruction is used to intercept information of a pre-built adjustment model, the adjustment model is a model obtained after adjusting the pre-built initial model; in response to the first instruction, intercepting the adjustment model information corresponding to the adjustment model, and the initial model information corresponding to the initial model; based on the adjustment model information and the initial model information, the adjustment model is risk evaluated to obtain the risk evaluation result corresponding to the adjustment model; when the risk evaluation result meets the expected result, the adjustment model is used as the target decision model to perform the batch pricing task. It solves the problem that developers need to retrain when the model cannot achieve the expected effect, reduces the difficulty of debugging the model, and improves the debugging efficiency.
[0095] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a method 300 for pricing auto insurance. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.
[0096] An embodiment of the present invention provides a method 300 for pricing an automobile insurance. The method 300 for adjusting automobile insurance pricing includes:
[0097] The instruction receiving module 310 is used to receive a first instruction, wherein the first instruction is used to intercept information of a pre-built adjustment model, wherein the adjustment model is a model obtained by adjusting the pre-built initial model;
[0098] A data interception module 320, configured to intercept, in response to the first instruction, adjustment model information corresponding to the adjustment model and initial model information corresponding to the initial model;
[0099] A risk assessment module 330, configured to perform risk assessment on the adjustment model based on the adjustment model information and the initial model information, and obtain a risk assessment result corresponding to the adjustment model;
[0100] The task execution module 340 is used to execute the batch pricing task by using the adjustment model as the target decision model when the risk assessment result meets the expected result.
[0101] Optionally, the data interception module further includes an interception subunit, an acquisition subunit, a determination subunit and a construction subunit, and the device includes:
[0102] The interception subunit is used to intercept the adjustment model information corresponding to the adjustment model, wherein the adjustment model information includes an adjustment factor, an adjustment calculation node, and a second execution relationship, and the second execution relationship is used to characterize the execution relationship between the adjustment calculation node and the adjustment factor;
[0103] The acquisition subunit is used to acquire initial model information corresponding to the initial model, wherein the initial model information includes initial factors, initial computing nodes, and a first execution relationship, and the first execution relationship is used to characterize the execution relationship between the initial computing nodes and the initial factors;
[0104] The determining subunit is used to determine the front-end rendering component based on the adjustment factor, the adjustment computing node, the second execution relationship, the initial factor, the initial computing node and the first execution relationship;
[0105] The construction subunit is used to call the front-end rendering component to build a model adjustment page.
[0106] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.
[0107] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can 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 microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.
[0108] 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.
[0109] The memory 41 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 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as the program code of the auto insurance pricing adjustment method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.
[0110] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run the program code stored in the memory 41 or process data, such as running the program code of the auto insurance pricing adjustment method.
[0111] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.
[0112] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores a calling program of the application, and the calling program of the application can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned auto insurance pricing adjustment method.
[0113] 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 online 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.
[0114] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.
[0115] 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 method for pricing automobile insurance, characterized in that: The method comprises: receiving a first instruction, wherein the first instruction is used to intercept information of a pre-built adjustment model, wherein the adjustment model is a model obtained by adjusting the pre-built initial model; In response to the first instruction, intercepting adjustment model information corresponding to the adjustment model and initial model information corresponding to the initial model; Performing risk assessment on the adjustment model based on the adjustment model information and the initial model information to obtain a risk assessment result corresponding to the adjustment model; When the risk assessment result meets the expected result, the adjustment model is used as the target decision model to execute the batch pricing task.
2. The method according to claim 1, characterized in that The intercepting of the adjustment model information corresponding to the adjustment model and the initial model information corresponding to the initial model includes: intercepting adjustment model information corresponding to the adjustment model, wherein the adjustment model information includes an adjustment factor, an adjustment calculation node, and a second execution relationship, wherein the second execution relationship is used to characterize an execution relationship between the adjustment calculation node and the adjustment factor; Acquire initial model information corresponding to the initial model, wherein the initial model information includes an initial factor, an initial computing node, and a first execution relationship, wherein the first execution relationship is used to characterize an execution relationship between the initial computing node and the initial factor; Determine a front-end rendering component based on the adjustment factor, the adjustment computing node, the second execution relationship, the initial factor, the initial computing node, and the first execution relationship; The front-end rendering component is called to build a model adjustment page.
3. The method according to claim 2, characterized in that performing risk assessment on the adjustment model based on the adjustment model information and the initial model information to obtain a risk assessment result corresponding to the adjustment model; Obtaining a first weight value assigned to the initial factor in the first execution relationship and an initial probability value corresponding to the initial calculation node; Perform risk assessment calculation based on the first weight value and the initial probability value to obtain an initial risk value corresponding to the initial model; Acquire a second weight value assigned to the adjustment factor in the second execution relationship, and an adjustment probability value corresponding to the adjustment calculation node; A risk assessment calculation is performed based on the second weight value and the adjusted probability value to obtain an adjusted risk value corresponding to the adjustment model.
4. The method according to claim 3, characterized in that After performing risk assessment calculation based on the adjusted probability value of the second weight value to obtain the adjusted risk value corresponding to the adjustment model, the method includes: Obtaining a correlation interval corresponding to the initial probability value; determining whether a difference between the adjusted risk value and the initial risk value exists within a relevant interval; If so, determining that the adjustment factor corresponding to the adjustment model is related to the initial factor; If it does not exist, the adjustment factor corresponding to the adjustment model will be deleted.
5. The method according to claim 4, characterized in that After determining that the adjustment factor corresponding to the adjustment model is related to the initial factor, the method includes: Obtain the preset risk object determination table; Determine whether the difference between the initial risk result and the adjusted risk result is in the high risk interval of the risk determination object table; If yes, then generate a high-risk verification workflow corresponding to the batch pricing task; If not, a standard approval workflow corresponding to the batch pricing task is generated.
6. The method according to claim 2, characterized in that Before the extraction call calls the front-end rendering component to build the model adjustment page, it also includes: The first design page includes a first design page for configuring parameters, and the first design page includes a first display part and a second display part Acquire the initial model information and adjustment model information input by the user in the first display part; The second display part is dynamically adjusted according to the initial model information and the adjustment model information.
7. A vehicle insurance pricing device, characterized in that: The device comprises: An instruction receiving module, used for receiving a first instruction, wherein the first instruction is used for intercepting information of a pre-built adjustment model, wherein the adjustment model is a model obtained by adjusting the pre-built initial model; a data interception module, configured to intercept, in response to the first instruction, adjustment model information corresponding to the adjustment model and initial model information corresponding to the initial model; A risk assessment module, configured to perform risk assessment on the adjustment model based on the adjustment model information and the initial model information, and obtain a risk assessment result corresponding to the adjustment model; The task execution module is used to execute the batch pricing task by using the adjustment model as the target decision model when the risk assessment result meets the expected result.
8. The device according to claim 7, wherein the data interception module further comprises an interception subunit, an acquisition subunit, a determination subunit and a construction subunit, and the device comprises: The interception subunit is used to intercept the adjustment model information corresponding to the adjustment model, wherein the adjustment model information includes an adjustment factor, an adjustment calculation node, and a second execution relationship, and the second execution relationship is used to characterize the execution relationship between the adjustment calculation node and the adjustment factor; The acquisition subunit is used to acquire initial model information corresponding to the initial model, wherein the initial model information includes initial factors, initial computing nodes, and a first execution relationship, and the first execution relationship is used to characterize the execution relationship between the initial computing nodes and the initial factors; The determining subunit is used to determine the front-end rendering component based on the adjustment factor, the adjustment computing node, the second execution relationship, the initial factor, the initial computing node and the first execution relationship; The construction subunit is used to call the front-end rendering component to build a model adjustment page.
9. A computer device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the auto insurance pricing adjustment method according to any one of claims 1 to 6 when executing the program stored in the memory.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the auto insurance pricing adjustment method according to any one of claims 1 to 6 is implemented.
