Data processing method and device, computing equipment, storage medium and program product
By using pre-trained large models to process the pricing data of insurance products, and automatically extract and adjust key parameters, the problems of low pricing efficiency and poor accuracy of insurance products are solved, and a more efficient and accurate pricing process is achieved.
Patent Information
- Application Number
- CN202411143883.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-20
- Publication Date
- 2024-12-13
AI Technical Summary
Insurance products are inefficient in pricing and inaccurate, and are limited by manual evaluation and data processing efficiency, making it difficult to effectively control underwriting risks.
Data processing is performed using a pre-trained large model. By receiving data processing tasks, determining task prompt information, inputting pending data and task prompt information, obtaining project value information and project adjustment parameters, and processing according to preset processing rules to obtain standardization. Parameters, reduce manual adjustment.
It improves the efficiency and accuracy of project value information and project adjustment parameters, reduces manual adjustments, and improves the accuracy and efficiency of pricing results.
Smart Images
Figure CN119130508A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of this specification relate to the field of computer technology, and in particular, to a data processing method, apparatus, computing device, storage medium, and program product. Background Art
[0002] In order to adapt to changes in customer and market demands, insurance companies need to constantly design new insurance coverage for various events, as well as new insurance products for various insured persons.
[0003] At present, the premium pricing of insurance products is usually done offline by underwriters based on factors such as the regularity of the risks faced by the insurance subject, combined with their own experience to make an evaluation and quotation. This is inefficient and limited by the lack of experience of underwriters. The pricing results may not be reasonable, and the underwriting risk is difficult to control. Therefore, there is an urgent need for a method to improve the accuracy and efficiency of pricing for new insurance products. Summary of the invention
[0004] In view of this, an embodiment of this specification provides a data processing method. One or more embodiments of this specification also relate to a data processing device, a computing device, a computer-readable storage medium and a computer program product to solve the technical defects existing in the prior art.
[0005] According to a first aspect of an embodiment of this specification, a data processing method is provided, including:
[0006] receiving a data processing task and determining task prompt information corresponding to the data processing task, wherein the data processing task carries data to be processed, the data to be processed includes at least one specified project, and the task prompt information is constructed based on project information of the specified project;
[0007] Input the data to be processed and the task prompt information into the task processing model to obtain the project value information and project adjustment parameters of each designated project, wherein the task processing model is a large model obtained by pre-training;
[0008] According to preset processing rules, the project adjustment parameters are processed to obtain standard project adjustment parameters, and the project value information and standard project adjustment parameters of each designated project are stored.
[0009] According to a second aspect of an embodiment of this specification, there is provided a data processing device, including:
[0010] A receiving module is configured to receive a data processing task and determine task prompt information corresponding to the data processing task, wherein the data processing task carries data to be processed, the data to be processed includes at least one specified project, and the task prompt information is constructed based on project information of the specified project;
[0011] An input module is configured to input the data to be processed and the task prompt information into the task processing model to obtain the project value information and project adjustment parameters of each designated project, wherein the task processing model is a large model obtained by pre-training;
[0012] The processing module is configured to process the project adjustment parameters according to preset processing rules, obtain standard project adjustment parameters, and store the project value information and standard project adjustment parameters of each designated project.
[0013] According to a third aspect of an embodiment of this specification, a computing device is provided, including:
[0014] Memory and processor;
[0015] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the above data processing method are implemented.
[0016] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned data processing method are implemented.
[0017] According to a fifth aspect of the embodiments of this specification, a computer program product is provided, comprising a computer program / instruction, which implements the steps of the above-mentioned data processing method when executed by a processor.
[0018] An embodiment of the present specification implements receiving a data processing task and determining task prompt information corresponding to the data processing task, wherein the data processing task carries data to be processed, the data to be processed includes at least one specified project, and the task prompt information is constructed based on project information of the specified project; inputting the data to be processed and the task prompt information into a task processing model to obtain project value information and project adjustment parameters of each specified project, wherein the task processing model is a large model obtained by pre-training; processing the project adjustment parameters according to preset processing rules to obtain standard project adjustment parameters, and storing the project value information and standard project adjustment parameters of each specified project.
[0019] In this way, by obtaining task prompt information and inputting the data to be processed and the task prompt information into the task processing model, the task processing capability of the task processing model can be improved, and the efficiency and accuracy of extracting project value information and project adjustment parameters of the designated project can be improved; by processing the project adjustment parameters according to preset processing rules and obtaining standard project adjustment parameters, the data results output by the task processing model can be adjusted, and the adjusted standard project adjustment parameters are more in line with actual needs, reducing the work of manual adjustment, thereby improving the accuracy and efficiency of determining project value information and standard project adjustment parameters. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Figure 1 is a flow chart of a data processing method provided by an embodiment of this specification;
[0021] Figure 2 is a data parsing process flow chart of a data processing method provided by an embodiment of this specification;
[0022] Figure 3 is a flow chart of a data correction process of a data processing method provided by an embodiment of this specification;
[0023] Figure 4 is a data review process flow chart of a data processing method provided by an embodiment of this specification;
[0024] Figure 5 is a data use process flow chart of a data processing method provided by an embodiment of this specification;
[0025] Figure 6 is a structural schematic diagram of a data processing device provided by an embodiment of this specification;
[0026] Figure 7 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION
[0027] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.
[0028] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.
[0029] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
[0030] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0031] In one or more embodiments of this specification, a large model refers to a deep learning model with large-scale model parameters, which usually contains hundreds of millions, tens of billions, hundreds of billions, trillions, or even more than 10 trillion model parameters. A large model can also be called a foundation model / foundation model. The large model is pre-trained with large-scale unlabeled corpus to produce a pre-trained model with more than 100 million parameters. This model can adapt to a wide range of downstream tasks, and the model has good generalization ability, such as a large-scale language model (LLM), a multi-modal pre-training model, etc.
[0032] When the big model is used in practice, only a small number of samples are needed to fine-tune the pre-trained model and it can be applied to different tasks. The big model can be widely used in natural language processing (NLP), computer vision and other fields. Specifically, it can be applied to computer vision tasks such as visual question answering (VQA), image description (IC), image generation, as well as natural language processing tasks such as text-based sentiment classification, text summary generation, and machine translation. The main application scenarios of the big model include digital assistants, intelligent robots, search, online education, office software, e-commerce, intelligent design, etc.
[0033] First, the terms involved in one or more embodiments of this specification are explained.
[0034] Risk factors: refers to factors that affect the probability of insurance claims and the amount of claims, such as the insured's age, gender, occupation, whether there is social security, etc. The risk factors of different insurance products can be the same or different.
[0035] Risk factor conditions: The same risk factor can include multiple conditions, and different conditions can correspond to different adjustment coefficients. For example, when the risk factor is age, the risk factor conditions can include various age groups.
[0036] Adjustment coefficient of risk factor: It is the adjustment coefficient corresponding to the condition of risk factor. Different conditions correspond to different adjustment coefficients. In practical applications, the adjustment coefficient can be determined based on the personal information of the insured and the condition of risk factor; based on the base premium and adjustment coefficient, the actual premium that the insured needs to pay is determined.
[0037] Insurance liability: refers to the insurance payment liability that the insurer bears to the insured in accordance with the insurance contract. Insurance liability covers the scope of risks that the insurer is clearly stipulated to bear in the insurance contract, as well as the compensation liability that the insurer needs to bear when an insurance accident occurs.
[0038] Pure risk premium: refers to the compensation cost corresponding to the risk of the insurance liability itself.
[0039] Base premium: includes pure risk premium and additional cost. The additional cost is calculated based on the additional expense rate and pure risk premium. The additional expense rate is set by relevant professionals based on actual conditions.
[0040] OSS (Object Storage Service): is a cloud computing-based storage method that helps users effectively store and manage large amounts of data objects. Data objects can be any type of file, such as pictures, videos, documents, etc.
[0041] ChatGPT-4O: is a large model that can process and generate data in multiple modalities such as text, audio, and images in real time. It has good real-time processing and reasoning capabilities, and can respond to users' complex queries and needs quickly and accurately. It can be applied to a variety of application scenarios to provide users with a smarter and more efficient interactive experience.
[0042] Prompt: Also called prompt information or rule instructions. It can guide the large model to accurately extract the required specific parameters from the file.
[0043] Temperature: It is a general model parameter of ChatGPT. The higher the value of Temperature, the more divergent the generated answers are, which is generally suitable for scenarios that require creativity and innovation; the lower the value, the more fixed the generated answers are, which is generally suitable for scenarios with relatively standard processes.
[0044] In order to adapt to the changes in customer and market demands, insurance companies need to constantly design new insurance coverage for various events and new insurance products for various insured objects. However, the insurance pricing process is a complex process involving the consideration of multiple factors and objectives. Assessing the risk profile of the customer is one of the important factors.
[0045] In actual applications, assessing a customer's risk profile often requires reference to the pricing levels of similar insurance products. Currently, actuaries usually read pricing documents for insurance products and manually extract and organize data. However, manual processing requires a lot of time and effort, and it is difficult to ensure data quality, requiring multiple proofreadings. This results in low pricing efficiency and accuracy for newly launched insurance products.
[0046] Based on this, an embodiment of the present specification provides a data processing method, which receives a data processing task and determines task prompt information corresponding to the data processing task, wherein the data processing task carries data to be processed, the data to be processed includes at least one specified project, and the task prompt information is constructed based on the project information of the specified project; the data to be processed and the task prompt information are input into a task processing model to obtain project value information and project adjustment parameters of each specified project, wherein the task processing model is a large model obtained by pre-training; the project adjustment parameters are processed according to preset processing rules to obtain standard project adjustment parameters, and the project value information and standard project adjustment parameters of each specified project are stored.
[0047] In this way, by obtaining task prompt information and inputting the data to be processed and the task prompt information into the task processing model, the task processing capability of the task processing model can be improved, and the efficiency and accuracy of extracting project value information and project adjustment parameters of the designated project can be improved; by processing the project adjustment parameters according to preset processing rules and obtaining standard project adjustment parameters, the data results output by the task processing model can be adjusted, and the adjusted standard project adjustment parameters are more in line with actual needs, reducing the work of manual adjustment, thereby improving the accuracy and efficiency of determining project value information and standard project adjustment parameters.
[0048] In this specification, a data processing method is provided. This specification also relates to a data processing apparatus, a computing device, a computer-readable storage medium, and a computer program product, which are described in detail one by one in the following embodiments.
[0049] See also Figure 1 , Figure 1 A flow chart of a data processing method provided according to an embodiment of the present specification is shown, which specifically includes the following steps.
[0050] Step 102: Receive a data processing task and determine task prompt information corresponding to the data processing task, wherein the data processing task carries data to be processed, the data to be processed includes at least one specified project, and the task prompt information is constructed based on project information of the specified project.
[0051] In practical applications, a data structured processing system can be built based on a pre-trained large model. The large model can be called through system services to parse the data to be processed, thereby extracting key data from the data to be processed.
[0052] According to an optional embodiment of the present specification, a data processing task may be received, and task prompt information corresponding to the data processing task may be determined.
[0053] Specifically, the data processing task can be understood as a task to extract key data from the data to be processed, that is, a task to parse the data to be processed. Task prompt information, that is, prompt, can be input into the big model to guide the big model to extract key data. The data to be processed can be understood as a data file to be parsed, and its format may include html or docx. The data to be processed includes key data such as benchmark value information and adjustment parameters, which can be used as a pricing reference for newly launched products. The data to be processed includes at least one designated item, which can be understood as a charging item for the product.
[0054] In one or more optional embodiments of the present specification, the data to be processed may be a pricing source file of an insurance product, that is, a rate file of an insurance product for customers. The pricing source file of an insurance product may be obtained based on an internal data source, or may be obtained based on an external public data source, such as insurance product description materials disclosed by other insurance companies. Furthermore, the designated item may be understood as an insurance liability, and a source file may include one or more insurance liabilities, and each insurance liability may include its corresponding base premium and adjustment parameters.
[0055] It should be noted that the insurance liabilities in the same source file can belong to the same insurance field, such as health insurance, or different insurance fields, such as health insurance, financial insurance, transportation insurance, etc. In other words, an insurance product can cover multiple insurance fields, and each insurance field has corresponding insurance liabilities and corresponding rate information in the source file of the insurance product.
[0056] According to another optional embodiment of the present specification, before receiving the data processing task, the following may also be included:
[0057] Receive the data to be processed uploaded by the front-end users and create data processing tasks for the data to be processed;
[0058] The data to be processed is stored and the data storage address of the data to be processed is recorded.
[0059] Specifically, the front-end user can be understood as a business person of an insurance company, or a front-end business system storing pricing source files of insurance products.
[0060] In actual applications, when the system service receives the data to be processed, it can trigger the creation of a data processing task, send the data to be processed to OSS for storage, and record the data storage address of the data to be processed. Furthermore, the system service can call the intelligent analysis service, which calls the large model to complete the analysis of the data to be processed.
[0061] Optionally, the intelligent analysis service can pull the data to be processed from OSS according to the data storage address, so as to parse and process the data to be processed.
[0062] In the actual implementation process, since the names of insurance liabilities in the source files are different and the format and expression of rate information are not fixed, it is difficult to parse accurate results through manual extraction or model analysis, and it is easy to have errors and omissions.
[0063] Based on this, in one or more optional embodiments of the present specification, the project information may include project value information and project adjustment parameters; before determining the task prompt information corresponding to the data processing task, the following steps may also be included:
[0064] Determine the preset text structure according to the task type of the data processing task;
[0065] Based on the preset text structure, task prompt information for extracting project value information and project adjustment parameters is generated.
[0066] In practical applications, before executing a structured processing flow on the data to be processed, task prompt information for inputting a large model can be customized in advance for the data processing task. The task prompt information can be customized according to the data to be identified and extracted. Specifically, the task type of the data processing task can be determined first, and then the general task prompt information under the task type can be formulated according to the data to be extracted by the task.
[0067] Specifically, the project information of the specified project may include project value information and project adjustment parameters. The task type of the data processing task may be a task of extracting key data from a data file, that is, a task of parsing data from a data file. The preset text structure may be understood as the basic structure of the task prompt information. The preset text structure may be determined based on a preset template or may be generated by customization.
[0068] Exemplarily, the preset text structure may be: identifying a designated project, extracting xxx information of the designated project, and organizing the extracted data into xxx format.
[0069] Furthermore, based on the project information including the project value information and the project adjustment parameters, more specific guidance information or prompt text can be generated on the basis of the preset text structure.
[0070] Continuing with the above example, when the data to be processed is the pricing source file of an insurance product, the guide information may include: the name of the designated project is generally xxx liability, xxx information includes base premium and risk factor, if there is no base premium, extract the base rate, and so on.
[0071] In summary, based on the preset text structure and guiding information, a customized prompt corresponding to the data processing task can be generated, that is, the task prompt information: "First, extract the insurance liability, whose name is generally xxxx liability; then extract the benchmark premium and risk factor. If there is no benchmark premium, extract the benchmark rate; finally, organize the extracted data into JSON format."
[0072] Furthermore, when constructing task prompt information, the task prompt information can be iteratively optimized according to the big model's response to the task prompt information and the task execution of the data processing task. Specifically, this can include adjusting the order of sentences, modifying key words, adding or removing examples, etc., until the big model can accurately understand and execute the task.
[0073] By applying this embodiment, a preset text structure is determined according to the task type of the data processing task, and task prompt information for extracting project value information and project adjustment parameters is generated based on the preset text structure. This can generate customized prompt information for the data processing task before executing the structured processing flow on the data to be processed. This can guide the big model to extract project information more accurately when inputting file data into the big model, thereby improving data extraction accuracy.
[0074] Step 104: Input the data to be processed and the task prompt information into the task processing model to obtain the project value information and project adjustment parameters of each designated project, wherein the task processing model is a large model obtained by pre-training.
[0075] In practical applications, when the data to be processed and the task prompt information are obtained, the data to be processed and the task prompt information can be input into the task processing model, and the large model will parse the data to be processed based on the task prompt information to obtain the project value information and project adjustment parameters of each specified project.
[0076] Specifically, the project value information can be understood as the value information corresponding to the specified project, that is, the benchmark premium corresponding to the insurance liability. The benchmark premium can be calculated according to the formula: benchmark premium = pure risk cost x (1 + additional expense rate). Among them, the additional expense rate is set by professionals according to the actual situation of the insurance company. The project adjustment parameter can be understood as the data used to adjust the benchmark premium. The project adjustment parameter can include at least one risk factor, each risk factor can include multiple conditions, and each condition can correspond to a different adjustment coefficient.
[0077] According to an optional embodiment of the present specification, inputting the data to be processed and the task prompt information into the task processing model to obtain the project value information and project adjustment parameters of each designated project may include:
[0078] Convert the data to be processed into target processing data in plain text format;
[0079] Combining the task prompt information and the target processing data to obtain a combined result;
[0080] The combined results are input into the task processing model to obtain the project value information and project adjustment parameters of each specified project.
[0081] In actual applications, the system service can call the intelligent analysis service, which calls the big model to complete the analysis of the data to be processed. The intelligent analysis service pulls the data to be processed from OSS according to the data storage address, and converts the data to be processed into the target processing data in plain text format, such as txt format; then calls the big model, and inputs the task prompt information and the target processing data into the big model as the input data of the big model.
[0082] Optionally, the general model parameters of the task processing model can be adjusted according to the accuracy of the project value information and project adjustment parameters output by the large model each time. The general model parameters can include Temperature. In the application of parsing the pricing source file of insurance products, a lower Temperature value (usually not more than 0.5) is usually used. On this basis, the general model parameters can be adjusted according to the accuracy and stability of the model output results.
[0083] By applying this embodiment, the efficiency of parsing data by the big model can be improved by converting the data to be processed into target processing data in a plain text format; the accuracy of data extraction by the model can be improved by inputting the combined results of the target processing data and the task prompt information into the big model; and the optimization iteration of the big model can be achieved in the actual application process by adjusting the general model parameters according to the output results of the big model, thereby improving the accuracy and efficiency of the big model in identifying and extracting project value information and project adjustment parameters.
[0084] Step 106: Process the project adjustment parameters according to preset processing rules to obtain standard project adjustment parameters, and store the project value information and standard project adjustment parameters of each designated project.
[0085] In practical applications, when project value information and project adjustment parameters are obtained based on large model extraction, the project adjustment parameters can be processed according to preset processing rules to obtain standard project adjustment parameters, and the project value information and standard project adjustment parameters of each specified project can be stored.
[0086] Specifically, the preset processing rules can be understood as pre-set processing rules for processing the raw data output by the large model. The preset processing rules are used to adjust the raw data to obtain standardized data results that better meet the system service requirements. The preset processing rules may include processing rules for project value information, and may also include processing rules for standard project adjustment parameters. The processing rules for project value information may include: data cleaning, deduplication, and other operations on project value information.
[0087] Optionally, the project value information and standard project adjustment parameters of each designated project may be stored in the database in the form of a structured data file. The system service may record the storage address of the structured data file.
[0088] In one or more optional embodiments of the present specification, processing the project adjustment parameters according to the preset processing rules to obtain the standard project adjustment parameters may include the following steps:
[0089] According to the processing object indicated by the preset processing rule, the target project adjustment parameter is obtained from the project adjustment parameters of each designated project, and the data processing method corresponding to the target project adjustment parameter is determined according to the preset processing rule;
[0090] Based on the data processing method, the target project adjustment parameters are processed to obtain the standard project adjustment parameters.
[0091] In actual applications, the preset processing rules may include general rules for processing various project adjustment parameters, or may include personalized rules for processing designated project adjustment parameters. Therefore, according to the processing object indicated by the preset processing rules, the target project adjustment parameters that need to be adjusted according to the preset processing rules can be screened from the project adjustment parameters of each designated project.
[0092] Optionally, when the preset processing rule is a general rule, the target project adjustment parameter is a project adjustment parameter of each specified project; when the preset processing rule is a personalized rule, the target project adjustment parameter is at least one project adjustment parameter in each specified project.
[0093] Specifically, the preset processing rules specify a data processing method for adjusting parameters of target projects. The data processing methods corresponding to adjustment parameters of different projects may be different, and may be specifically determined according to data adjustment requirements in actual applications.
[0094] By applying this embodiment, the target project adjustment parameters are screened from the project adjustment parameters of each designated project according to the processing object indicated by the preset processing rules, and the data processing method corresponding to the target project adjustment parameters is determined according to the preset processing rules. The project adjustment parameters output by the large model can be standardized to obtain standardized data that meets the system service requirements, so that pricing calculations for new products can be performed based on the standardized data, thereby improving the pricing accuracy and efficiency of new products. In addition, personalized processing of different project adjustment parameters can be achieved, further improving the flexibility and applicability of data processing, and improving the accuracy of data analysis results.
[0095] According to an optional embodiment of the present specification, according to the processing object indicated by the preset processing rule, the target project adjustment parameter is obtained by screening the project adjustment parameters of each designated project, which may include the following steps:
[0096] Get the whitelist corresponding to the preset processing rules;
[0097] It is determined whether the project adjustment parameters of each designated project hit the whitelist, and the project adjustment parameters that hit the whitelist are determined as the target project adjustment parameters.
[0098] Specifically, the whitelist can be pre-set for project adjustment parameters that require data processing and whose data processing method is different from the general processing method. That is, the whitelist specifies the project adjustment parameters that require personalized processing and the personalized processing rules corresponding to the project adjustment parameters.
[0099] By applying this embodiment, by judging whether the project adjustment parameters of each designated project hit the whitelist, and determining the project adjustment parameters that hit the whitelist as the target project adjustment parameters, the target project adjustment parameters that need personalized processing can be processed according to their corresponding personalized processing methods, thereby better meeting the system's requirements for pricing data style.
[0100] Further, according to an optional embodiment of the present specification, based on the data processing method, processing the target project adjustment parameters to obtain the standard project adjustment parameters may include the following steps:
[0101] Determine the initial data format of the target project adjustment parameters;
[0102] The initial data format is converted into the target data format to obtain the standard project adjustment parameters.
[0103] Specifically, the initial data format can be understood as the format in which the large model outputs the target project adjustment data. When the target project adjustment parameters are output by the large model, they can correspond to the initial data format. The initial data format can include multiple types, such as plain text, plain values, values and description text, etc. The target data format can be understood as a standardized data format, that is, a format that meets the system service requirements and is convenient for subsequent use.
[0104] Specifically, the target project adjustment parameters may include an adjustment factor, a plurality of adjustment conditions corresponding to the adjustment factor, and an adjustment coefficient corresponding to each adjustment condition. Among them, the adjustment factor, the adjustment condition, and the adjustment coefficient may all correspond to the initial data format and the target data format. The adjustment factor can be understood as a factor that affects the project value information, such as age, gender, health level, etc., which can all be regarded as factors that affect the project value information. In practical applications, the factors that affect the project value information may include more than one, so a specified project may include multiple adjustment factors. Each adjustment factor may include multiple adjustment conditions, for example, age may include different age groups, gender may include male and female, and health level may include no major disease diagnosis and treatment records, major disease diagnosis and treatment records, etc. Different adjustment conditions may correspond to different adjustment coefficients. For example, when the adjustment factor is age, the adjustment coefficients corresponding to the age conditions of 0 years old and 1 year old are different.
[0105] In the application scenario of insurance product pricing, the adjustment factor can be understood as the risk factor, the adjustment condition can be understood as the condition of the risk factor, and the adjustment coefficient can be understood as the adjustment coefficient of the risk factor.
[0106] For example, in the requirements of system services, some risk factor conditions should be pure numbers without units and description information. Therefore, the personalized processing rules corresponding to the conditions of such risk factors are: remove redundant units and description information, and only keep pure numbers. For example: the original recognition result of the deductible adjustment coefficient condition is 100,000 yuan, then it is necessary to process the original recognition result into "100,000" based on the personalized processing rules corresponding to the deductible adjustment coefficient condition.
[0107] By applying this embodiment, by determining the initial data format of the target project adjustment parameters, converting the initial data format into the target data format, and obtaining the standard project adjustment parameters, it is possible to achieve standardized processing of the data format of the target project adjustment parameters and improve the accuracy of the standard project adjustment parameters.
[0108] According to another optional embodiment of the present specification, the target project adjustment parameter includes an adjustment factor, and the adjustment factor includes an adjustment condition interval and an adjustment coefficient interval corresponding to the adjustment condition interval; based on the data processing method, the target project adjustment parameter is processed to obtain the standard project adjustment parameter, which may include the following steps:
[0109] Split adjustment condition interval and adjustment coefficient interval;
[0110] Obtaining multiple adjustment conditions corresponding to the adjustment factor and adjustment coefficients corresponding to each adjustment condition;
[0111] Each adjustment condition and the adjustment coefficient corresponding to each adjustment condition are determined as the standard item adjustment parameter.
[0112] Specifically, both the adjustment condition interval and the adjustment coefficient interval can be understood as a numerical range. The adjustment condition can be understood as a numerical value included in the adjustment condition interval, and the adjustment coefficient can be understood as a numerical value included in the adjustment coefficient interval.
[0113] In the application scenario of insurance product pricing, the adjustment factor can be understood as the risk factor, the adjustment condition can be understood as the condition of the risk factor, and the adjustment coefficient can be understood as the adjustment coefficient of the risk factor.
[0114] For example, when the risk factor is age, the standardized conditions need to be refined to each age, and each age will correspond to a different adjustment coefficient. The condition of the risk factor obtained by the large model identification is a range, such as 0-5 years old; the corresponding adjustment coefficient is also a range, such as 1-2; then the range interval 0-5 years old corresponding to the condition needs to be split into separate conditions 0, 1, 2, 3, 4, 5; the range interval of the adjustment coefficient needs to be split into separate adjustment coefficients 1, 1.2, 1.4, 1.6, 1.8, 2. After the split, the adjustment conditions and the adjustment coefficients corresponding to the adjustment conditions are: {0:1, 1:1.2, 2:1.4, 3:1.6, 4:1.8, 5:2}.
[0115] By applying this embodiment, the analysis results output by the large model are processed secondary according to data processing rules, so that the analysis results can be refined so that the processed data better meets system requirements, avoids manual processing, and improves data processing efficiency and accuracy.
[0116] According to an optional embodiment of the present specification, after storing the project value information and the standard project adjustment parameters of each designated project, the following steps may also be included:
[0117] In response to the data verification instruction, the project value information, the standard project adjustment parameters and the data to be processed are obtained, wherein the data to be processed is used to instruct the verification object to verify the project value information and the standard project adjustment parameters according to the data to be processed;
[0118] Receive and store the verification results sent by the verification object.
[0119] Specifically, the data verification instruction can be understood as an instruction to verify the accuracy of the project value information and the standard project adjustment parameters of each designated project. The verification object can be an automation system or a related technician.
[0120] In actual applications, technical personnel can log in to the pricing system, obtain the project value information and standard project adjustment parameters of each specified project from the database, that is, the parsing file, and obtain the source file corresponding to the parsing file from OSS, that is, the data to be processed; based on the source file, modify the project value information and standard project adjustment parameters in the parsing file, and store the modified updated parsing file in the database.
[0121] Furthermore, relevant personnel can also obtain the revised update parsing file from the database, and manually review the update parsing file, modify the content of the file that fails the review, and store the parsing file that passes the review as the final version of the parsing file in OSS and the database.
[0122] It should be noted that in the final version of the parsing file, the project value information of the specified project may include the base premium and the pure risk premium. The pure risk premium can be calculated based on the base premium and the additional expense rate. Specifically, it can be calculated according to the formula: base premium = pure risk cost x (1 + additional expense rate).
[0123] By applying this embodiment, the accuracy of parsing the file can be further improved by verifying the project value information and the standard project adjustment parameters based on the data to be processed.
[0124] According to an optional embodiment of the present specification, the standard project adjustment parameter includes an adjustment factor, and the adjustment factor includes multiple adjustment conditions and adjustment coefficients corresponding to each adjustment condition; after storing the project value information of each designated project and the standard project adjustment parameter, the following steps may also be included:
[0125] In response to a request for generating actual value information of a target specified project, obtaining project value information and standard project adjustment parameters of the target specified project, wherein the request for generating carries a set adjustment condition corresponding to the adjustment factor;
[0126] Determine the target adjustment coefficient corresponding to the set adjustment condition from the adjustment coefficients corresponding to the various adjustment conditions;
[0127] Based on the project value information of the target specified project and the target adjustment coefficient, actual value information of the target specified project is generated.
[0128] Specifically, the target designated project can be understood as a project that is a new product among the designated projects. In the application scenario of insurance product pricing, the target designated project is the insurance liability in the newly launched insurance product. The actual value information can be understood as the price of the target designated project to the customer, that is, the premium that the insured needs to pay to the insurer for the insurance liability.
[0129] In actual applications, a newly launched insurance product contains at least one insurance liability. The adjustment coefficient of the risk factor can be determined based on the base premium and risk factor corresponding to the insurance liability in the parsing file, as well as the risk factor matching conditions of the insured. Since the risk factor can include one or more, the adjustment coefficient can also include one or more. Based on the base premium of the insurance liability and a set of adjustment coefficients, the premium corresponding to the insurance liability can be calculated.
[0130] For example, the base premium is 10 yuan, the age adjustment coefficient is {0:1, 1:1.2, 2:1.4, 3:1.6, 4:1.8, 5:2}, and the gender adjustment coefficient is {male: 1, female: 0.8}. If the insured is a 3-year-old girl, the premium to be paid is: 10 yuan*1.6*0.8=12.8 yuan.
[0131] By applying this embodiment, the actual value information of the target designated project is generated based on the project value information and the target adjustment coefficient of the target designated project. Based on the benchmark premium and risk factors of the insurance liability in the existing insurance products, the pricing information of the newly launched insurance products can be determined, thereby improving the pricing efficiency and accuracy of new products.
[0132] In applying this embodiment, a data processing task is received, and task prompt information corresponding to the data processing task is determined, wherein the data processing task carries data to be processed, the data to be processed includes at least one specified project, and the task prompt information is constructed based on the project information of the specified project; the data to be processed and the task prompt information are input into a task processing model to obtain project value information and project adjustment parameters of each specified project, wherein the task processing model is a large model obtained by pre-training; the project adjustment parameters are processed according to preset processing rules to obtain standard project adjustment parameters, and the project value information and standard project adjustment parameters of each specified project are stored.
[0133] In this way, by obtaining task prompt information and inputting the data to be processed and task prompt information into the task processing model, the task processing capability of the task processing model can be improved, and the extraction efficiency and accuracy of the project value information and project adjustment parameters of the specified project can be improved; by processing the project adjustment parameters according to the preset processing rules and obtaining the standard project adjustment parameters, the data results output by the task processing model can be adjusted, and the adjusted standard project adjustment parameters are more in line with actual needs, reducing the work of manual adjustment, thereby improving the accuracy and efficiency of determining the project value information and standard project adjustment parameters. This is conducive to improving the pricing efficiency and accuracy of newly launched insurance products.
[0134] The following combination Figure 2-Figure 5 , taking the application of the data processing method provided in this specification in the pricing system of insurance products as an example, the data processing method is further explained. Figure 2 A data parsing process flow chart of a data processing method provided by one embodiment of the present specification is shown; Figure 3 A flow chart showing a data correction process of a data processing method provided by an embodiment of the present specification is shown; Figure 4 A data review process flow chart of a data processing method provided by one embodiment of the present specification is shown; Figure 5 A data usage process flow chart of a data processing method provided by an embodiment of the present specification is shown.
[0135] The pricing data structuring process of insurance products involves multiple parties such as users, pricing system services, OSS, intelligent analysis services, large models and databases.
[0136] like Figure 2As shown in the figure, the process of parsing the source file and obtaining the standard parsing result specifically includes:
[0137] The user uploads the source file through the front end. The pricing system service creates a parsing task based on the source file, sends the source file to OSS for storage, and stores the source file address. The pricing system service calls the intelligent parsing service. The intelligent parsing service pulls the source file from OSS based on the source file address, converts the source file to txt format, and combines the txt format file with the customized prompt. The intelligent parsing service calls the big model, inputs the combined result into the big model, and the big model parses the data to obtain the parsing result. The big model organizes the parsing result into a file in the xl sx format and uploads it to OSS. OSS stores the parsing result and notifies the pricing system service. The pricing system service stores the parsing result address, pulls the parsing result file based on the parsing result address, reads the parsing result, and performs secondary processing on the parsing result according to the data processing rules to obtain the standard parsing result. The pricing system service stores the standard parsing result in the database.
[0138] It should be noted that the source file can be understood as the pricing source file of the insurance product, or as the rate source file. The source file contains at least one insurance liability, as well as the benchmark premium and risk factor corresponding to the insurance liability. The customized prompt is customized based on the task requirements of the parsing task of the source file, and the task requirements include extracting the benchmark premium and risk factors. The parsing results obtained by the large model can be stored in a file in xl sx format, and the parsing results are structured parsing results. The parsing results can include the benchmark premium and pure risk premium of each insurance liability, as well as risk factors, conditions of risk factors, adjustment coefficients corresponding to conditions, etc., which can be used as key data for pricing reference of new insurance products.
[0139] like Figure 3 As shown, the process of modifying the standard analysis result and obtaining the updated analysis result specifically includes:
[0140] The user queries the parsing result, and the pricing service system accesses the database to obtain the parsing result. The pricing service system pulls the source file from OSS and returns the parsing result and source file to the user. The user modifies the parsing result based on the source file. The pricing service system updates the parsing result based on the modified result and stores the updated parsing result in the database.
[0141] like Figure 4 As shown in the figure, the process of reviewing the analysis results and obtaining the latest analysis result file specifically includes:
[0142] The user reviews the parsing results, and the pricing system service queries the latest parsing results from the database, and the database returns the latest parsing results. The pricing system service generates the latest parsing result file based on the user's review results and stores the latest parsing result file in OSS. Furthermore, when the pricing system performs pricing for new products, the latest parsing results can be imported into the database.
[0143] like Figure 5 As shown, the process of downloading the parsing result file and using the parsing result file specifically includes:
[0144] The user downloads the parsing result file, and the pricing system service pulls the parsing result file from OSS. The user uses the parsing result file.
[0145] In this embodiment, the pricing data structuring process mainly includes data parsing process, data correction process, data review process and data use process. Through the data parsing process, the benchmark premium and risk factors in the insurance product source file can be parsed and extracted through customized prompts and large models to obtain structured parsing results; through secondary processing, the output results of the model are processed to obtain standardized parsing results, thereby improving the accuracy and efficiency of extracting key data such as benchmark premiums and risk factors; through the data correction process, the standardized parsing results can be corrected according to the source file to further improve the accuracy of the standardized parsing results; through the data review process, the latest parsing result file can be reviewed to obtain the final version of the data file; through the data use process, the staff can perform pricing calculations for subsequent newly launched insurance products based on the final version of the data file, thereby improving the pricing efficiency and accuracy of new insurance products.
[0146] Corresponding to the above method embodiment, this specification also provides a data processing device embodiment, Figure 6 FIG. 1 is a schematic diagram showing the structure of a data processing device provided by an embodiment of the present specification. Figure 6 As shown, the device comprises:
[0147] Receiving module 602: configured to receive a data processing task and determine task prompt information corresponding to the data processing task, wherein the data processing task carries data to be processed, the data to be processed includes at least one specified project, and the task prompt information is constructed based on the project information of the specified project.
[0148] Input module 604: is configured to input the data to be processed and the task prompt information into the task processing model to obtain the project value information and project adjustment parameters of each designated project, wherein the task processing model is a large model obtained through pre-training.
[0149] Processing module 606: configured to process the project adjustment parameters according to preset processing rules, obtain standard project adjustment parameters, and store the project value information and the standard project adjustment parameters of each designated project.
[0150] Optionally, the project information includes project value information and project adjustment parameters; the data processing device further includes a determination module configured to:
[0151] Determine the preset text structure according to the task type of the data processing task;
[0152] Based on the preset text structure, task prompt information for extracting project value information and project adjustment parameters is generated.
[0153] Optionally, the processing module 606 is further configured to:
[0154] According to the processing object indicated by the preset processing rule, the target project adjustment parameter is obtained from the project adjustment parameters of each designated project, and the data processing method corresponding to the target project adjustment parameter is determined according to the preset processing rule;
[0155] Based on the data processing method, the target project adjustment parameters are processed to obtain the standard project adjustment parameters.
[0156] Optionally, the processing module 606 is further configured to:
[0157] Get the whitelist corresponding to the preset processing rules;
[0158] It is determined whether the project adjustment parameters of each designated project hit the whitelist, and the project adjustment parameters that hit the whitelist are determined as the target project adjustment parameters.
[0159] Optionally, the processing module 606 is further configured to:
[0160] Determine the initial data format of the target project adjustment parameters;
[0161] The initial data format is converted into the target data format to obtain the standard project adjustment parameters.
[0162] Optionally, the target item adjustment parameter includes an adjustment factor, and the adjustment factor includes an adjustment condition interval and an adjustment coefficient interval corresponding to the adjustment condition interval; the processing module 606 is further configured to:
[0163] Split adjustment condition interval and adjustment coefficient interval;
[0164] Obtaining multiple adjustment conditions corresponding to the adjustment factor and adjustment coefficients corresponding to each adjustment condition;
[0165] Each adjustment condition and the adjustment coefficient corresponding to each adjustment condition are determined as the standard item adjustment parameter.
[0166] Optionally, the data processing device further includes a verification module configured to:
[0167] In response to the data verification instruction, the project value information, the standard project adjustment parameters and the data to be processed are obtained, wherein the data to be processed is used to instruct the verification object to verify the project value information and the standard project adjustment parameters according to the data to be processed;
[0168] Receive and store the verification results sent by the verification object.
[0169] Optionally, the standard item adjustment parameter includes an adjustment factor, and the adjustment factor includes a plurality of adjustment conditions and an adjustment coefficient corresponding to each adjustment condition; the data processing device further includes a generation module configured to:
[0170] In response to a request for generating actual value information of a target specified project, obtaining project value information and standard project adjustment parameters of the target specified project, wherein the request for generating carries a set adjustment condition corresponding to the adjustment factor;
[0171] Determine the target adjustment coefficient corresponding to the set adjustment condition from the adjustment coefficients corresponding to the various adjustment conditions;
[0172] Based on the project value information of the target specified project and the target adjustment coefficient, actual value information of the target specified project is generated.
[0173] By applying this embodiment, by obtaining task prompt information and inputting the data to be processed and the task prompt information into the task processing model, the task processing capability of the task processing model can be improved, and the efficiency and accuracy of extracting project value information and project adjustment parameters of the designated project can be improved; by processing the project adjustment parameters according to preset processing rules to obtain standard project adjustment parameters, the data results output by the task processing model can be adjusted, and the adjusted standard project adjustment parameters can be more in line with actual needs, reducing the work of manual adjustment, thereby improving the accuracy and efficiency of determining project value information and standard project adjustment parameters.
[0174] The above is a schematic scheme of a data processing device of this embodiment. It should be noted that the technical scheme of the data processing device and the technical scheme of the above data processing method belong to the same concept, and the details of the technical scheme of the data processing device that are not described in detail can be referred to the description of the technical scheme of the above data processing method.
[0175] Figure 7The block diagram of a computing device 700 according to an embodiment of the present specification is shown. The components of the computing device 700 include but are not limited to a memory 710 and a processor 720. The processor 720 is connected to the memory 710 via a bus 730, and the database 750 is used to store data.
[0176] The computing device 700 also includes an access device 740 that enables the computing device 700 to communicate via one or more networks 760. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 740 may include one or more of any type of network interface, wired or wireless (e.g., a network interface card (NIC)), such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, and a Near Field Communication (NFC).
[0177] In one embodiment of the present specification, the above components of the computing device 700 and Figure 7 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 7 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.
[0178] The computing device 700 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 700 may also be a mobile or stationary server.
[0179] The processor 720 is used to execute the following computer executable instructions, which implement the steps of the above data processing method when executed by the processor.
[0180] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above data processing method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above data processing method.
[0181] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which can implement the steps of the above-mentioned data processing method when executed by a processor.
[0182] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above data processing method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above data processing method.
[0183] An embodiment of the present specification also provides a computer program product, including a computer program / instruction, which implements the steps of the above data processing method when executed by a processor.
[0184] The above is a schematic scheme of a computer program product of this embodiment. It should be noted that the technical scheme of the computer program product and the technical scheme of the above data processing method belong to the same concept, and the details not described in detail in the technical scheme of the computer program product can be referred to the description of the technical scheme of the above data processing method.
[0185] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0186] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.
[0187] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.
[0188] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0189] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.
Claims
1. A data processing method, characterized in that: include: Receive a data processing task, and determine task prompt information corresponding to the data processing task, wherein the data processing task carries data to be processed, the data to be processed includes at least one specified project, and the task prompt information is constructed based on project information of the specified project; Input the data to be processed and the task prompt information into a task processing model to obtain project value information and project adjustment parameters of each designated project, wherein the task processing model is a large model obtained by pre-training; The project adjustment parameters are processed according to preset processing rules to obtain standard project adjustment parameters, and the project value information and the standard project adjustment parameters of each designated project are stored.
2. The method according to claim 1, characterized in that The project information includes project value information and project adjustment parameters; Before determining the task prompt information corresponding to the data processing task, the method further includes: Determining a preset text structure according to the task type of the data processing task; Based on the preset text structure, task prompt information for extracting the project value information and the project adjustment parameters is generated.
3. The method according to claim 1, characterized in that The step of processing the project adjustment parameters according to the preset processing rules to obtain the standard project adjustment parameters includes: According to the processing object indicated by the preset processing rule, a target project adjustment parameter is obtained from the project adjustment parameters of each designated project, and a data processing method corresponding to the target project adjustment parameter is determined according to the preset processing rule; Based on the data processing method, the target project adjustment parameters are processed to obtain standard project adjustment parameters.
4. The method according to claim 3, characterized in that The processing object indicated by the preset processing rule, screening the target project adjustment parameters from the project adjustment parameters of the designated projects, comprises: Obtaining a whitelist corresponding to the preset processing rule; It is determined whether the project adjustment parameters of each designated project hit the white list, and the project adjustment parameters hitting the white list are determined as the target project adjustment parameters.
5. The method according to claim 3, characterized in that: The step of processing the target project adjustment parameters based on the data processing method to obtain the standard project adjustment parameters includes: Determining the initial data format of the target project adjustment parameters; The initial data format is converted into a target data format to obtain the standard item adjustment parameters.
6. The method according to claim 3, characterized in that: The target item adjustment parameter includes an adjustment factor, and the adjustment factor includes an adjustment condition interval and an adjustment coefficient interval corresponding to the adjustment condition interval; The step of processing the target project adjustment parameters based on the data processing method to obtain the standard project adjustment parameters includes: splitting the adjustment condition interval and the adjustment coefficient interval; Obtaining a plurality of adjustment conditions corresponding to the adjustment factor and an adjustment coefficient corresponding to each adjustment condition; The adjustment conditions and the adjustment coefficients corresponding to the adjustment conditions are determined as the standard item adjustment parameters.
7. The method according to claim 1, characterized in that After storing the item value information of each designated item and the standard item adjustment parameter, the method further includes: In response to the data verification instruction, the project value information, the standard project adjustment parameters and the data to be processed are obtained, wherein the data to be processed is used to instruct the verification object to verify the project value information and the standard project adjustment parameters according to the data to be processed; Receive and store the verification result sent by the verification object.
8. The method according to claim 1, characterized in that The standard item adjustment parameters include adjustment factors, and the adjustment factors include a plurality of adjustment conditions and adjustment coefficients corresponding to each adjustment condition; After storing the item value information of each designated item and the standard item adjustment parameter, the method further includes: In response to a request for generating actual value information of a target specified project, acquiring project value information and standard project adjustment parameters of the target specified project, wherein the request for generating carries a set adjustment condition corresponding to the adjustment factor; Determining a target adjustment coefficient corresponding to the set adjustment condition from the adjustment coefficients corresponding to the respective adjustment conditions; Based on the item value information of the target specifying item and the target adjustment coefficient, actual value information of the target specifying item is generated.
9. A data processing device, characterized in that: include: A receiving module is configured to receive a data processing task and determine task prompt information corresponding to the data processing task, wherein the data processing task carries data to be processed, the data to be processed includes at least one specified project, and the task prompt information is constructed based on project information of the specified project; An input module is configured to input the data to be processed and the task prompt information into a task processing model to obtain project value information and project adjustment parameters of each designated project, wherein the task processing model is a large model obtained by pre-training; The processing module is configured to process the project adjustment parameters according to preset processing rules, obtain standard project adjustment parameters, and store the project value information and the standard project adjustment parameters of each designated project.
10. A computing device, characterized in that include: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer program / instructions are executed by the processor, the steps of the data processing method according to any one of claims 1 to 8 are implemented.
11. A computer-readable storage medium, characterized in that: It stores a computer program / instruction, which, when executed by a processor, implements the steps of the data processing method described in any one of claims 1 to 8.
12. A computer program product, characterized in that The invention comprises a computer program / instruction, which, when executed by a processor, implements the steps of the data processing method according to any one of claims 1 to 8.