Big data-based business data determination method, system, device and storage medium

Abstract

The present application relates to artificial intelligence, and provides a business data determination method, system, device and storage medium, the method comprising: obtaining the insurance type data to be counted corresponding to the data statistical requirement, and a plurality of insurance policies, each insurance policy comprising an insurance type mark; determining the target insurance type mark from the insurance type mark according to the insurance type data to be counted; determining the insurance policy business with the target insurance type mark as the target business, extracting the attribute information of the target business, and generating a business information table; associating and matching the data corresponding to the business field of the business information table from the preset query table to obtain the insurance policy information; associating and matching the factor parameters corresponding to the insurance policy information from the preset factor table to obtain the first business data and the second business data; and calculating the target business data according to the first business data, the second business data and the insurance policy information.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method, system, device, and storage medium for determining business data based on big data. Background Technology

[0002] As people become more insurance-conscious, insurance companies are offering more and more types of insurance products and a larger number of policies, resulting in a large amount of business data to be processed. Currently, insurance companies' business data systems calculate the business data of each policy individually, which takes a long time.

[0003] For example, insurance reserves refer to a fund set aside by insurers from their premiums or assets to fulfill their insurance liabilities or cover future claims. The calculation method for insurance reserves differs for each type of insurance. The more types of insurance products and policies an insurance company offers, the greater the amount of insurance reserves required for calculation. However, the reserve systems within insurance companies process each policy independently, resulting in massive data processing volumes, long calculation times, and an inability to meet usage requirements. Therefore, improving the efficiency of business data calculation is a pressing technical problem that needs to be solved. Summary of the Invention

[0004] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.

[0005] This invention provides a method, system, device, and storage medium for determining business data based on big data, which can improve the computational efficiency of business data and meet user needs.

[0006] In a first aspect, embodiments of the present invention provide a method for determining business data, the method comprising:

[0007] Obtain the insurance data to be statistically analyzed corresponding to the data statistics requirements, as well as multiple insurance policy businesses, each of which includes an insurance type tag;

[0008] The target insurance type marker is determined from the insurance type markers based on the insurance type data to be statistically analyzed;

[0009] The policy business with the target insurance type tag is identified as the target business, and the attribute information of the target business is extracted to generate a business information table;

[0010] The policy information is obtained by retrieving data corresponding to the business fields of the business information table from the preset query table;

[0011] The factor parameters corresponding to the policy information are matched and associated from the preset factor table to obtain the first business data and the second business data;

[0012] The target business data is calculated based on the first business data, the second business data, and the policy information.

[0013] The business data determination method according to embodiments of the present invention has at least the following beneficial effects: Given data on insurance types to be statistically analyzed and a large number of insurance policies, the insurance policies are classified according to the insurance type tags attached to each policy. The insurance type tags corresponding to the data on insurance types to be statistically analyzed are identified as target insurance type tags, thereby identifying policy policies with target insurance type tags as target policies. The attribute information of the target policies is extracted to generate a business information table. The business fields in the business information table are correlated and matched with data in a preset query table to find corresponding information and obtain policy information. After obtaining the policy information, it can be correlated and matched with a preset factor table to find factor parameters that match the policy information, thereby mapping to first business data and second business data. The target business data is obtained by calculating using the policy information, the first business data, and the second business data. Therefore, by classifying a large number of insurance policies and processing policies belonging to the same target insurance type simultaneously, and by using big data to associate with a pre-set dataset for query matching, the calculation parameters for calculating the target business data can be obtained. This allows for the rapid calculation of the target business data without having to calculate the target business data for each individual policy. By using big data to associate with a pre-set dataset, the calculation efficiency can be improved, thus meeting the user's needs.

[0014] According to some embodiments of the present invention, in the above-described method for determining business data based on big data, the policy information includes insured rating information, policy year information, and policy duration.

[0015] The step of retrieving policy information by associating and matching data corresponding to the business fields of the business information table from a preset query table includes:

[0016] Contract data corresponding to the business fields of the business information table are retrieved from the preset contract query table to obtain the insured's basic parameters and the policy's basic parameters.

[0017] The insured's rating information is determined based on the insured's basic parameters;

[0018] The policy year information and the policy effective duration are determined based on the policy basic parameters and the preset settlement date information. The policy year information represents the number of contract cycles from the contract effective date to the settlement date, and the policy effective duration represents the duration from the contract effective date to the current cycle's policy effective date.

[0019] By using a pre-defined contract lookup table and business information table for correlation and matching, contract data matching the business fields in the contract lookup table is retrieved and mapped to generate basic parameters for the insured and the policy. The basic parameters for the insured can determine the insured's credit rating, and the basic parameters for the policy, along with pre-defined settlement date information, can determine the policy year and policy duration. By correlating and matching the corresponding datasets, matching information can be mapped to quickly obtain the calculation parameters for the target business data, improving computational efficiency.

[0020] According to some embodiments of the present invention, in the above-described business data determination method based on big data, the basic parameters of the insured include information on the place of contract effectiveness, information on the contract signing organization, the insured's occupation type, and the insured's physiological information;

[0021] The process of determining the insured's rating information based on the insured's basic parameters includes:

[0022] The occupational level information is obtained by matching the category information corresponding to the occupational category of the insured from the preset occupational query table;

[0023] Contract level information is obtained by matching and correlating the record data corresponding one-to-one with the contract effective location information and the contract signing agency information from the preset contract record table;

[0024] The insured's rating information is determined based on the occupational level information, the contract level information, and the physiological information.

[0025] By matching the insured's occupational type in the basic parameters with a pre-defined occupational lookup table, the corresponding category information can be found, thus obtaining occupational level information. Simultaneously, by matching the contract's effective location and signing organization information in the insured's basic parameters with data from a pre-defined contract record table, contract level information can be obtained. Furthermore, by combining occupational level information, contract level information, and physiological information, the insured's rating information can be determined. Using a pre-defined dataset for correlation matching allows for rapid acquisition of the required parameters, improving computational efficiency.

[0026] According to some embodiments of the present invention, in the above-described method for determining business data based on big data, the basic policy parameters include contract effective date information and contract period information;

[0027] The process of determining the policy year information and the policy duration based on the contract basic parameters and preset settlement date information includes:

[0028] The policy year information is obtained based on the contract effective date information, the contract period information, and the preset settlement date information;

[0029] The policy duration is obtained by matching the updated information corresponding to the contract effective date and the contract period information from the preset policy number change tracking table.

[0030] The policy year information represents the number of contract cycles from the contract effective date to the settlement date, while the policy effective duration represents the length of time from the contract effective date to the current cycle's policy effective date. The policy year information can be determined by using the contract effective date information, contract cycle information, and a preset settlement date information. Furthermore, the policy effective duration can be determined by correlating and matching the contract effective date information, contract cycle information, and a preset policy number change tracking table.

[0031] According to some embodiments of the present invention, in the above-described method for determining business data based on big data, the policy information includes contract period information;

[0032] The step of calculating the target business data based on the first business data, the second business data, and the policy information includes:

[0033] The effective period of the insurance cycle is determined based on the policy information and the preset settlement date. The effective period of the insurance cycle is characterized by the duration of coverage within the current insurance cycle.

[0034] The target business data is calculated based on the first business data, the second business data, the effective duration of the period, and the contract period information.

[0035] The policy information can determine the effective period of the cycle, and the policy information includes contract cycle information. By using the effective period of the cycle, contract cycle information, and the first and second business data that have been obtained, the target business data can be calculated, thereby improving the accuracy of the target business data calculation.

[0036] According to some embodiments of the present invention, in the above-described business data determination method based on big data, the step of determining the effective duration of the cycle based on the policy information and the preset settlement date includes:

[0037] The update information corresponding to the contract period information is obtained by matching the preset policy number change tracking table;

[0038] The effective period is obtained based on the effective date information of the cycle and the preset settlement date information.

[0039] The contract period information is correlated and matched with a preset policy number change tracking table. Updated information corresponding to the contract period information is retrieved from the policy number change tracking table to obtain the period effective date information. The period effective duration is then calculated by determining the difference between the period effective date information and the preset settlement date information.

[0040] According to some embodiments of the present invention, in the above-described method for determining business data based on big data, the step of calculating the target business data based on the first business data, the second business data, the periodic effective duration, and the contract period information includes:

[0041] The settlement coefficient is determined based on the effective duration of the period and the contract period information;

[0042] The target business data is obtained based on the second business data, the first business data, and the settlement coefficient.

[0043] By using the effective duration of the period and the contract period information, a settlement coefficient corresponding to the proportion of the insured time can be obtained. By using the settlement coefficient, the second business data, and the first business data to calculate the target business data, the calculation efficiency of the target business data can be improved.

[0044] Secondly, embodiments of the present invention provide a business data determination system based on big data, comprising:

[0045] The business acquisition module is used to acquire the insurance data to be statistically analyzed corresponding to the data statistics requirements, as well as multiple insurance policy businesses, each of which includes an insurance type tag.

[0046] The insurance type determination module is used to determine the target insurance type marker from the insurance type markers based on the insurance type data to be statistically analyzed;

[0047] The information extraction module is used to identify the policy business with the target insurance type tag as the target business, extract the attribute information of the target business, and generate a business information table;

[0048] The information query module is used to retrieve data corresponding to the business fields of the business information table from a preset query table to obtain policy information;

[0049] The factor query module is used to associate and match the policy information with the factor parameters of a preset factor table to obtain first business data and second business data.

[0050] The data calculation module is used to calculate the target business data based on the first business data, the second business data, and the policy information.

[0051] Thirdly, embodiments of the present invention provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the business data determination method as described in the first aspect above.

[0052] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the business data determination method as described in the first aspect above.

[0053] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description and the drawings. Attached Figure Description

[0054] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the technical solutions of the present invention, and do not constitute a limitation on the technical solutions of the present invention.

[0055] Figure 1 This is a flowchart of a business data determination method based on big data provided in an embodiment of the present invention;

[0056] Figure 2 yes Figure 1 A schematic diagram illustrating the specific implementation process of step S400;

[0057] Figure 3 yes Figure 2 A schematic diagram illustrating the specific implementation process of step S420;

[0058] Figure 4 yes Figure 2 A schematic diagram illustrating the specific implementation process of step S430;

[0059] Figure 5 yes Figure 1 A schematic diagram illustrating the specific implementation process of step S600;

[0060] Figure 6 yes Figure 5 A schematic diagram illustrating the specific implementation process of step S410;

[0061] Figure 7 yes Figure 5 A schematic diagram illustrating the specific implementation process of step S420;

[0062] Figure 8 This is a schematic diagram of the structure of the business data determination system based on big data provided in an embodiment of the present invention;

[0063] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0065] It should be noted that although functional modules are divided in the module diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the module diagram or the order in the flowchart. The terms "first," "second," etc., used in the specification and the above figures are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0066] Insurance reserves refer to a certain amount of funds set aside by an insurer from premium income or surplus to ensure its fulfillment of insurance compensation or payment obligations, in accordance with relevant government laws or specific business needs, and corresponding to the insurance liabilities it undertakes. To ensure the normal operation of insurance companies and protect the interests of policyholders, most countries stipulate in insurance legislation that insurance companies should set aside insurance reserves to ensure that they have the solvency commensurate with the scale of their insurance business.

[0067] In related technologies, insurance companies' reserve systems calculate reserves for policy business by calculating each policy individually. This results in a massive amount of data and is prone to situations where the calculation process approaches the critical point of the expected time. As the number of insurance products and policies continues to increase, the processing volume of reserve calculation will become increasingly large. The calculation method of calculating reserves for each policy individually is inefficient and cannot meet the needs of users.

[0068] The embodiments of this invention can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that utilize digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0069] This invention relates to artificial intelligence and provides a method for determining business data based on big data. The method involves acquiring data on insurance types to be statistically analyzed, corresponding to data statistical needs, as well as multiple insurance policy transactions, each including an insurance type tag. Based on the data on the insurance types to be analyzed, a target insurance type tag is determined from the insurance type tags. Policy transactions with the target insurance type tag are identified as target transactions. The attribute information of the target transactions is extracted to generate a business information table. Data corresponding to the business fields in the business information table is matched from a preset query table to obtain policy information. Factor parameters corresponding to the policy information are matched from a preset factor table to obtain first business data and second business data. The target business data is calculated based on the first business data, the second business data, and the policy information. This invention improves the computational efficiency of business data and meets user needs.

[0070] Firstly, referring to Figure 1 , Figure 1 The flowchart illustrates a business data determination method based on big data provided in an embodiment of the present invention. This business data determination method includes, but is not limited to, the following steps:

[0071] Step S100: Obtain the insurance data to be statistically analyzed corresponding to the data statistical requirements, as well as multiple insurance policy businesses, each insurance policy business including insurance type tags;

[0072] Step S200: Determine the target insurance type marker from the insurance type markers based on the insurance type data to be statistically analyzed;

[0073] Step S300: Identify the insurance policies marked with the target insurance type as the target business, extract the attribute information of the target business, and generate a business information table.

[0074] Step S400: Retrieve data corresponding to the business fields of the business information table from the preset query table to obtain policy information;

[0075] Step S500: Match the factor parameters corresponding to the policy information from the preset factor table to obtain the first business data and the second business data;

[0076] Step S600: Calculate the target business data based on the first business data, the second business data, and the policy information.

[0077] Understandably, insurance policy data can be obtained from the insurance company's system platform. However, there are numerous types of insurance policies, and the calculation methods for target business data differ for different types of policies. Insurance policies contain insurance type tags, which can be used to distinguish the type of insurance. Therefore, to improve processing efficiency, policies with the same insurance type tag can be grouped into a policy set. The attribute information of each policy in the set can be extracted and used to construct a business information table. Thus, each type of insurance corresponds to a business information table containing the attribute information of policies of the same type. This allows data in the same business information table to be processed simultaneously using the same target reserve calculation method, eliminating the need to process different types of policies individually and improving processing efficiency.

[0078] The business information table is linked to a pre-defined query table. Data corresponding to the business fields in the business information table is matched and retrieved from the query table. This allows for the extraction of policy information, which can be obtained from policy transactions and includes details such as premium, sum assured, policy status, payment date, insurance period, and insurance year for each policy. For example, the business information table may only contain the fields needed to calculate the target business data, without including the individual contents of each field. The target business data could be target reserve information. This can be directly determined through the pre-defined query table, reducing data processing volume and improving efficiency.

[0079] By matching policy information with a pre-set factor table, the policy information is matched with its corresponding factor parameters. The factor table records the beginning-of-year reserve information and the second business data corresponding to each factor parameter. Therefore, the first and second business data can be directly determined from the corresponding factor parameters and policy information. For example, in a policy where the insured is male, 32 years old, and has a policy year of 2, the first business data is the beginning-of-year reserve information, and the second business data is the end-of-year reserve information. Therefore, the factor parameter matching the policy information is found in the factor table—that is, the factor parameter matching the insured's gender, age, and policy year of 2. This factor parameter corresponds to a beginning-of-year reserve and an end-of-year reserve, thus directly determining the beginning-of-year and end-of-year reserve information for this policy. This eliminates the need to calculate the corresponding beginning-of-year and end-of-year reserve information for each policy, improving processing efficiency.

[0080] Therefore, by associating and matching the business fields in the business information table with the data in the preset data set, the first business data, the second business data, and the policy information for calculating the target business data can be obtained. The target business data can then be derived using the preset calculation formula. This eliminates the need to calculate each parameter individually. By using the large amount of data stored in the preset data set, the required parameters can be mapped by querying the corresponding data, thus improving processing efficiency.

[0081] Reference Figure 2 , Figure 1 Step S400 in the illustrated embodiment includes, but is not limited to, the following steps:

[0082] Step S410: Match the contract data corresponding to the business fields in the business information table from the preset contract query table to obtain the basic parameters of the insured and the basic parameters of the policy.

[0083] Step S420: Determine the insured's rating information based on the insured's basic parameters;

[0084] Step S430: Determine the policy year information and policy effective duration based on the policy basic parameters and preset settlement date information. The policy year information represents the number of contract cycles from the contract effective date to the settlement date, and the policy effective duration represents the duration from the contract effective date to the current cycle's policy effective date.

[0085] Understandably, obtaining the first and second business data through the preset factor table requires matching the insured's rating information, policy year information, and policy duration from the business information table. The business fields in the business information table can be matched with a preset contract query table. The contract query table can contain a storage table of all policy businesses, or a storage table of policy businesses for the same type of insurance; the policy businesses contained in that storage table are the target businesses. The contract query table contains various basic information for each policy business, such as partial codes, policy numbers, insurance types, effective dates, insurance status, sum assured, number of policies, maturity dates, payment periods, and insurance periods. Therefore, by matching the contract data corresponding to the business fields in the business information report from the large amount of contract data in the contract query table, the basic parameters of the insured and the basic parameters of the policy are derived.

[0086] Because each insured's situation is different, the required target business data also differs. For example, the probability of a claim varies for each insured, and the effective status of the policy contract differs, resulting in different claim amounts and varying target reserve information. Therefore, it is necessary to determine the insured's rating information to determine the target business data. Basic insured parameters include gender, age, occupation, health status, policy effective location, and policy signing institution information. Thus, insured rating information can be determined using these basic parameters. Basic policy parameters include the number of policies, effective date, maturity date, and insurance term. Therefore, using these basic parameters and a preset settlement date, the policy year information and policy effective duration of the current policy can be determined. Policy year information represents the period from the contract effective date to the required settlement date, and the number of contract cycles the policy has gone through. Policy effective duration represents the time from the contract effective date to the current cycle's policy effective date.

[0087] Therefore, by matching and associating with a pre-set contract lookup table, the basic parameters of the insured and the basic parameters of the policy can be obtained. Then, the insured's rating information can be determined using the basic parameters of the insured, and the policy year information and policy duration can be determined using the basic parameters of the policy and the settlement date information.

[0088] Reference Figure 3 , Figure 2 Step S420 in the illustrated embodiment includes, but is not limited to, the following steps:

[0089] Step S421: Match the category information corresponding to the insured's occupation from the preset occupational query table to obtain occupational level information;

[0090] Step S422: Match the records from the preset contract record table to obtain the contract level information by matching the information of the place of contract effectiveness and the information of the contract signing agency.

[0091] Step S423: Determine the insured's rating information based on occupational level information, contract level information, and physiological information.

[0092] Understandably, the insured's basic parameters include information on the contract's effective location, the contract signing organization, the insured's occupation, and the insured's physiological information. By matching the insured's occupation with a pre-set occupational lookup table, matching categories are found, thus determining the occupational level of the policy. Similarly, by linking with a pre-set contract record table, matching records for the contract's effective location and contract signing organization information are found, thus determining the contract level. Different insureds have different circumstances, and different policy effective locations result in different probabilities of claims and different claim amounts, thus requiring different target business data. Using occupational level information, contract level information, and the insured's physiological information, the insured's rating information can be determined. Therefore, matching the pre-set occupational lookup table and contract record table allows for quick retrieval of the required parameters, improving processing efficiency.

[0093] Reference Figure 4 , Figure 2 Step S430 in the illustrated embodiment includes, but is not limited to, the following steps:

[0094] Step S431: Obtain the policy year information based on the contract effective date information, contract period information, and preset settlement date information;

[0095] Step S432: Match the updated information that corresponds one-to-one with the contract effective date information and contract period information from the preset policy number change tracking table to obtain the policy effective duration.

[0096] Understandably, the basic policy parameters include contract effective date information and contract period information. The policy year information can be obtained by combining the contract effective date information, contract period information, and preset settlement date information. The contract effective date information and contract period information are then matched and correlated with a preset policy number change tracking table. The updated information in the policy number change tracking table determines the policy's effective duration, which represents the time from the contract effective date to the current period's policy effective date.

[0097] The target business data can be target reserve information, and the preset settlement date information can be obtained simultaneously with the acquisition of policy business, i.e., received through the system platform. The target reserve information is calculated in response to the preset settlement date and the received policy business. The target reserve information differs depending on the policy year and the policy's effective duration; therefore, the policy year and policy effective duration are crucial parameters for calculating the target business data.

[0098] By linking to pre-set data tables and finding matching information, key parameters of the target insurance claim can be quickly determined, improving the calculation efficiency of target business data and meeting user needs.

[0099] Reference Figure 5 , Figure 1 Step S600 in the illustrated embodiment includes, but is not limited to, the following steps:

[0100] Step S610: Determine the effective period of the insurance cycle based on the policy information and the preset settlement date. The effective period of the insurance cycle is represented by the duration of coverage within the current insurance cycle.

[0101] Step S620: Calculate the target business data based on the first business data, the second business data, the period effective duration, and the contract period information.

[0102] Understandably, policy information includes contract period information. This information includes the contract effective date. Using the effective date, contract period information, and a preset settlement date, the duration of coverage for the current policy within the current insurance period is determined, i.e., the period effective duration. The coverage ratio for the current period is determined using the period effective duration and contract period information. The insurance period can be one year. If the first business data is the beginning-of-year reserve information, the second business data is the end-of-year reserve information, and the target business data is the target reserve information, the target business data can be calculated using the first business data, the second business data, the period effective duration, and the contract period information, thus improving the accuracy of the target business data calculation.

[0103] Reference Figure 6 , Figure 5 Step S610 in the illustrated embodiment includes, but is not limited to, the following steps:

[0104] Step S611: Match the updated information corresponding to the contract period information from the preset policy number change tracking table to obtain the period effective date information;

[0105] Step S612: Obtain the effective duration of the period based on the period effective date information and the preset settlement date information.

[0106] Understandably, by correlating and matching the contract period information with the updated information in the pre-set policy number change tracking table, the effective date of the period can be obtained, thus determining the start effective date of the current insurance period. Using the effective date information and the pre-set settlement date information, the duration of the effective period can be calculated from the start effective date to the current settlement date. By correlating and matching with the policy number change tracking table, the required effective date information can be determined without storing excessive data in the business information table or calculating each parameter individually, thus improving processing efficiency.

[0107] Reference Figure 7 , Figure 5 Step S620 in the illustrated embodiment includes, but is not limited to, the following steps:

[0108] Step S621: Determine the settlement coefficient based on the effective duration of the period and the contract period information.

[0109] Step S622: Obtain the target business data based on the second business data, the first business data, and the settlement coefficient.

[0110] Understandably, the settlement coefficient corresponding to the proportion of the current period's insured time can be obtained by using the effective duration of the period and contract period information. Calculating the target business data using the settlement coefficient, second business data, and first business data can improve the efficiency of target business data calculation. The target business data can be calculated by taking the difference between the second and first business data to obtain the business difference information, multiplying the business difference information by the settlement coefficient to obtain the required insured business data, and then summing the first business data and the required insured business data to obtain the target business data. For example, target reserve information can be obtained by multiplying the difference between the year-end reserve information and the beginning reserve information by the settlement coefficient.

[0111] Secondly, referring to Figure 8 , Figure 8 The diagram shows the structure of a business data determination system 800 based on big data provided in an embodiment of the present invention.

[0112] The business data determination system 800 based on big data includes:

[0113] The business acquisition module 810 is used to acquire the insurance data to be statistically analyzed corresponding to the data statistics requirements, as well as multiple insurance policy businesses, each of which includes an insurance type tag.

[0114] The insurance type determination module 820 is used to determine the target insurance type label from the insurance type labels based on the insurance type data to be statistically analyzed.

[0115] The information extraction module 830 is used to identify policy business with target insurance type tags as target business, extract the attribute information of the target business, and generate a business information table.

[0116] The information query module 840 is used to associate and match the business fields of the business information table with the data in the preset query table to obtain the policy information.

[0117] The factor query module 850 is used to associate and match policy information with factor parameters in a preset factor table to obtain first business data and second business data.

[0118] The data calculation module 860 is used to calculate the target business data based on the first business data, the second business data, and the policy information.

[0119] Therefore, the big data-based business data determination system 800 acquires the data of the insurance types to be statistically analyzed, as well as multiple insurance policy businesses, corresponding to the data statistical requirements through the business acquisition module 810. The insurance type determination module 820 determines the target insurance type marker from the insurance type markers through the data of the insurance types to be statistically analyzed. Therefore, the information extraction module 830 selects the insurance policies with the target insurance type marker as the target business from a large number of insurance policy businesses, and extracts the attribute information of the target business to generate a business information table. The information query module 840 associates and matches the business fields in the business information table with the data in the preset query table to find the corresponding information and obtain the policy information. After obtaining the policy information, the factor query module 850 can associate and match the policy information with the preset factor table to find the factor parameters that match the policy information, thereby mapping to obtain the first business data and the second business data. The data calculation module 860 uses the policy information, the first business data, and the second business data to perform calculations to obtain the target business data. Therefore, by classifying a large number of insurance policies and processing policies of the same target insurance type simultaneously, and by using big data to associate with a pre-set dataset for query matching, the calculation parameters for calculating the target business data can be obtained. This allows for the rapid calculation of the target business data without having to calculate the target business data for each individual policy. By using big data to associate with a pre-set dataset, the calculation efficiency can be improved, thus meeting the user's needs.

[0120] In addition, the information query module 840 also includes:

[0121] The basic parameter determination module 841 is used to match and associate contract data corresponding to the business fields of the business information table from the preset contract query table to obtain the basic parameters of the insured and the basic parameters of the policy.

[0122] The information rating module 842 is used to determine the insured's rating information based on the insured's basic parameters.

[0123] The policy time module 843 is used to determine the policy year information and policy effective duration based on the basic policy parameters and preset settlement date information. The policy year information represents the number of contract cycles that have passed from the contract effective date to the settlement date, and the policy effective duration represents the duration from the contract effective date to the policy effective date of the current cycle.

[0124] Therefore, the basic parameter determination module 841 uses a preset contract query table and business information table for correlation matching, retrieving contract data matching the business fields from the contract query table and mapping it to generate the insured's basic parameters and policy basic parameters. The information rating module 842 determines the insured's rating information using the insured's basic parameters, and uses the policy time module 843 to determine the policy year information and policy effective duration using the policy basic parameters and preset settlement date information. By correlating and matching the corresponding datasets, matching information can be mapped to quickly obtain the calculation parameters for the target business data, improving calculation efficiency.

[0125] In addition, the information rating module 842 also includes:

[0126] The occupational rating module 844 is used to match the type information corresponding to the insured's occupation from the preset occupational query table to obtain occupational rating information.

[0127] The contract rating module 845 is used to match the contract effective location information and the contract signing agency information one by one from the preset contract record table to obtain the contract rating information.

[0128] The comprehensive rating module 846 is used to determine the insured's rating information based on occupational level information, contract level information, and physiological information.

[0129] Therefore, the occupational rating module 844 matches the insured's occupational type in the insured's basic parameters with a preset occupational lookup table to find the corresponding category information, thus obtaining occupational level information. Simultaneously, the contract rating module 845 matches the contract effective location information and contract signing agency information in the insured's basic parameters with the recorded data in a preset contract record table to obtain contract level information. Furthermore, the comprehensive rating module 846 combines occupational level information, contract level information, and physiological information to determine the insured's rating information. Using a preset dataset for matching, the required parameters can be quickly obtained, improving calculation efficiency.

[0130] In addition, the policy time module 843 also includes:

[0131] The annual determination module 847 is used to obtain policy annual information based on the contract effective date information, contract period information, and preset settlement date information.

[0132] The effective duration determination module 848 is used to match and retrieve the updated information that corresponds one-to-one with the contract effective date information and contract period information from the preset policy number change tracking table to obtain the policy effective duration.

[0133] Therefore, the annual determination module 847 can determine the policy year information by using the contract effective date information, contract period information, and preset settlement date information. At the same time, the effective duration determination module 848 can determine the policy effective duration by using the contract effective date information, contract period information, and preset policy number change tracking table for correlation and matching.

[0134] In addition, the effective duration determination module 848 is also used to determine the period effective duration based on the policy information and the preset settlement date. The period effective duration information is represented as the insured duration within the current insurance period.

[0135] The data calculation module 860 is also used to calculate the target business data based on the first business data, the second business data, the periodic effective duration, and the contract period information.

[0136] Therefore, the effective duration module can determine the period effective duration through the policy information, and the policy information includes the contract period information. The data calculation module 860 can use the period effective duration, the contract period information, and the first and second business data that have been obtained to calculate the target business data, thereby improving the accuracy of the target business data calculation.

[0137] In addition, the policy time module 843 also includes:

[0138] The effective date determination module 849 is used to match and retrieve the updated information corresponding to the contract period information from the preset policy number change tracking table to obtain the period effective date information.

[0139] In addition, the effective duration module is also used to obtain the effective duration of a period based on the period effective date information and the preset settlement date information.

[0140] Therefore, the effective date determination module 849 correlates and matches the contract period information with the preset policy number change tracking table, and retrieves the updated information corresponding to the contract period information from the policy number change tracking table to obtain the period effective date information. The effective duration module can also calculate the period effective duration by calculating the difference between the period effective date information and the preset settlement date information.

[0141] In addition, the data computing module 860 also includes:

[0142] The coefficient determination module 861 is used to determine the settlement coefficient based on the effective duration of the period and the contract period information.

[0143] The data calculation module 860 is also used to obtain target business data based on the second business data, the first business data, and the settlement coefficient.

[0144] Therefore, the coefficient determination module 861 can obtain the settlement coefficient corresponding to the proportion of the insured time through the period effective duration and contract period information. The data calculation module 860 can also use the settlement coefficient, the second business data and the first business data to calculate the target business data, which can improve the calculation efficiency of the target business data.

[0145] Thirdly, referring to Figure 9 , Figure 9 An electronic device 900 according to an embodiment of the present invention is shown. The electronic device 900 includes a memory 910, a processor 920, and a computer program stored in the memory 910 and executable on the processor 920. When the processor 920 executes the computer program, it implements the business data determination method as described in the above embodiment.

[0146] The memory 910, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs, such as the service data determination method in the above embodiments of the present invention. The processor 920 implements the service data determination method in the above embodiments of the present invention by running the non-transitory software program and instructions stored in the memory 910.

[0147] The memory 910 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data required for executing the density radius-based clustering method described in the above embodiments. Furthermore, the memory 910 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. It should be noted that the memory 910 may optionally include memory remotely located relative to the processor 920, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0148] The non-transient software program and instructions required to implement the business data determination method in the above embodiments are stored in memory. When executed by one or more processors, the business data determination method in the above embodiments is executed, for example, the method described above is executed. Figure 1 Method steps S100 to S500 Figure 2 Method steps S310 to S330, Figure 3 Method steps S321 to S323, Figure 4Method steps S331 to S332, Figure 5 Method steps S510 to S520 Figure 6 Method steps S511 to S512, Figure 7 The method steps S521 to S522 are described above. Therefore, using the electronic device provided in the above embodiment, the target insurance type marker can be determined using the insurance type data to be statistically analyzed, thereby filtering out target insurance businesses with the target insurance type marker from a large number of policy businesses. The attribute information of policy businesses belonging to the target insurance type is extracted to generate a business information table. The business fields in the business information table are associated and matched with data in a preset query table to find corresponding matching information and obtain policy information. After obtaining the policy information, the policy information can be associated and matched with a preset factor table to find factor parameters that match the policy information, thereby mapping the first business data and the second business data. The target business data is obtained by calculating using the policy information, the first business data, and the second business data. Therefore, by classifying a large number of policy businesses, processing policy businesses belonging to the target insurance type simultaneously, and using big data to associate a preset dataset for query matching to map the calculation parameters for the target business data, the target business data can be calculated quickly without calculating the target business data for each policy business individually. Using big data to associate a preset dataset improves calculation efficiency and meets user needs.

[0149] Fourthly, the present invention also provides a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the business data determination method as described in the above embodiments, for example, performing the above-described... Figure 1 Method steps S100 to S500 Figure 2 Method steps S310 to S330, Figure 3 Method steps S321 to S323, Figure 4 Method steps S331 to S332, Figure 5 Method steps S510 to S520 Figure 6 Method steps S511 to S512, Figure 7The method steps S521 to S522 are as follows: Given a large number of insurance policy transactions, target insurance type markers are determined from the insurance type markers using the data of the insurance types to be statistically analyzed. The insurance policy transactions are then classified according to the insurance type markers carried by each policy. Policy transactions with the target insurance type marker are identified as target transactions. Therefore, the attribute information of the target transactions is extracted to generate a business information table. The business fields in the business information table are matched with data in a preset query table to find corresponding information and obtain policy information. After obtaining the policy information, it can be matched with a preset factor table to find factor parameters that match the policy information, thereby mapping the first business data and the second business data. The target business data is obtained by calculating using the policy information, the first business data, and the second business data. Therefore, by classifying a large number of insurance policies and processing policies of the same type simultaneously, and by using big data to correlate with a pre-set dataset for query matching, the calculation parameters for the target business data can be mapped to obtain the calculation parameters. This allows for the rapid calculation of the target business data without having to calculate the target business data for each individual policy. By using big data to correlate with a pre-set dataset, the calculation efficiency can be improved, thus meeting the user's needs.

[0150] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0151] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0152] It should be noted that a server can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0153] It should be noted that all or some of the steps in the methods disclosed above can be used in numerous general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. This 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. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can reside in local and remote computer storage media, including storage devices.

[0154] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of the present invention.

Claims

1. A method for determining business data based on big data, the method comprising: Obtain the insurance data to be statistically analyzed corresponding to the data statistics requirements, as well as multiple insurance policy businesses, each of which includes an insurance type tag; The target insurance type marker is determined from the insurance type markers based on the insurance type data to be statistically analyzed; The policy business with the target insurance type tag is identified as the target business, and the attribute information of the target business is extracted to generate a business information table; The policy information is obtained by retrieving data corresponding to the business fields of the business information table from the preset query table; the policy information includes the insured's rating information, policy year information and policy duration. The step of retrieving policy information by associating and matching data corresponding to the business fields of the business information table from a preset query table includes: Contract data corresponding to the business fields of the business information table are retrieved from the preset contract query table to obtain the basic parameters of the insured and the basic parameters of the policy. The basic parameters of the insured include the contract effective place information, the contract signing agency information, the insured's occupation type and the insured's physiological information, and the basic parameters of the policy include the contract effective date information and the contract period information. The insured's occupational category information is obtained by matching the category information corresponding to the occupational category in the preset occupational query table; the contract level information is obtained by matching the record data corresponding to the contract effective place information and the contract signing agency information in the preset contract record table; the insured's rating information is determined based on the occupational level information, the contract level information, and the physiological information. Based on the contract effective date information, the contract period information, and the preset settlement date information, the policy year information is obtained; the update information corresponding one-to-one with the contract effective date information and the contract period information is matched from the preset policy number change tracking table to obtain the policy effective duration. The policy year information represents the number of contract periods from the contract effective date to the settlement date, and the policy effective duration represents the duration from the contract effective date to the current period's policy effective date. Factor parameters corresponding to the policy information are matched from a preset factor table to obtain first business data and second business data; the policy information includes contract period information. The update information corresponding to the contract period information is matched with the preset policy number change tracking table to obtain the period effective date information, and the period effective duration is obtained based on the period effective date information and the preset settlement date information. The target business data is calculated based on the first business data, the second business data, the period effective duration, and the contract period information, including: The settlement coefficient is determined based on the effective duration of the period and the contract period information; Calculate the difference between the second business data and the first business data to obtain business difference information; Calculate the product of the business difference information and the settlement coefficient to obtain the business data required for insurance coverage; The target business data is obtained by summing the first business data and the business data required for protection.

2. A business data determination system based on big data, characterized in that, include: The business acquisition module is used to acquire the insurance data to be statistically analyzed corresponding to the data statistics requirements, as well as multiple insurance policy businesses, each of which includes an insurance type tag. The insurance type determination module is used to determine the target insurance type marker from the insurance type markers based on the insurance type data to be statistically analyzed; The information extraction module is used to identify the policy business with the target insurance type tag as the target business, extract the attribute information of the target business, and generate a business information table; The information query module is used to match data corresponding to the business fields of the business information table from a preset query table to obtain policy information; the policy information includes insured rating information, policy year information and policy duration. The step of retrieving policy information from a preset query table by matching data corresponding to the business fields of the business information table includes: retrieving contract data from a preset contract query table by matching contract data corresponding to the business fields of the business information table to obtain basic parameters of the insured and basic parameters of the policy; wherein, the basic parameters of the insured include information on the place of contract effectiveness, information on the contract signing organization, the insured's occupation type, and the insured's physiological information, and the basic parameters of the policy include information on the contract effectiveness date and the contract period; retrieving type information corresponding to the insured's occupation type from a preset occupation query table to obtain occupational level information; and retrieving the contract effectiveness information from a preset contract record table. The contract level information is obtained by recording data that corresponds one-to-one with the location information and the contract signing agency information; the insured's rating information is determined based on the occupational level information, the contract level information, and the physiological information; the policy year information is obtained based on the contract effective date information, the contract period information, and the preset settlement date information; the policy effective duration is obtained by matching and retrieving the update information that corresponds one-to-one with the contract effective date information and the contract period information from the preset policy number change tracking table. The policy year information represents the number of contract periods experienced from the contract effective date to the settlement date, and the policy effective duration represents the duration from the contract effective date to the current period's policy effective date. The factor query module is used to associate and match the policy information with the factor parameters of a preset factor table to obtain first business data and second business data. The data calculation module is used to correlate and match the updated information corresponding to the contract cycle information from the preset policy number change tracking table, obtain the cycle effective date information, and obtain the cycle effective duration based on the cycle effective date information and the preset settlement date information. The target business data is calculated based on the first business data, the second business data, the period effective duration, and the contract period information, including: The settlement coefficient is determined based on the effective duration of the period and the contract period information; Calculate the difference between the second business data and the first business data to obtain business difference information; Calculate the product of the business difference information and the settlement coefficient to obtain the business data required for insurance coverage; The target business data is obtained by summing the first business data and the business data required for protection.

3. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the business data determination method as described in claim 1.

4. A computer-readable storage medium, characterized in that, The system contains a computer program that, when executed by a processor, implements the business data determination method as described in claim 1.

Images