Verification rule generation method and device, storage medium and computer equipment

Abstract

The invention discloses a verification rule generation method and device, a storage medium and computer equipment, and the method comprises the steps: responding to verification rule generation signals of different insurance items, and obtaining the item attribute information, verification demand information and item source information of each insurance item, and the user feature information of an insurance user of the audience of each insurance item; determining a demand verification rule of each insurance project based on the project attribute information, the verification demand information, the project source information and the user feature information; determining rule attribute information of each demand verification rule, and classifying each demand verification rule based on the rule attribute information to obtain a target rule category to which each demand verification rule belongs; and respectively determining a rule generation mode corresponding to each target rule category, and generating a verification rule of the corresponding insurance item by using the rule generation mode.

Description

Technical Field

[0001] The present invention relates to the fields of information technology and financial technology, and in particular to a verification rule generation method, device, storage medium and computer equipment. Background Art

[0002] With the continuous development of society and people's growing demand for protection, various insurance products are emerging one after another. In order to ensure the accuracy of various information in insurance products, it is necessary to perform rule verification on insurance products. Based on this, it is first necessary to write various verification rules.

[0003] At present, various verification rules are usually generated by writing source code in a unified way. However, this rule generation method requires technicians to rewrite the source code for each rule, resulting in low rule generation efficiency. At the same time, due to the uneven technical levels of technicians, code writing errors may occur, resulting in low rule generation accuracy. Summary of the invention

[0004] The present invention provides a verification rule generation method, device, storage medium and computer equipment, which are mainly capable of improving the generation efficiency and generation accuracy of insurance product verification rules.

[0005] According to a first aspect of the present invention, there is provided a verification rule generation method, comprising:

[0006] In response to verification rule generation signals of different insurance items, obtaining item attribute information, verification requirement information, item source information, and user characteristic information of insured users covered by each insurance item;

[0007] Determine the requirement verification rules for each of the insurance items based on the item attribute information, the verification requirement information, the item source information, and the user characteristic information;

[0008] Determine the rule attribute information of each of the demand verification rules, and classify each of the demand verification rules based on the rule attribute information to obtain the target rule category to which each of the demand verification rules belongs;

[0009] The rule generation methods corresponding to the target rule categories are determined respectively, and the verification rules of the corresponding insurance items are generated by using the rule generation methods.

[0010] Optionally, the rule attribute information includes: the number of verification conditions of each verification condition in the verification rule, and the association relationship between each of the verification conditions;

[0011] The classifying each of the demand verification rules based on the rule attribute information to obtain the target rule category to which each of the demand verification rules belongs includes:

[0012] Based on the number of verification conditions corresponding to each of the verification conditions and the association relationship, determine the verification logic complexity corresponding to each of the demand verification rules, and judge whether the verification logic complexity is less than a preset threshold;

[0013] If the verification logic complexity is less than the preset threshold, the demand verification rule is classified as a simple verification rule to be generated; if the verification logic complexity is greater than or equal to the preset threshold, the demand verification rule is classified as a complex verification rule to be generated.

[0014] Optionally, the determining the verification logic complexity corresponding to each of the requirement verification rules based on the number of verification conditions corresponding to each of the verification conditions and the association relationship includes:

[0015] Determine whether there is a correlation relationship between the verification conditions;

[0016] If the association relationship does not exist, the verification logic complexity corresponding to each of the requirement verification rules is set based on the number of verification conditions. If the association relationship exists, the relationship type to which the association relationship belongs is determined, and the verification logic complexity corresponding to each of the requirement verification rules is set based on the relationship type and the number of verification conditions.

[0017] Optionally, the rule generation method generates verification rules for corresponding insurance items, including:

[0018] Determine a script generation method corresponding to the simple verification rule to be generated, and generate the simple verification rule using the script generation method;

[0019] A hard-coded generation method corresponding to the complex verification rule to be generated is determined, and the complex verification rule is generated using the hard-coded generation method.

[0020] Optionally, the generating a simple verification rule by using the script generating method includes:

[0021] Determine the rule type corresponding to the simple verification rule to be generated, and determine the rule script template corresponding to the rule type, wherein the rule script template includes the general rule code and configurable parameter items under the rule type;

[0022] Determine the verification parameters in the simple verification rule to be generated, and fill the verification parameters into the preset positions corresponding to the configurable parameter items in the rule script template to obtain the simple verification rule;

[0023] After generating the simple verification rules by using the script generation method, the method further includes:

[0024] The simple verification rule is sent to the verification terminal for rule verification. If the verification passes, it is determined that the generation accuracy of the simple verification rule meets the generation requirement. If the verification fails, the simple verification rule is regenerated.

[0025] Optionally, after generating the verification rules for the corresponding insurance items by using the rule generation method, the method further includes:

[0026] Based on the correspondence between each of the insurance items and the corresponding verification rules, a verification rule list is constructed;

[0027] In response to the verification signal of the target insurance item, the insurance verification rule corresponding to the target insurance item is determined based on the verification rule list, and the target insurance item is subjected to rule verification using the insurance verification rule.

[0028] Optionally, the determining of the demand verification rules for each of the insurance items based on the item attribute information, the verification requirement information, the item source information, and the user characteristic information includes:

[0029] Determine an attribute feature vector corresponding to the project attribute information, a requirement feature vector corresponding to the verification requirement information, a source feature vector corresponding to the project source information, and a user feature vector corresponding to the user feature information;

[0030] Cross-processing the attribute feature vector, the demand feature vector, the source feature vector, and the user feature vector to obtain a verification rule cross-vector;

[0031] The verification rule cross vector is input into a preset verification rule prediction model to perform rule prediction to obtain the demand verification rule.

[0032] According to a second aspect of the present invention, there is provided a verification rule generating device, comprising:

[0033] An acquisition unit, for generating signals in response to verification rules of different insurance items, and acquiring item attribute information, verification requirement information, item source information, and user characteristic information of insured users covered by each insurance item of each insurance item;

[0034] A determination unit, configured to determine a requirement verification rule for each of the insurance items based on the item attribute information, the verification requirement information, the item source information, and the user characteristic information;

[0035] A classification unit, used to determine rule attribute information of each of the demand verification rules, and classify each of the demand verification rules based on the rule attribute information to obtain a target rule category to which each of the demand verification rules belongs;

[0036] The generating unit is used to respectively determine the rule generating methods corresponding to each of the target rule categories, and generate the verification rules of the corresponding insurance items by using the rule generating methods.

[0037] According to a third aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, which implements the above rule generation method when executed by a processor.

[0038] According to a fourth aspect of the present invention, there is provided a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above rule generation method when executing the program.

[0039] According to a verification rule generation method, device, storage medium and computer equipment provided by the present invention, compared with the current method of generating various verification rules by adopting a unified source code writing method, the present invention specifies the demand verification rules for each insurance project by comprehensively analyzing the project attribute information, verification requirement information, project source information and user characteristic information of the insured users of each insurance project, thereby improving the accuracy of the formulation of the demand verification rules. Then, according to the attribute information of the demand verification rules, the rule category to which each insurance project belongs is determined. Since different rule generation methods are formulated in advance for different rule categories, a rule generation method applicable to the insurance project is selected according to the rule category of the insurance project, and finally the verification rules for the corresponding insurance project are generated using the rule generation method. Therefore, the present invention selects the applicable rule generation method for the insurance project according to the rule category, which can avoid the waste of generation time and code writing resources when all rules are generated by a unified source code writing method, and can also avoid the situation of source code writing errors, so that the present invention can improve the generation efficiency and generation accuracy of insurance verification rules. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0041] Figure 1 A flow chart of a verification rule generation method provided by an embodiment of the present invention is shown;

[0042] Figure 2Another flow chart of a verification rule generation method provided by an embodiment of the present invention is shown;

[0043] Figure 3 A schematic diagram of the structure of a verification rule generating device provided by an embodiment of the present invention is shown;

[0044] Figure 4 A schematic diagram of the physical structure of a computer device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0045] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0046] At present, various verification rules are generated by uniformly writing source code. Each rule requires technicians to rewrite the source code, resulting in low rule generation efficiency. At the same time, due to the uneven technical levels of technicians, code writing errors may occur, resulting in low rule generation accuracy.

[0047] In order to solve the above problems, the embodiment of the present invention provides a verification rule generation method, such as Figure 1 As shown, the method includes:

[0048] 101. In response to verification rule generation signals of different insurance items, obtain item attribute information, verification requirement information, item source information, and user characteristic information of insured users covered by each insurance item.

[0049] Among them, project attribute information includes: project type of insurance project (such as health insurance, property insurance, life insurance, etc.), coverage content, etc.; verification requirement information refers to the verification requirements proposed by the project manager of the insurance project for the insurance project, such as data format verification requirements, data range verification requirements, etc.; project source information includes: insurance projects produced by the company's APP, insurance projects produced by third-party companies, etc.; user characteristic information includes: age range, gender range, occupation range, health status, interests and hobbies of the target users of the insurance project.

[0050] For the embodiment of the present invention, when verification rules for different insurance items need to be generated, it is first necessary to obtain the project attribute information, verification requirement information, project source information, and user characteristic information of the insured users of each insurance item. It should be noted that the project attribute information, verification requirement information, project source information, and user characteristic information obtained in this embodiment are not private data, but relevant information (non-private data) that can be obtained in the process of generating verification rules.

[0051] 102. Determine the demand verification rules for each insurance project based on project attribute information, verification requirement information, project source information, and user characteristic information.

[0052] Among them, the required verification rules include field value non-empty verification, field value size verification, enumeration verification, etc.

[0053] After obtaining the project attribute information, verification requirement information, project source information, and user characteristic information of the insured users of each insurance project, the project attribute information, verification requirement information, project source information, and user characteristic information are comprehensively analyzed, and the demand verification rules of each insurance project are determined according to the analysis results. The embodiment of the present invention can improve the accuracy of determining the demand verification rules by comprehensively analyzing the project attribute information, verification requirement information, project source information, and user characteristic information to determine the demand verification rules.

[0054] 103. Determine the rule attribute information of each demand verification rule, and classify the demand verification rules based on the rule attribute information to obtain the target rule category to which each demand verification rule belongs.

[0055] Among them, the rule attribute information includes: the number of verification conditions in the requirement verification rules and the relationship between each verification condition, such as logical relationship, hierarchical relationship, dependency relationship, verification order relationship, etc.; the target rule categories include: simple verification rules, complex verification rules, etc.

[0056] For the embodiment of the present invention, in order to determine the rule generation method applicable to the demand verification rule, it is first necessary to classify the demand verification rule. Based on this, the method includes: determining the centroid vectors corresponding to different rule categories; and determining the attribute feature vectors corresponding to the rule attribute information of the demand verification rule; respectively calculating the Euclidean distance between the attribute feature vector and the centroid vector under each of the rule categories; and determining the target rule category to which the demand verification rule belongs based on the Euclidean distance. That is, the rule category with the shortest Euclidean distance is determined as the target rule category to which the demand verification rule belongs, and then the demand verification rule is generated using the rule generation method corresponding to the target rule category. Since different rule categories correspond to different rule generation methods, the embodiment of the present invention can determine the applicable rule generation method for the demand verification rule according to the target rule category by determining the target rule category to which the demand verification rule belongs, thereby ensuring that the verification rule generated using the rule generation method is more accurate, and can also avoid the waste of rule generation resources and rule generation time when using a complex generation method to generate simple rules, so that the embodiment of the present invention can also save rule generation resources and save rule generation time.

[0057] 104. Determine the rule generation method corresponding to each target rule category respectively, and use the rule generation method to generate verification rules for corresponding insurance items.

[0058] For the embodiment of the present invention, simple rules correspond to simple generation methods, and complex rules correspond to complex generation methods. The simple generation method can also ensure the generation accuracy of simple rules. The embodiment of the present invention specifies different rule generation methods for different rule categories, thereby avoiding the waste of rule generation resources caused by using a complex rule generation method of writing source code to generate all rules.

[0059] According to a verification rule generation method provided by the present invention, compared with the current method of generating various verification rules by adopting a unified source code writing method, the present invention specifies the demand verification rules for each insurance project by comprehensively analyzing the project attribute information, verification requirement information, project source information, and user characteristic information of the insured users of each insurance project, thereby improving the accuracy of the formulation of the demand verification rules. Then, according to the attribute information of the demand verification rules, the rule category to which each insurance project belongs is determined. Since different rule generation methods are formulated in advance for different rule categories, a rule generation method applicable to the insurance project is selected according to the rule category of the insurance project, and finally the verification rules for the corresponding insurance project are generated using the rule generation method. Therefore, the present invention selects the applicable rule generation method for the insurance project according to the rule category, which can avoid the generation time and code writing resources wasted when all rules are generated by a unified source code writing method, and can also avoid source code writing errors. Therefore, the present invention can improve the generation efficiency and generation accuracy of insurance verification rules.

[0060] Further, in order to better illustrate the process of generating the verification rules, as a refinement and extension of the above embodiment, the embodiment of the present invention provides another verification rule generation method, such as Figure 2 As shown, the method includes:

[0061] 201. In response to verification rule generation signals of different insurance items, obtain item attribute information, verification requirement information, item source information, and user characteristic information of insured users covered by each insurance item.

[0062] According to the embodiment of the present invention, the project attribute information, verification requirement information, project source information, and user characteristic information of the insured users covered by each insurance project can be obtained from sources such as the project database.

[0063] 202. Determine the demand verification rules for each insurance project based on project attribute information, verification requirement information, project source information, and user characteristic information.

[0064] For the embodiment of the present invention, after obtaining the project attribute information, verification requirement information, project source information, and user characteristic information, it is necessary to determine the demand verification rules for each insurance project based on the project attribute information, verification requirement information, project source information, and user characteristic information. Based on this, step 202 specifically includes: determining the attribute feature vector corresponding to the project attribute information, the demand feature vector corresponding to the verification requirement information, the source feature vector corresponding to the project source information, and the user feature vector corresponding to the user characteristic information; cross-processing the attribute feature vector, the demand feature vector, the source feature vector, and the user feature vector to obtain a verification rule cross vector; inputting the verification rule cross vector into a preset verification rule prediction model for rule prediction to obtain the demand verification rule. Among them, the method for cross-processing the attribute feature vector, the requirement feature vector, the source feature vector, and the user feature vector includes: performing feature-level cross-processing on the attribute feature vector, the requirement feature vector, the source feature vector, and the user feature vector to obtain a feature cross-vector; performing element-level cross-processing on the attribute feature vector, the requirement feature vector, the source feature vector, and the user feature vector to obtain an element cross-vector; performing low-order cross-processing on the attribute feature vector, the requirement feature vector, the source feature vector, and the user feature vector to obtain a low-order cross-vector; and using a preset transformation function to transform the feature cross-vector, the element cross-vector, and the low-order cross-vector to obtain the verification rule cross-vector.

[0065] Specifically, firstly, word embedding and other methods are used to respectively determine the attribute feature vector corresponding to the project attribute information, the demand feature vector corresponding to the verification demand information, the source feature vector corresponding to the project source information, and the user feature vector corresponding to the user feature information. Since the project attribute information, verification demand information, project source information, and user feature information are different fields, the processing method is to embed the data of the four fields into vectors of the same latitude. For example, if the attribute feature vector is (a1, a2), the demand feature vector is (b1, b2), the source feature vector is (c1, c2), and the user feature vector is (d1, d2), the specific cross processing method includes: performing feature-level crossover between different feature vectors, that is, performing Hadamard product on all elements between vectors, and then performing convolution transformation under certain weights to obtain a feature crossover vector of f(w*(a1*b1*c1*d1,a2*b2*c2*d2,a3*b3*c3*d3)); at the same time, performing element-level crossover on all feature vector data, that is, performing Hadamard product on each element between vectors, and giving The result after each multiplication is assigned a different weight value, and then a linear transformation is performed, and the obtained element cross vector is f(w1*a1*b1*c1*d1, w2*a2*b2*c2*d2, w3*a3*b3*c3*d3); in addition, all feature vectors are subjected to low-order cross processing, and weight coefficients are assigned to the results after the cross processing, and then a linear transformation is performed, and the obtained low-order cross vector is f(w2(a1, a2, b1, b2, c1, c2, d1, d2)); finally, the above feature cross vectors, element cross vectors, and low-order cross vectors are combined together, and the preset function is used for transformation processing to obtain a rule verification cross vector. The preset function here can be set according to the actual situation, and this embodiment does not limit this. It should be noted that the above examples are only illustrative and do not limit the embodiments of the present application. Therefore, by cross-processing the attribute feature vector, demand feature vector, source feature vector, and user feature vector, different features can be automatically or explicitly combined to generate new feature combinations. These combined features may contain complex nonlinear relationships between the original features, so that the model can capture more detailed and rich information in the data, that is, it can make full use of the relationship between various data, extract more implicit features, and take into account both high-order and low-order processing, so that data utilization is more complete, and the verification rule generation results obtained later are more accurate, meeting the needs of actual application scenarios.

[0066] 203. Determine the number of verification conditions for each verification condition in each requirement verification rule and the correlation between each verification condition.

[0067] Among them, each check condition includes: not empty check condition, comparison operation check condition, inclusion / non-inclusion check condition, value range check condition, etc.; the association relationship includes: logical association relationship between each check condition, hierarchical association relationship between each check condition, dependent association relationship between each check condition, etc. The logical association relationship between each check condition is such as "and", "or", "not", etc. These logical relationships determine how multiple check conditions work together in a data verification process, hierarchical association relationship between each check condition, hierarchical association relationship between each check condition means that the check conditions may be organized according to a hierarchical structure, and some of the check conditions may depend on the results of other check conditions, such as preconditions: some check conditions may need to be verified before other conditions. For example, before verifying whether a field conforms to a specific format, it may be necessary to verify whether the field has been filled in, cascade verification: when the value of a field meets or does not meet a certain condition, the verification of another field is triggered. For example, when the "Country" field is selected as "China", you may need to verify whether the "ID Number" field conforms to the Chinese ID number format. The dependency relationship between the various verification conditions means that there may be a dependency between the verification conditions, that is, the validity of one verification condition may depend on the results of another or more verification conditions, including inter-field dependency: the verification of one field may depend on the value of another field. For example, when filling in the "Province" and "City" fields, you may need to ensure that the value of the "City" field is a valid city under the selected "Province". Dependency between data tables: In some complex data verification scenarios, the verification of one data table may depend on the data in another data table. For example, when verifying user information, you may need to ensure that the ID number entered by the user is not repeated in another table.

[0068] 204. Based on the number and correlation of verification conditions corresponding to each verification condition, determine the verification logic complexity corresponding to each requirement verification rule.

[0069] For the embodiment of the present invention, in order to classify the demand verification rules, it is first necessary to determine the verification logic complexity corresponding to the demand verification rules. Based on this, step 204 specifically includes: judging whether there is an association relationship between each of the verification conditions; if the association relationship does not exist, then based on the number of verification conditions, setting the verification logic complexity corresponding to each of the demand verification rules; if the association relationship exists, determining the relationship type to which the association relationship belongs, and based on the relationship type and the number of verification conditions, setting the verification logic complexity corresponding to each of the demand verification rules.

[0070] Specifically, if there is no association between the various verification conditions in the demand verification rules, the verification logic complexity is set according to the number of verification conditions. For example, as the number of verification conditions increases, the corresponding verification logic complexity also increases. On the contrary, if there is an association between the various verification conditions, the verification logic complexity is set according to the relationship type corresponding to the association and the number of verification conditions. If there is only a simple association between the various verification conditions and the number of verification conditions is small, a lower verification logic complexity can be set at this time. If there is a complex association between the various verification conditions, or the number of verification conditions is large, a higher verification logic complexity can be set at this time.

[0071] 205. Based on the complexity of the verification logic, classify each requirement verification rule to obtain the target rule category to which each requirement verification rule belongs.

[0072] Specifically, if the verification logic complexity of the demand verification rule is less than a preset threshold (the preset threshold is set according to actual needs), the demand verification rule is classified as a simple verification rule to be generated; if the verification logic complexity is greater than or equal to the preset threshold, the demand verification rule is classified as a complex verification rule to be generated, and then, according to the category described in the demand verification rule, a suitable rule generation method is selected to generate the verification rule. Thus, by classifying the verification rules and selecting a suitable rule generation method according to the classification category, the accuracy of rule generation can be ensured, and the time and rule generation resources wasted by using a complex rule generation method to generate verification rules can be avoided.

[0073] 206. Determine the rule generation method corresponding to each target rule category respectively, and use the rule generation method to generate verification rules for corresponding insurance items.

[0074] For the embodiment of the present invention, after determining the target rule category to which the demand verification rule belongs, in order to determine a suitable rule generation method for the demand verification rule based on the target rule category, step 206 specifically includes: determining a script generation method corresponding to the simple verification rule to be generated, and using the script generation method to generate the simple verification rule; determining a hard-coded generation method corresponding to the complex verification rule to be generated, and using the hard-coded generation method to generate the complex verification rule.

[0075] Specifically, if the demand verification rule belongs to a simple verification rule, the demand verification rule is generated by using a script generation method corresponding to the simple verification rule; if the demand verification rule belongs to a complex verification rule, the demand verification rule is generated by using a hard-coded generation method corresponding to the complex verification rule. The method of generating the demand verification rule by using a script generation method specifically includes: determining the rule type corresponding to the simple verification rule to be generated, and determining a rule script template corresponding to the rule type, wherein the rule script template includes a general rule code and configurable parameter items under the rule type; determining the verification parameters in the simple verification rule to be generated, and filling the verification parameters into the preset position corresponding to the configurable parameter item in the rule script template to obtain the simple verification rule.

[0076] Among them, rule types include: field non-empty check type, value range check type, value size check type, enumeration type, etc. Different rule script templates are pre-built for different rule types. The rule script template stores the general rule code and configurable parameter items under the corresponding rule type; the check parameters in the simple check rule are, for example, if the check rule is to determine whether the age is between 18 and 50 years old, then the corresponding check parameters are 18 and 50; the preset position corresponds to the blank position of the configurable parameter item.

[0077] Specifically, after determining the rule type to which the simple verification rule belongs, based on the corresponding relationship between different rule types and rule script templates, determine the rule script template corresponding to the rule type, and then determine the verification parameters in the simple verification rule to be generated, and select the verification parameters in the form of a drop-down menu in the rule script template, or manually configure the verification parameters in the blank position corresponding to the configurable parameter item in the rule script template. In this way, the method of generating simple rules through rule script templates can improve the generation efficiency and accuracy of rules, and avoid the time wasted by manual recoding and writing errors.

[0078] Furthermore, after generating simple verification rules using rule script templates, in order to further improve the accuracy of rule generation, it is necessary to test the generated simple verification rules. Based on this, the method includes: sending the simple verification rules to the inspection terminal for rule inspection, and if the inspection passes, determining that the generation accuracy of the simple verification rules meets the generation requirements, and if the inspection fails, regenerating the simple verification rules. Specifically, the simple verification rules are sent to the inspection terminal for inspection, and if the inspection passes, the simple verification rules are published, otherwise the simple verification rules need to be regenerated until the simple verification rules pass the inspection. Similarly, in order to improve the accuracy of complex verification rules generated by hard coding, the generated complex verification rules can also be sent to the inspection terminal for inspection.

[0079] Furthermore, after generating verification rules corresponding to each insurance item, in order to apply the verification rules, the method includes: constructing a verification rule list based on the correspondence between each of the insurance items and the corresponding verification rules; in response to the verification signal of the target insurance item, determining the insurance verification rule corresponding to the target insurance item based on the verification rule list, and performing rule verification on the target insurance item using the insurance verification rule.

[0080] Specifically, after generating the verification rules corresponding to each insurance item, a mapping relationship between each insurance item and its corresponding verification rule is established, and based on the mapping relationship, a verification rule list is constructed. When a signal for verifying a target insurance item is received, the target insurance item is matched with each insurance item in the verification rule list to find an insurance item matching the target insurance item in the verification rule list, and the verification rule corresponding to the matched insurance item is determined, and finally the target insurance item is verified using the verification rule. Thus, by constructing a verification rule list, it is possible to facilitate the determination of the verification rules for each insurance item and improve the efficiency of determining the verification rules.

[0081] According to another verification rule generation method provided by the present invention, compared with the current method of generating various verification rules by adopting a unified source code writing method, the present invention specifies the demand verification rules for each insurance project by comprehensively analyzing the project attribute information, verification requirement information, project source information, and user characteristic information of the insured users of each insurance project, thereby improving the accuracy of the formulation of the demand verification rules. Then, according to the attribute information of the demand verification rules, the rule category to which each insurance project belongs is determined. Since different rule generation methods are formulated in advance for different rule categories, a rule generation method applicable to the insurance project is selected according to the rule category of the insurance project, and finally the verification rules for the corresponding insurance project are generated using the rule generation method. Therefore, the present invention selects the applicable rule generation method for the insurance project according to the rule category, which can avoid the generation time and code writing resources wasted when all rules are generated by a unified source code writing method, and can also avoid source code writing errors. Therefore, the present invention can improve the generation efficiency and generation accuracy of insurance verification rules.

[0082] Further, as Figure 1 The specific implementation of the present invention provides a verification rule generation device, such as Figure 3 As shown, the device includes: an acquisition unit 31, a determination unit 32, a classification unit 33, and a generation unit 34.

[0083] The acquisition unit 31 can be used to generate signals in response to verification rules of different insurance projects, and acquire project attribute information, verification requirement information, project source information, and user feature information of insured users covered by each insurance project.

[0084] The determination unit 32 may be configured to determine a requirement verification rule for each of the insurance items based on the item attribute information, the verification requirement information, the item source information, and the user characteristic information.

[0085] The classification unit 33 may be used to determine rule attribute information of each of the demand verification rules, and classify each of the demand verification rules based on the rule attribute information to obtain a target rule category to which each of the demand verification rules belongs.

[0086] The generating unit 34 may be used to respectively determine the rule generating methods corresponding to the target rule categories, and generate verification rules for corresponding insurance items using the rule generating methods.

[0087] In a specific application scenario, the rule attribute information includes: the number of verification conditions of each verification condition in the verification rule, and the correlation between each verification condition; in order to classify each requirement verification rule, the classification unit 33 includes a first determination module 331 and a classification module 332.

[0088] The first determination module 331 can be used to determine the verification logic complexity corresponding to each of the requirement verification rules based on the number of verification conditions corresponding to each of the verification conditions and the association relationship, and determine whether the verification logic complexity is less than a preset threshold.

[0089] The classification module 332 can be used to classify the demand verification rule as a simple verification rule to be generated if the verification logic complexity is less than the preset threshold, and to classify the demand verification rule as a complex verification rule to be generated if the verification logic complexity is greater than or equal to the preset threshold.

[0090] In a specific application scenario, in order to determine the verification logic complexity corresponding to each requirement verification rule, the first determination module 331 can be specifically used to determine whether there is an association relationship between each of the verification conditions; if the association relationship does not exist, then based on the number of verification conditions, the verification logic complexity corresponding to each of the requirement verification rules is set; if the association relationship exists, then the relationship type to which the association relationship belongs is determined, and based on the relationship type and the number of verification conditions, the verification logic complexity corresponding to each of the requirement verification rules is set.

[0091] In a specific application scenario, in order to generate verification rules for corresponding insurance items, the generation unit 34 can be specifically used to determine a script generation method corresponding to the simple verification rules to be generated, and use the script generation method to generate simple verification rules; determine a hard-coded generation method corresponding to the complex verification rules to be generated, and use the hard-coded generation method to generate complex verification rules.

[0092] In a specific application scenario, in order to generate a simple verification rule by using a script generation method, the generation unit 34 includes a second determination module 341 and a filling module 342 .

[0093] The second determination module 341 can be used to determine the rule type corresponding to the simple verification rule to be generated, and determine the rule script template corresponding to the rule type, wherein the rule script template includes the general rule code and configurable parameter items under the rule type.

[0094] The filling module 342 may be used to determine the verification parameters in the simple verification rule to be generated, and fill the verification parameters into the preset positions corresponding to the configurable parameter items in the rule script template to obtain the simple verification rule.

[0095] In a specific application scenario, in order to verify the rules, the generating unit 34 further includes a verification module 343 .

[0096] The inspection module 343 may be used to send the simple verification rule to the inspection terminal for rule inspection. If the inspection passes, it is determined that the generation accuracy of the simple verification rule meets the generation requirements. If the inspection fails, the simple verification rule is regenerated.

[0097] In a specific application scenario, in order to perform rule verification on the target insurance item, the device further includes: a construction unit 35 and a verification unit 36 ​​.

[0098] The construction unit 35 may be used to construct a verification rule list based on the correspondence between each of the insurance items and the corresponding verification rules.

[0099] The verification unit 36 ​​may be configured to respond to a verification signal of a target insurance item, determine an insurance verification rule corresponding to the target insurance item based on the verification rule list, and perform rule verification on the target insurance item using the insurance verification rule.

[0100] In a specific application scenario, in order to determine the demand verification rules for each insurance item, the determination unit 32 includes a third determination module 321 , a cross module 322 , and a prediction module 323 .

[0101] The third determination module 321 may be used to determine an attribute feature vector corresponding to the project attribute information, a requirement feature vector corresponding to the verification requirement information, a source feature vector corresponding to the project source information, and a user feature vector corresponding to the user feature information.

[0102] The cross module 322 may be used to perform cross processing on the attribute feature vector, the demand feature vector, the source feature vector, and the user feature vector to obtain a verification rule cross vector.

[0103] The prediction module 323 may be used to input the verification rule cross vector into a preset verification rule prediction model to perform rule prediction and obtain the demand verification rule.

[0104] It should be noted that for other corresponding descriptions of the functional modules involved in the verification rule generation device provided in the embodiment of the present invention, reference can be made to Figure 1 The corresponding description of the method shown will not be repeated here.

[0105] Based on the above Figure 1 The method shown, accordingly, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the following steps are implemented: in response to verification rule generation signals of different insurance projects, the project attribute information, verification requirement information, project source information, and user characteristic information of the insured users of each insurance project are obtained; based on the project attribute information, the verification requirement information, the project source information, and the user characteristic information, the requirement verification rules of each insurance project are determined; the rule attribute information of each requirement verification rule is determined, and based on the rule attribute information, each requirement verification rule is classified to obtain the target rule category to which each requirement verification rule belongs; the rule generation method corresponding to each target rule category is determined respectively, and the verification rules of the corresponding insurance project are generated by using the rule generation method.

[0106] Based on the above Figure 1 The method shown and Figure 3 The embodiment of the device shown in the figure, the embodiment of the present invention also provides a physical structure diagram of a computer device, such as Figure 4As shown, the computer device includes: a processor 41, a memory 42, and a computer program stored in the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are both arranged on a bus 43, and when the processor 41 executes the program, the following steps are implemented: in response to verification rule generation signals of different insurance items, the project attribute information, verification requirement information, project source information, and user characteristic information of the insured users of each insurance item are obtained; based on the project attribute information, the verification requirement information, the project source information, and the user characteristic information, the requirement verification rule of each insurance item is determined; the rule attribute information of each requirement verification rule is determined, and based on the rule attribute information, each requirement verification rule is classified to obtain the target rule category to which each requirement verification rule belongs; the rule generation method corresponding to each target rule category is determined respectively, and the verification rule of the corresponding insurance item is generated by using the rule generation method.

[0107] Through the technical solution of the present invention, the present invention specifies the demand verification rules for each insurance project by comprehensively analyzing the project attribute information, verification requirement information, project source information, and user characteristic information of the insured users of each insurance project, which can improve the accuracy of the formulation of the demand verification rules. Then, according to the attribute information of the demand verification rules, the rule category to which each insurance project belongs is determined. Since different rule generation methods are pre-established for different rule categories, a rule generation method suitable for the insurance project is selected according to the rule category of the insurance project, and finally the verification rules for the corresponding insurance project are generated using the rule generation method. Therefore, the present invention selects the applicable rule generation method for the insurance project according to the rule category, which can avoid the waste of generation time and code writing resources when all rules are generated in a unified source code writing method, and can also avoid source code writing errors. Therefore, the present invention can improve the generation efficiency and generation accuracy of insurance verification rules.

[0108] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0109] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A verification rule generation method, characterized in that: include: In response to verification rule generation signals of different insurance items, obtaining item attribute information, verification requirement information, item source information, and user characteristic information of insured users covered by each insurance item; Determine the requirement verification rules for each of the insurance items based on the item attribute information, the verification requirement information, the item source information, and the user characteristic information; Determine the rule attribute information of each of the demand verification rules, and classify each of the demand verification rules based on the rule attribute information to obtain the target rule category to which each of the demand verification rules belongs; The rule generation methods corresponding to the target rule categories are determined respectively, and the verification rules of the corresponding insurance items are generated by using the rule generation methods.

2. The method according to claim 1, characterized in that: The rule attribute information includes: the number of verification conditions of each verification condition in the verification rule, and the association relationship between each of the verification conditions; The classifying each of the demand verification rules based on the rule attribute information to obtain the target rule category to which each of the demand verification rules belongs includes: Based on the number of verification conditions corresponding to each of the verification conditions and the association relationship, determine the verification logic complexity corresponding to each of the demand verification rules, and judge whether the verification logic complexity is less than a preset threshold; If the verification logic complexity is less than the preset threshold, the demand verification rule is classified as a simple verification rule to be generated; if the verification logic complexity is greater than or equal to the preset threshold, the demand verification rule is classified as a complex verification rule to be generated.

3. The method according to claim 2, characterized in that The determining, based on the number of verification conditions corresponding to each of the verification conditions and the association relationship, the verification logic complexity corresponding to each of the requirement verification rules includes: Determine whether there is a correlation relationship between the verification conditions; If the association relationship does not exist, the verification logic complexity corresponding to each of the requirement verification rules is set based on the number of verification conditions. If the association relationship exists, the relationship type to which the association relationship belongs is determined, and the verification logic complexity corresponding to each of the requirement verification rules is set based on the relationship type and the number of verification conditions.

4. The method according to claim 2, characterized in that: The respectively determining the rule generation methods corresponding to the target rule categories and using the rule generation methods to generate verification rules for corresponding insurance items include: Determine a script generation method corresponding to the simple verification rule to be generated, and generate the simple verification rule using the script generation method; A hard-coded generation method corresponding to the complex verification rule to be generated is determined, and the complex verification rule is generated using the hard-coded generation method.

5. The method according to claim 4, characterized in that The method of generating a simple verification rule by using the script generation method includes: Determine the rule type corresponding to the simple verification rule to be generated, and determine the rule script template corresponding to the rule type, wherein the rule script template includes the general rule code and configurable parameter items under the rule type; Determine the verification parameters in the simple verification rule to be generated, and fill the verification parameters into the preset positions corresponding to the configurable parameter items in the rule script template to obtain the simple verification rule; After generating the simple verification rules by using the script generation method, the method further includes: The simple verification rule is sent to the verification terminal for rule verification. If the verification passes, it is determined that the generation accuracy of the simple verification rule meets the generation requirement. If the verification fails, the simple verification rule is regenerated.

6. The method according to claim 1, characterized in that After generating the verification rules for the corresponding insurance items by using the rule generation method, the method further includes: Based on the correspondence between each of the insurance items and the corresponding verification rules, a verification rule list is constructed; In response to the verification signal of the target insurance item, the insurance verification rule corresponding to the target insurance item is determined based on the verification rule list, and the target insurance item is subjected to rule verification using the insurance verification rule.

7. The method according to claim 1, characterized in that The step of determining the requirement verification rules for each insurance item based on the item attribute information, the verification requirement information, the item source information, and the user characteristic information includes: Determine an attribute feature vector corresponding to the project attribute information, a requirement feature vector corresponding to the verification requirement information, a source feature vector corresponding to the project source information, and a user feature vector corresponding to the user feature information; Cross-processing the attribute feature vector, the demand feature vector, the source feature vector, and the user feature vector to obtain a verification rule cross-vector; The verification rule cross vector is input into a preset verification rule prediction model to perform rule prediction to obtain the demand verification rule.

8. A verification rule generating device, characterized in that: include: An acquisition unit, configured to generate signals in response to verification rules of different insurance items, and acquire item attribute information, verification requirement information, item source information, and user characteristic information of insured users covered by each insurance item of each insurance item; A determination unit, configured to determine a requirement verification rule for each of the insurance items based on the item attribute information, the verification requirement information, the item source information, and the user characteristic information; A classification unit, used to determine the rule attribute information of each of the demand verification rules, and classify each of the demand verification rules based on the rule attribute information to obtain the target rule category to which each of the demand verification rules belongs; The generating unit is used to respectively determine the rule generating methods corresponding to each of the target rule categories, and generate the verification rules of the corresponding insurance items by using the rule generating methods.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images