Rule generation method and device, electronic equipment and computer readable storage medium

Abstract

The invention relates to the technical field of rule generation and intelligent insurance business, and provides a rule generation method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: obtaining original data; based on the original data, wide table data is created, and the wide table data comprises multiple pieces of entry record data; performing feature calculation processing on the plurality of item record data to obtain a plurality of pieces of feature information; screening the plurality of pieces of feature information based on a preset feature threshold set to obtain a plurality of initial rules; performing cross-time verification processing on the plurality of initial rules to obtain verification information; and taking the corresponding initial rule as a final rule under the condition that the verification information represents that the initial rule meets the preset verification requirement information. According to the technical scheme, the rule generation efficiency can be well improved, and the time required for rule generation is shortened.

Description

Technical Field

[0001] The embodiments of the present application relate to, but are not limited to, the field of rule generation, and in particular to a rule generation method, apparatus, electronic device, and computer-readable storage medium. Background Art

[0002] With the continuous improvement of people's living standards, the insurance business has also been well promoted and developed. As a simple and efficient technology, rule-based models have been widely used in fields such as financial risk control and insurance business systems. Rule-based models define a series of conditions to determine the output. The advantage of rule-based models lies in their transparency and explainability, making the decision-making process more visible, easy to understand, and easy to audit. However, in actual application, the workload of quickly identifying effective rules from vast amounts of data is enormous and time-consuming, which in turn reduces the efficiency of rule generation. Summary of the Invention

[0003] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0004] In order to solve the problems mentioned in the above background technology, the embodiments of the present application provide a rule generation method, device, electronic device and computer-readable storage medium, which can greatly improve the efficiency of rule generation and reduce the time required for rule generation.

[0005] In a first aspect, an embodiment of the present application provides a rule generation method, comprising:

[0006] Get the original data;

[0007] Creating wide table data based on the original data, wherein the wide table data includes a plurality of entry record data;

[0008] Performing feature calculation processing on the plurality of entry record data to obtain a plurality of feature information;

[0009] Filtering the plurality of feature information based on a preset feature threshold set to obtain a plurality of initial rules;

[0010] Performing cross-time verification processing on the plurality of initial rules to obtain verification information;

[0011] In the case where the verification information indicates that the initial rule meets the preset verification requirement information, the corresponding initial rule is used as the final rule.

[0012] In a second aspect, an embodiment of the present application further provides a rule generation device, the rule generation device comprising:

[0013] An acquisition unit, used for acquiring original data;

[0014] a creating unit, configured to create wide table data based on the original data, wherein the wide table data includes a plurality of entry record data;

[0015] a calculation unit, configured to perform feature calculation processing on the plurality of item record data to obtain a plurality of feature information;

[0016] a screening unit, configured to screen the plurality of feature information based on a preset feature threshold set to obtain the plurality of initial rules;

[0017] a verification unit, configured to perform cross-time verification processing on the plurality of initial rules to obtain verification information;

[0018] The selection unit is configured to use the corresponding initial rule as the final rule when the verification information indicates that the initial rule meets preset verification requirement information.

[0019] In a third aspect, an embodiment of the present application further provides an electronic device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the rule generation method as described in the first aspect above is implemented.

[0020] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the rule generation method described in the first aspect above.

[0021] According to the rule generation method of the embodiment provided by the present application, there are at least the following beneficial effects: in the process of rule generation, first, the original data is obtained; then, based on the original data, wide table data is created, wherein the wide table data includes multiple entry record data; then, feature calculation processing is performed on the multiple entry record data to obtain multiple feature information; then, based on a preset feature threshold set, the multiple feature information is filtered and processed to obtain multiple initial rules; then, cross-time verification processing is performed on the multiple initial rules to obtain verification information; finally, when the verification information indicates that the initial rule meets the preset verification requirement information, the corresponding initial rule can be used as the final rule. Through the above technical solution, wide table data is created based on the original data, and feature calculation processing is performed on the multiple entry record data in the wide table data to obtain multiple feature information, then, based on a feature threshold set, the multiple feature information is filtered and processed to obtain the initial rule, and finally, the obtained initial rule is verified and processed. When the verification meets the requirements, the final rule can be obtained. Through the above method, the final rule can be determined intelligently from the original data, which greatly improves the efficiency of rule generation and reduces the time required for rule generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to provide a further understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

[0023] Figure 1 This is a flowchart of a rule generation method provided by an embodiment of the present application;

[0024] Figure 2 yes Figure 1 A schematic flow chart of a specific implementation of step S200;

[0025] Figure 3 yes Figure 1 A schematic flow chart of a specific implementation of step S300;

[0026] Figure 4 yes Figure 1 A schematic flow chart of a specific implementation of step S400;

[0027] Figure 5 yes Figure 1 A schematic flow chart of a specific implementation of step S500;

[0028] Figure 6 yes Figure 5 A schematic flow chart of a specific implementation of step S530;

[0029] Figure 7 It is executed Figure 1 A schematic flow chart of a specific implementation method after step S600;

[0030] Figure 8 is a schematic diagram of a rule generation device provided by an embodiment of the present application;

[0031] Figure 9 This is a schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0033] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, used in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0034] It should be noted that, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0035] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0036] AI is a new technical discipline that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence. Artificial intelligence is a branch of computer science that seeks to understand the essence of intelligence and produce new intelligent machines that can respond in a manner similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. Artificial intelligence can simulate the information processes of human consciousness and thinking. It also refers to the theories, methods, technologies, and application systems that use 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 achieve optimal results.

[0037] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0038] Artificial intelligence, or AI, is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0039] The servers involved in artificial intelligence technology can be independent servers or cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), as well as big data and artificial intelligence platforms.

[0040] The present application provides a rule generation method, device, electronic device and computer-readable storage medium. In the process of rule generation, firstly, the original data is obtained; then, based on the original data, wide table data is created, wherein the wide table data includes multiple entry record data; then, feature calculation processing is performed on the multiple entry record data to obtain multiple feature information; then, based on a preset feature threshold set, the multiple feature information is filtered and processed to obtain multiple initial rules; then, cross-time verification processing is performed on the multiple initial rules to obtain verification information; finally, when the verification information indicates that the initial rule meets the preset verification requirement information, the corresponding initial rule can be used as the final rule. Through the above technical solution, wide table data is created based on the original data, and feature calculation processing is performed on the multiple entry record data in the wide table data to obtain multiple feature information, then, based on a feature threshold set, the multiple feature information is filtered and processed to obtain the initial rule, and finally, the obtained initial rule is verified and processed. When the verification meets the requirements, the final rule can be obtained. Through the above method, the final rule can be determined intelligently from the original data, which greatly improves the efficiency of rule generation and reduces the time required for rule generation.

[0041] The rule generation method provided in the embodiment of the present application relates to the field of rule generation technology. The rule generation method provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server side, and can also be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0042] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0043] It should be noted that in each specific embodiment of the present application, when it comes to the need to perform relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of such data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0044] The embodiments of the present application are further described below with reference to the accompanying drawings.

[0045] like Figure 1 As shown, Figure 1 This is a flowchart of a rule generation method provided by an embodiment of the present application, which includes the following steps:

[0046] Step S100: Obtain original data.

[0047] The rule generation method provided in the embodiment of the present application first needs to obtain original data from the running system during the rule generation process; the original data is the data stored during the system operation process; illustratively, for an insurance business management system, the original data may include policy number, customer gender, customer age, customer education, customer marital status, number of customer complaints in the past year, number of insurance agents complained about in the past year, whether complaints were made, type of insurance purchased, whether a claim was applied for, and number of claims applied for, etc.; or, for a pension insurance business management system, the original data may include customer age, type of insurance purchased by the customer, range of amount of pension insurance purchased by the customer, and pension insurance payment method, etc.

[0048] It should be noted that, during the rule generation process of this application, the user's permission or consent will be obtained before obtaining the original data, and the collection, use, and processing of such data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of this application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After the user's separate permission or consent is clearly obtained, the necessary user-related data for the normal operation of the embodiment of this application will be obtained.

[0049] It is worth noting that the original data can be a set of interrelated data. Taking the insurance business system as an example, for a policy number, it can correspond to a customer's gender, customer age, customer education, customer marital status, the number of customer complaints in the past year, the number of complaints against the agent in the past year, and whether the agent has been complained about. This is a set of interrelated data.

[0050] In the insurance industry, "rule generation" refers to the use of technical means such as rule engines to transform various insurance business rules (such as risk assessment, underwriting, claims settlement, premium calculation, etc.) into executable models to achieve automation and intelligent business processes. Insurance companies conduct risk analysis based on customer information (such as industry, address, type of goods, etc.) and generate rating results through rule models for underwriting decisions. The application of generated rules in underwriting business can improve underwriting efficiency and accuracy, achieve business standardization, and reduce the time-consuming manual analysis of underwriting data. In the claims business, generated rules realize the centralized management of claims rules, calculation of settlement formulas and log archiving, thereby improving the accuracy and risk resistance of claims. Generated rules realize information exchange with external platform systems, automate decision-making, reduce manual processing errors and delays, and improve efficiency.

[0051] Step S200: creating wide table data based on original data, wherein the wide table data includes a plurality of entry record data.

[0052] The rule generation method provided in the embodiments of the present application can create wide table data based on the raw data after obtaining the raw data, wherein the wide table data includes multiple entry records. Based on the wide table data, the raw data can be better statistically managed and processed to prepare for subsequent feature operations.

[0053] It's worth noting that wide tables are a common form of data organization. By integrating information from multiple related tables into a single wide table, they reduce the number of inter-table joins and thus improve the efficiency of data query and analysis. Wide table data can include a variety of different types of data, such as customer number, name, gender, date of birth, ID number, contact information, and address; customer type (e.g., individual, corporate), customer level (e.g., VIP, regular customer), and customer source (e.g., online, offline); policy number, policy status (e.g., effective, expired, terminated), insurance product type (e.g., life insurance, health insurance, property insurance), insurance amount, premium, insurance term, insurance start and end dates, policyholder information, insured information, agent information, and policy sales channel. Wide tables can consolidate information from multiple related tables into a single table, reducing inter-table join operations and improving query efficiency. Wide table design also reduces table joins, lowering the database's computational burden and improving query performance. Wide table structures are suitable for data warehouse and data lake analysis scenarios, enabling rapid report generation and data analysis. Wide table design makes data management and maintenance more intuitive, making it easier for insurance professionals to understand and use data. Wide table data can include multiple entry records, using complaint policies as the dimension, with each policy corresponding to one entry record.

[0054] like Figure 2 As shown, creating wide table data based on original data may include the following steps:

[0055] Step S210, performing dimension screening processing on the original data to obtain record dimension information;

[0056] Step S220, performing data combination processing according to the record dimension information to obtain multiple entry record data;

[0057] Step S230: merging multiple entry record data to obtain wide table data.

[0058] In steps S210 to S230, when creating wide table data based on raw data, the raw data is first dimensionally filtered to obtain record dimension information; then, data is combined based on the record dimension information to obtain multiple entry record data; and finally, the multiple entry record data are merged to obtain the corresponding wide table data. This technical solution allows for the quick and easy acquisition of the corresponding wide table data, preparing for the subsequent feature calculation of the entry records.

[0059] For example, for an insurance business system, by performing dimension screening on the original data in the insurance business system, the "policy number" can be used as the record dimension information; subsequently, data combination processing can be performed based on the "policy number", and related data belonging to the same "policy number" can be combined to obtain the entry record data corresponding to the "policy number"; subsequently, the entry record data of multiple "policy numbers" can be merged to obtain wide table data, which is prepared for subsequent feature calculations.

[0060] Step S300: performing feature calculation processing on a plurality of entry record data to obtain a plurality of feature information.

[0061] The rule generation method provided in the embodiment of the present application can perform feature calculation processing on multiple entry record data after creating wide table data based on original data, thereby obtaining multiple feature information to prepare for subsequent rule generation.

[0062] It's worth noting that by performing feature calculations on multiple entry records, multiple feature information can be obtained. For example, for insurance business systems, features can be divided into continuous features and discrete features. Continuous features include age and number of complaints, while discrete features include gender and educational background. Continuous features can be discretized first, using either equal-frequency or equal-width methods. Taking age as an example, equal-frequency segmentation means sorting the ages from smallest to largest. If the total sample size of the wide table is 10,000, and it is divided into five segments, each segment contains 2,000 samples. The maximum age corresponding to 2,000 samples is the upper limit of this item. Similarly, let's use 5 segments to illustrate equal-width segmentation. If the age range is 18-90 years old, and it needs to be divided into 5 segments, then the age is divided into 5 segments equally, and the age difference between each segment is (90-18) / 5=14.4. The corresponding segments of the 5 segments are [18,32.4), [32.4,46.8), [46.8,61.2), [61.2,75.6), [75.6,90). For ease of processing, the first segment can be changed to <32.4, and the last segment can be changed to >=75.6. Taking underwriting data as an example, we calculate the quantity of each value of each individual feature, the number of positive samples, the proportion of positive samples, the recall rate, etc.; taking age as an example after equal frequency segmentation, we count the corresponding statistical data of each of the five age groups (age <32.4, [32.4, 46.8), [46.8, 61.2), [61.2, 75.6), >=75.6). For example, in the age <32.4 segment, there are 1,000 samples that meet the age <32.4 years old, of which 100 have complaints, then the proportion of positive samples is 10%. If there are 500 complaint samples in the full sample, then the complaint recall rate is 100 / 500=20%.

[0063] like Figure 3 As shown, performing feature calculation processing on multiple entry record data to obtain multiple feature information may include the following steps:

[0064] Step S310, determining continuous feature information from the entry record data;

[0065] Step S320, performing equal-width division processing on the plurality of item record data according to the continuous characteristic information to obtain a plurality of divided data sets;

[0066] Step S330: performing feature extraction processing on the multiple divided data sets to obtain multiple feature information.

[0067] For steps S310 to S330, in the process of performing feature calculation processing on multiple entry record data, first determine the continuous feature information from the entry record data; then perform equal-width division processing on the multiple entry record data according to the continuous feature information to obtain multiple divided data sets; finally, perform feature extraction processing on the multiple divided data sets to obtain multiple feature information, in preparation for subsequent rule generation.

[0068] It is worth noting that in the process of feature calculation and processing, the continuous feature information is first determined from the item record data. For example, in the insurance business system, age and number of complaints are both continuous feature information; then, multiple item record data can be divided into equal widths according to age. If the age is 18-90 years old and is to be divided into 5 segments, then the age is divided into 5 segments, and the age difference of each segment is (90-18) / 5=14.4. The corresponding segments of the 5-segment divided data set are [18,32.4), [32.4,46.8), [46.8,61.2), [61.2,75.6), [75.6,90); subsequently, feature extraction processing can be performed on the multiple divided data sets, and then multiple feature information can be obtained to prepare for the subsequent initial rule generation.

[0069] Step S400: screening multiple feature information based on a preset feature threshold set to obtain multiple initial rules.

[0070] The rule generation method provided in the embodiment of the present application performs feature calculation processing on multiple entry record data to obtain multiple feature information. Then, the multiple feature information can be filtered based on a pre-set feature threshold set to obtain multiple initial rules. The feature threshold set includes multiple feature thresholds, each of which can be set according to actual needs. The feature information is compared with the feature thresholds in the feature threshold set, and the feature information that meets the preset requirements is used as the initial rule.

[0071] It is worth noting that in an embodiment of the present application, multiple feature information is screened and processed based on a pre-set feature threshold set; in the insurance business system, the rule generation method can be applied to multiple aspects, such as risk assessment rule generation, claims rule generation and premium calculation rule generation, among which risk assessment rule generation can automatically generate rules for assessing customer risk levels based on historical data and business logic; claims rule generation is used to generate rules for determining whether a claim application is reasonable, thereby improving the efficiency and accuracy of claims processing; premium calculation rule generation is used to generate premium calculation rules based on different insurance products and customer characteristics.

[0072] It is worth noting that the thresholds are dynamically adjusted according to business needs or data analysis results so that the feature thresholds in the feature threshold set are adjusted and processed, so that the feature thresholds in the feature threshold set can better adapt to the requirements of business development and provide a basis for subsequent business decisions or model construction.

[0073] like Figure 4 As shown, filtering multiple feature information based on a preset feature threshold set to obtain multiple initial rules may include the following steps:

[0074] Step S410: for each piece of feature information, select a target feature threshold from a feature threshold set according to the feature information;

[0075] Step S420, comparing the feature information with the target feature threshold to obtain feature comparison information;

[0076] Step S430: When the feature comparison information indicates that the feature information meets the preset comparison requirement, the corresponding feature information is determined as an initial rule.

[0077] For steps S410 to S430, after performing feature calculation processing on multiple entry record data to obtain multiple feature information, the multiple feature information can be screened based on a preset feature threshold set to obtain multiple initial rules; for each feature information, a target feature threshold can be selected from the feature threshold set based on the feature information; then the feature information is compared with the target feature threshold to obtain feature comparison information; finally, when the feature comparison information indicates that the feature information meets the pre-set comparison requirements, the corresponding feature information can be determined as the initial rule, making prerequisite preparations for the subsequent generation of final rules.

[0078] Exemplarily, for an insurance business system, the characteristic information may include sample size, positive sample size, positive sample ratio, and recall rate. The positive sample ratio and recall rate can be obtained based on the sample size and positive sample size. For example, the recall rate threshold is set to 20%. If the recall rate of the insurance business system is lower than the recall rate threshold of 20%, it is considered that the characteristic information does not meet the requirements; if the recall rate of the insurance business system is not lower than the recall rate threshold of 20%, it is considered that the characteristic information meets the requirements.

[0079] It's worth noting that this embodiment of the application presets a threshold for each feature (age, income, credit score) and defines a comparison requirement (such as greater than or less than). For each row of data, the actual value of each feature is compared with the preset threshold. If the comparison requirement is met, the feature information is added to the rule. If a row of data has multiple features that meet the conditions, the feature information that meets the requirements is combined into a single rule, and finally, duplicates are removed and all generated initial rules are output.

[0080] It is worth noting that in the embodiments of the present application, the threshold is dynamically adjusted according to business needs or data analysis results; then, multiple features are combined to generate more complex rules, such as using a decision tree or a rule engine; then, the generated rules are evaluated to ensure their accuracy and effectiveness, and optimized as needed; however, for large-scale data sets, parallel processing technology can be used to improve processing efficiency.

[0081] Step S500: Perform cross-time verification processing on multiple initial rules to obtain verification information.

[0082] The rule generation method provided in the embodiment of the present application, after filtering and processing multiple feature information based on a pre-set feature threshold set to obtain multiple initial rules, can then perform cross-time verification processing on the multiple initial rules to obtain verification information, and when the verification information indicates that the initial rule meets the pre-set verification requirement information, the corresponding initial rule will be used as the final rule; wherein, in the process of cross-time verification of multiple initial rules, the stability of the initial rule can be verified. In the embodiment of the present application, the stability of the initial rule can be evaluated using a group stability index; illustratively, when the group stability index is 0-0.1, it means that the initial rule has not changed or has changed very little during the verification process; when the group stability index is 0.1-0.25, it means that the initial rule is a little unstable during the verification process; when the group stability index is greater than 0.25, it means that the initial rule is relatively unstable during the verification process.

[0083] It is worth noting that after obtaining the initial rules, historical data can be used to verify the initial rules across time to verify the stability of the initial rules. If the subsequent verification meets the requirements, the corresponding initial rules can be determined as the final rules.

[0084] like Figure 5 As shown, performing cross-time verification processing on multiple initial rules to obtain verification information may include the following steps:

[0085] Step S510: for each initial rule, determine data type information based on the initial rule;

[0086] Step S520, extracting historical verification data from preset historical operation raw data according to the data type information;

[0087] Step S530: Verify the initial rules based on historical verification data to obtain verification information.

[0088] In steps S510 to S530, during the process of performing cross-temporal verification processing on multiple initial rules to obtain verification information, for each initial rule, data type information can be determined based on the initial rule; then, based on the data type information, historical verification data can be extracted from pre-set historical operation raw data; and finally, the initial rule can be verified based on the historical verification data to obtain corresponding verification information. Through the above technical solution, verification of the initial rules can be faster, more accurate, and more reliable.

[0089] It is worth noting that for each initial rule, for example, the initial rule is related to the number of complaints in the insurance business system, so the data type information can be determined based on the initial rule; then, the historical verification data related to the number of complaints can be extracted from the historical operation original data according to the data type information; subsequently, the initial rule can be verified based on the extracted historical verification data to obtain the corresponding verification information; subsequently, the final rule can be determined based on the verification information to facilitate subsequent business decision-making processing.

[0090] like Figure 6 As shown, the initial rules are verified based on historical verification data to obtain verification information, which may include the following steps:

[0091] Step S531, performing stability verification processing on the initial rule based on historical verification data to obtain a stability quantification value;

[0092] Step S532: Compare the stability quantification value with a preset stability setting threshold to obtain verification information.

[0093] For steps S531 to S532, in the process of verifying the initial rules based on historical verification data to obtain verification information, first, the initial rules are subjected to stability verification based on the historical verification data to obtain a stability quantification value, and then the stability quantification value is compared with a pre-set stability setting threshold to obtain verification information; through the above technical solution, verification information can be obtained simply, quickly and reliably, to prepare for the subsequent final rule generation.

[0094] It is worth noting that the stability of the initial rules can be verified based on historical verification data, and then the stability of the initial rules can be quantified to obtain a stability quantification value; subsequently, the stability quantification value can be compared with a pre-set stability setting threshold to obtain corresponding verification information; for example, when the stability of the initial rules is verified based on historical verification data, a stability quantification value of 0.3 is obtained, and the pre-set stability setting threshold is 0.4, so the stability quantification value can be compared with the pre-set stability setting threshold to obtain corresponding verification information.

[0095] Step S600: When the verification information indicates that the initial rule meets the preset verification requirement information, the corresponding initial rule is used as the final rule.

[0096] The rule generation method provided by the embodiment of the present application, after performing cross-time verification processing on multiple initial rules to obtain verification information, can use the corresponding initial rule as the final rule when the verification information indicates that the initial rule meets the pre-set verification requirement information. For example, for an insurance business system, a group stability index can be used to refer to the verification information, and the group stability index can be compared with a preset index, and the initial rule corresponding to the group stability index that meets the requirements can be used as the final rule; for example, the preset index can be set to 0.25, and it is required that the requirements are met only when the group stability index is lower than 0.25. Therefore, in the process of one verification comparison, the group stability index corresponding to an initial rule is 0.1. Since it is smaller than the preset index, the corresponding initial rule can be used as the final rule; and in another verification comparison process, the group stability index corresponding to an initial rule is 0.3. Since it is larger than the preset index and does not meet the requirements, the corresponding initial rule cannot be used as the final rule.

[0097] like Figure 7 As shown, when the verification information indicates that the initial rule meets the preset verification requirement information, after the corresponding initial rule is used as the final rule, the following steps may be included:

[0098] Step S710: transferring the final rule to the preset rule model to update the rule model;

[0099] Step S720: Perform risk screening on the received original verification data based on the updated rule model to obtain a risk screening result.

[0100] For steps S710 to S720, when the verification information indicates that the initial rule meets the preset verification requirement information, the corresponding initial rule can be used as the final rule, and then the final rule can be transferred to the pre-set rule model to update the rule model; then, the received original verification data can be subsequently risk checked based on the updated rule model, and the corresponding risk checking results can be obtained; through the above technical solution, a basis can be provided for subsequent risk checking based on the generated final rule, so that the subsequent risk checking can be more stable and reliable.

[0101] It is worth noting that the final rules are transferred to the pre-set rule model, and then the pre-set rule model can be updated to improve the risk identification accuracy of the rule model; subsequently, the received original verification data can be risk checked based on the updated scale model, making the risk check more accurate.

[0102] In addition, if Figure 8 As shown, an embodiment of the present application further provides a rule generating device 10, which includes:

[0103] An acquisition unit 100 is used to acquire original data;

[0104] A creating unit 200 is configured to create wide table data based on original data, wherein the wide table data includes a plurality of entry record data;

[0105] The calculation unit 300 is used to perform feature calculation processing on the plurality of item record data to obtain a plurality of feature information;

[0106] A screening unit 400 is configured to screen multiple feature information based on a preset feature threshold set to obtain multiple initial rules;

[0107] A verification unit 500 is used to perform cross-time verification processing on multiple initial rules to obtain verification information;

[0108] The selection unit 600 is configured to use the corresponding initial rule as the final rule when the verification information indicates that the initial rule meets the preset verification requirement information.

[0109] It should be noted that, in the process of rule generation, first obtain the original data; then create wide table data based on the original data, wherein the wide table data includes multiple entry record data; then perform feature calculation processing on the multiple entry record data to obtain multiple feature information; then perform screening processing on the multiple feature information based on a preset feature threshold set to obtain multiple initial rules; then perform cross-time verification processing on the multiple initial rules to obtain verification information; finally, when the verification information indicates that the initial rule meets the preset verification requirement information, the corresponding initial rule can be used as the final rule. Through the above technical solution, wide table data is created based on the original data, and feature calculation processing is performed on the multiple entry record data in the wide table data to obtain multiple feature information, then the multiple feature information is screened based on the feature threshold set to obtain the initial rule, and finally the obtained initial rule is verified. When the verification meets the requirements, the final rule can be obtained. Through the above method, the final rule can be determined intelligently from the original data, which greatly improves the efficiency of rule generation and reduces the time required for rule generation.

[0110] The specific implementation of the rule generation device 10 is substantially the same as the specific embodiment of the above-mentioned rule generation method, and will not be described in detail here.

[0111] In addition, if Figure 9 As shown, an embodiment of the present application further provides an electronic device 700 , which includes: a memory 720 , a processor 710 , and a computer program stored in the memory 720 and executable on the processor 710 .

[0112] The processor 710 and the memory 720 may be connected via a bus or other means.

[0113] The non-transitory software programs and instructions required to implement the rule generation methods of the above embodiments are stored in the memory 720 , and when executed by the processor 710 , the rule generation methods of the above embodiments are executed.

[0114] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0115] In addition, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are executed by a processor 710 or a controller, for example, by a processor 710 in the above-mentioned device embodiment, so that the above-mentioned processor 710 can execute the rule generation method in the above-mentioned embodiment.

[0116] The above embodiments may be used in combination, and modules with the same name in different embodiments may be the same or different.

[0117] The foregoing description describes specific embodiments of the present application, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0118] The various embodiments in this application are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, equipment, and computer-readable storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For relevant portions, refer to the descriptions of the method embodiments.

[0119] The apparatus, device, computer-readable storage medium and method provided in the embodiments of the present application correspond to each other. Therefore, the apparatus, device and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, device and computer storage medium will not be repeated here.

[0120] In the 1990s, technological improvements could be clearly distinguished as either hardware improvements (for example, improvements to circuit structures like diodes, transistors, and switches) or software improvements (improvements to process flows). However, with the advancement of technology, many process flow improvements today can now be considered direct improvements to hardware circuit structures. Designers almost always create the corresponding hardware circuit structure by programming the improved process flow into the hardware circuit. Therefore, it cannot be said that a process flow improvement cannot be implemented using hardware modules. For example, a programmable logic device (PLD), such as a field programmable gate array (FPGA), is an integrated circuit whose logical function is determined by user programming. Designers can "integrate" a digital system on a PLD through their own programming, without having to hire a chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly done using "logic compiler" software. This is similar to the software compiler used when developing programs. Before compilation, the original code must also be written in a specific programming language, called a hardware description language (HDL). There is not just one HDL, but many, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art will also understand that by simply programming the method flow in one of these hardware description languages ​​and then programming it into an integrated circuit, a hardware circuit that implements the logic method flow can be easily obtained.

[0121] The controller can be implemented in any suitable manner. For example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC625D, Atmel AT91 SAM, Microchip PIC18F26K20, and Silicone Labs C8051 F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also know that in addition to implementing the controller in a purely computer-readable program code format, the controller can be implemented in the form of logic gates, switches, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the means for implementing various functions included therein can also be considered as structures within the hardware component. Or even, the means for implementing various functions can be considered as both a software module implementing the method and a structure within the hardware component.

[0122] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0123] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing the embodiments of the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0124] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the embodiments of the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0126] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0127] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0128] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0129] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0130] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0131] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0132] In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c or a and b and c, where a, b, c can be single or multiple.

[0133] Embodiments of the present application may 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, and the like that perform specific tasks or implement specific abstract data types. Embodiments of the present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0134] The various embodiments in this application are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiment is generally similar to the method embodiment, so the description is relatively simple. For relevant parts, refer to the partial description of the method embodiment.

[0135] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included within the scope of the claims of the present application.

Claims

1. A rule generation method, characterized in that: include: Get the original data; Creating wide table data based on the original data, wherein the wide table data includes a plurality of entry record data; Performing feature calculation processing on the plurality of entry record data to obtain a plurality of feature information; Filtering the plurality of feature information based on a preset feature threshold set to obtain a plurality of initial rules; Performing cross-time verification processing on the plurality of initial rules to obtain verification information; In the case where the verification information indicates that the initial rule meets the preset verification requirement information, the corresponding initial rule is used as the final rule.

2. The rule generation method according to claim 1, characterized in that: The creating wide table data based on the original data includes: Performing dimension screening processing on the original data to obtain record dimension information; Performing data combination processing according to the record dimension information to obtain a plurality of the item record data; A plurality of the entry record data are merged to obtain the wide table data.

3. The rule generation method according to claim 1, characterized in that: The feature calculation process is performed on the plurality of entry record data to obtain a plurality of feature information, including: determining continuous feature information from the entry record data; Performing equal-width division processing on the plurality of item record data according to the continuous characteristic information to obtain a plurality of divided data sets; Feature extraction processing is performed on the plurality of divided data sets to obtain a plurality of feature information.

4. The rule generation method according to claim 1, characterized in that: The filtering and processing of the plurality of feature information based on the preset feature threshold set to obtain the plurality of initial rules includes: For each piece of feature information, selecting a target feature threshold from the feature threshold set according to the feature information; Comparing the feature information with the target feature threshold to obtain feature comparison information; In a case where the feature comparison information indicates that the feature information meets a preset comparison requirement, the corresponding feature information is determined as the initial rule.

5. The rule generation method according to claim 1, characterized in that: The performing of cross-time verification processing on the plurality of initial rules to obtain verification information includes: For each of the initial rules, determining data type information based on the initial rule; Extracting historical verification data from preset historical operation raw data according to the data type information; The initial rule is verified based on the historical verification data to obtain the verification information.

6. The rule generation method according to claim 5, characterized in that: The verifying the initial rule based on the historical verification data to obtain the verification information includes: Performing stability verification processing on the initial rule based on the historical verification data to obtain a stability quantification value; The stability quantification value is compared with a preset stability setting threshold to obtain the verification information.

7. The rule generation method according to claim 1, characterized in that: When the verification information indicates that the initial rule meets the preset verification requirement information, after taking the corresponding initial rule as the final rule, the method further includes: Transferring the final rule to a preset rule model to update the rule model; Based on the updated rule model, risk screening is performed on the received original verification data to obtain a risk screening result.

8. A rule generating device, characterized in that: The rule generating device comprises: An acquisition unit, used for acquiring original data; a creating unit, configured to create wide table data based on the original data, wherein the wide table data includes a plurality of entry record data; a calculation unit, configured to perform feature calculation processing on the plurality of item record data to obtain a plurality of feature information; a screening unit, configured to screen the plurality of feature information based on a preset feature threshold set to obtain the plurality of initial rules; a verification unit, configured to perform cross-time verification processing on the plurality of initial rules to obtain verification information; The selection unit is configured to use the corresponding initial rule as the final rule when the verification information indicates that the initial rule meets preset verification requirement information.

9. An electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the rule generation method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing computer-executable instructions, characterized in that: The computer-executable instructions are used to execute the rule generation method according to any one of claims 1 to 7.

Images