A Business Activity Information Standardization Method Based on the BOR Method

Abstract

The present invention discloses a method for standardizing business activity information based on the BOR method, which relates to the field of information technology. It mainly aims to standardize business object information, achieve the standardization processing and high-quality conversion from business activities, business information to data elements, thereby facilitating the management and application of business data and serving as the basis for improving the level of business informatization and achieving high-quality development. The method includes: obtaining the business activity information to be processed; determining the attribute information corresponding to the business object in the business activity information; inputting the attribute information into a preset data entity classification model for entity classification to obtain the data entity corresponding to the attribute information; inputting the data entity into a preset subject domain classification model for subject domain classification to obtain the subject domain corresponding to the data entity; and then determining the standardized processing result corresponding to the business activity information. The present invention is applicable to the processing of business information.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a method for standardizing business activity information based on the BOR method. Background Art

[0002] With the continuous improvement of user requirements, various business activities for users to participate in have emerged as the times require. A large amount of business activity information will be generated during the process of users participating in business activities. Effectively standardizing this business activity information and realizing high-quality conversion from business activities, business information to data elements is not only beneficial to the management and storage of business data, but also can effectively improve the level of business informatization, which is the basis for the digital transformation and high-quality development of enterprises. At present, there is no unified way to process business activity information, so it is impossible to standardize the definition of business data of business activities, which is not conducive to the effective management and application of business data. Summary of the Invention

[0003] The present invention provides a method for standardizing business activity information based on the BOR method, mainly capable of standardizing the processing of business object information, thereby realizing high-quality conversion from business activities, business information to data elements, which is beneficial to the management and application of business data.

[0004] According to the first aspect of the present invention, there is provided a method for standardizing business activity information based on the BOR method, including:

[0005] Obtaining the business activity information to be processed;

[0006] Determining the attribute information corresponding to the business object in the business activity information;

[0007] Inputting the attribute information into a preset data entity classification model for entity classification to obtain the data entity corresponding to the attribute information;

[0008] Inputting the data entity into a preset subject domain classification model for subject domain classification to obtain the subject domain corresponding to the data entity;

[0009] Determining the standardized processing result corresponding to the business activity information according to the data entity and the subject domain.

[0010] According to the second aspect of the present invention, there is provided a device for standardizing business activity information based on the BOR method, including:

[0011] An obtaining unit, configured to obtain the business activity information to be processed;

[0012] A first determining unit, configured to determine the attribute information corresponding to the business object in the business activity information;

[0013] The first classification unit is configured to input the attribute information into a preset data entity classification model for entity classification, so as to obtain the data entity corresponding to the attribute information;

[0014] The second classification unit is configured to input the data entity into a preset subject domain classification model for subject domain classification, so as to obtain the subject domain corresponding to the data entity;

[0015] The second determination unit is configured to determine the standardized processing result corresponding to the service activity information according to the data entity and the subject domain.

[0016] According to the third aspect of the present invention, there is provided 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:

[0017] Obtain the service activity information to be processed;

[0018] Determine the attribute information corresponding to the business object in the service activity information;

[0019] Input the attribute information into a preset data entity classification model for entity classification, so as to obtain the data entity corresponding to the attribute information;

[0020] Input the data entity into a preset subject domain classification model for subject domain classification, so as to obtain the subject domain corresponding to the data entity;

[0021] Determine the standardized processing result corresponding to the service activity information according to the data entity and the subject domain.

[0022] According to the fourth aspect of the present invention, there is provided a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the following steps are implemented:

[0023] Obtain the service activity information to be processed;

[0024] Determine the attribute information corresponding to the business object in the service activity information;

[0025] Input the attribute information into a preset data entity classification model for entity classification, so as to obtain the data entity corresponding to the attribute information;

[0026] Input the data entity into a preset subject domain classification model for subject domain classification, so as to obtain the subject domain corresponding to the data entity;

[0027] Determine the standardized processing result corresponding to the service activity information according to the data entity and the subject domain.

[0028] A method for standardizing business activity information based on the BOR method provided by the present invention can, compared with the current situation where it is impossible to standardize the business data of business activities, obtain the business activity information to be processed; determine the attribute information corresponding to the business objects in the business activity information; at the same time, input the attribute information into a preset data entity classification model for entity classification to obtain the data entity corresponding to the attribute information; input the data entity into a preset subject domain classification model for subject domain classification to obtain the subject domain corresponding to the data entity; and finally, determine the standardized processing result corresponding to the business activity information according to the data entity and the subject domain. Thus, by extracting the attribute information corresponding to the business objects in the business activity information, clustering the attribute information into data entities, and clustering the obtained data entities into subject domains, the standardization processing of business activity information can be realized, and then the business data of business activities can be defined in a unified manner, so as to achieve high-quality conversion from business activities, business information to data elements, which is beneficial to the management and application of business data. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The schematic 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:

[0030] Figure 1 shows a flowchart of a method for standardizing business activity information based on the BOR method provided by an embodiment of the present invention;

[0031] Figure 2 shows a flowchart of another method for standardizing business activity information based on the BOR method provided by an embodiment of the present invention;

[0032] Figure 3 shows a schematic structural diagram of a device for standardizing business activity information based on the BOR method provided by an embodiment of the present invention;

[0033] Figure 4 shows a schematic structural diagram of another device for standardizing business activity information based on the BOR method provided by an embodiment of the present invention;

[0034] Figure 5 shows a schematic structural diagram of an entity of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] The present invention will be described in detail below with reference to the drawings and in conjunction with the embodiments. It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other.

[0036] Currently, there is no unified way to process business activity information, so it is impossible to standardize the definition of business data of business activities, which is not conducive to the effective management and application of business data.

[0037] To solve the above problems, an embodiment of the present invention provides a method for standardizing business activity information based on the BOR method, as Figure 1 shown, the method includes:

[0038] 101. Obtain the business activity information to be processed.

[0039] Among them, business activity information refers to the business information generated by users during the process of participating in business activities. For example, in the underwriting link of the insurance field, the business activities participated by users include insurance application, underwriting, policy issuance, and charging. When users apply for insurance, they will generate insurance application form information, applicant information, and insurance type information. To overcome the defect in the prior art that it is impossible to standardize the definition of business activity information and is not conducive to the management and application of business data, an embodiment of the present invention extracts the attribute information corresponding to the business object from the business activity information, performs data entity clustering on the attribute information, and performs subject domain clustering on the obtained data entities, so as to be able to realize the standardized definition of business activity information, realize the high-quality conversion from business activities, business information to data elements, and further realize the effective management and efficient application of business data. The embodiment of the present invention is mainly applicable to standardizing the definition of business activity information. The execution subject of the embodiment of the present invention is a device or equipment capable of standardizing the processing of business activity information, which can be specifically set on the client side or the server side.

[0040] For the embodiment of the present invention, during the process of users participating in business activities, corresponding business activity information will be generated. For example, when users apply for insurance, they will generate insurance application form information, applicant information, and insurance type information. The insurance application form information specifically includes the insurance application form number, insurance company, etc. The applicant information specifically includes name, gender, ID number, bank account number, etc. The insurance type information specifically includes the insurance type name, insurance type, premium, and insured amount. The above information is the business activity information generated by users during the insurance application process. To facilitate the management and application of business activity information, it is necessary to standardize the definition of business activity information, so as to realize the high-quality conversion from business activities, business information to data elements.

[0041] 102. Determine the attribute information corresponding to the business object in the business activity information.

[0042] Among them, the business activity information includes at least one business object, and each business object includes at least one attribute information. For example, in the insurance field, the business activity information includes business objects such as insurance application forms, policyholders, and insurance types participating in the activity. For each business object, it can be described by several attribute information. For example, a policyholder can be described by attribute information such as name, gender, and ID number.

[0043] For the embodiments of the present invention, in the process of standardizing business activity information, it is necessary to first split the business activity information into attribute information corresponding to multiple business objects, and then perform data entity clustering and subject domain clustering processing on the attribute information, so as to realize the standardized definition of business data. Specifically, in the process of splitting the business activity information into attribute information corresponding to multiple business objects, a preset entity recognition algorithm can be used to recognize the business objects in the business activity information. For example, business objects such as insurance application forms, policyholders, and insurance types in the insurance business activity information can be recognized. Further, the attribute information corresponding to the above business objects is extracted from the business activity information respectively, so as to be able to split the business activity information into attribute information corresponding to multiple business objects, that is, to realize the data processing process from general to specific in the process of standardizing business data definition.

[0044] 103. Input the attribute information into a preset data entity classification model for entity classification to obtain the data entity corresponding to the attribute information.

[0045] Among them, the preset data entity classification model can specifically be a classification model in machine learning. For the embodiments of the present invention, after splitting the business activity information into attribute information corresponding to business objects, in order to avoid the business data being composed of a large number of disordered attribute information during the standardization process, it is necessary to perform clustering processing on the attribute information. Specifically, the attribute information can be input into a preset data entity classification model for entity classification to obtain the data entity to which the attribute information belongs, and then the attribute information belonging to the same data entity is clustered to obtain the attribute information under different data entities. For example, it is determined that the attribute information corresponding to the business object includes insurance application number, insurance company name, policyholder name, policyholder gender, insurance type name, and insurance type. Inputting the above attribute information into the preset data entity classification model for classification can determine that the data entity corresponding to the insurance application number and the insurance company name is the insurance application form, the data entity corresponding to the policyholder name and the policyholder gender is the policyholder, and the data entity corresponding to the insurance type name and the insurance type is the insurance type. Further, the attribute information belonging to the same data entity is clustered to obtain the attribute information under different data entities, so as to realize the clustering combination of attribute information with similar business logic relationships, obtain the data entity corresponding to the attribute information, and realize the data processing process from specific to general in the process of standardizing business data definition.

[0046] 104. Input the data entity into a preset subject domain classification model for subject domain classification to obtain the subject domain corresponding to the data entity.

[0047] Among them, the preset subject domain classification model can specifically be a classification model in machine learning. For the embodiments of the present invention, after clustering the data entities of the split attribute information, in order to further generalize the data entities, it is necessary to perform clustering processing on the data entities, and finally form data entities under different subject domains. Specifically, the data entity can be input into the preset subject domain classification model for subject domain classification to obtain the subject domain to which the data entity belongs, and then the data entities belonging to the same subject domain are clustered, that is, the data entities belonging to the same subject domain are divided into the same category, so as to obtain data entities under different subject domains. For example, the data entities after clustering include the basic information of the applicant, the address information of the applicant, the basic information of the insured, the address information of the insured, the claim information, the case-filing information, and the claim settlement information, etc. Inputting the above data entities into the preset subject domain classification model for classification respectively can determine that the basic information of the applicant, the address information of the applicant, the basic information of the insured, and the address information of the insured are shared information of the customer in different roles in different business links, and have identity, and can be refined to form the customer subject domain; while the claim information, the case-filing information, and the claim settlement information have a close coupling relationship in business activities, and they can be combined to form the claim settlement subject domain, thereby realizing the clustering processing of the data entities and obtaining the subject domain corresponding to the data entity.

[0048] 105. Determine the standardized processing result corresponding to the business activity information according to the data entity and the subject domain.

[0049] For the embodiments of the present invention, by splitting the business activity information into the attribute information of the business object and performing data entity clustering and subject domain clustering on the attribute information, it is possible to determine the attribute information under different data entities and the data entities under different subject domains, thereby completing the standardized definition of the business activity information and realizing the high-quality conversion from business activities, business information to data elements, which is convenient for subsequent effective management and application of business data.

[0050] A method for standardizing business activity information based on the BOR method provided by an embodiment of the present invention can, compared with the current situation where it is impossible to standardize the definition of business activity information, obtain the business activity information to be processed; determine the attribute information corresponding to the business object in the business activity information; at the same time, input the attribute information into a preset data entity classification model for entity classification to obtain the data entity corresponding to the attribute information; input the data entity into a preset subject domain classification model for subject domain classification to obtain the subject domain corresponding to the data entity; and finally, determine the standardized processing result corresponding to the business activity information according to the data entity and the subject domain. Thus, by extracting the attribute information corresponding to the business object in the business activity information, clustering the attribute information for data entities, and clustering the obtained data entities for subject domains, the standardized processing of business activity information can be realized, and then the business activity information can be defined in a unified manner, achieving high-quality conversion from business activities, business information to data elements, which is conducive to the effective management and efficient application of business data.

[0051] Further, in order to better illustrate the above-mentioned standardized processing process of business activity information, as a refinement and extension of the above embodiment, an embodiment of the present invention provides another method for standardizing business activity information based on the BOR method, as Figure 2 shown, the method includes:

[0052] 201. Obtain the business activity information to be processed.

[0053] For the embodiment of the present invention, business activities can be split into different levels. For example, first-level insurance business activities such as sales, underwriting, policy maintenance, claims settlement, and services. For the underwriting link, it can be further split into second-level and even third-level business activities such as application, underwriting review, policy issuance, and premium collection. The obtained business activity information is also the business information generated by users participating in different-level business activities. It should be noted that the business activity information in the embodiment of the present invention can specifically be the insurance business activity information generated by users during the participation in insurance business activities, or the business activity information generated by users during the participation in business activities in other fields. The embodiment of the present invention does not make specific limitations on this.

[0054] 202. Use a preset entity recognition algorithm to recognize the business objects in the business activity information.

[0055] For the embodiments of the present invention, in order to standardize the definition of business activity information, it is necessary to first identify the business object entities included in the business object information. For the specific process of identifying business objects, as an alternative embodiment, step 202 specifically includes: performing word segmentation on the business activity information to obtain each word segment corresponding to the business activity information; inputting each word segment corresponding to the business activity information into a preset entity recognition model for entity recognition to determine the business objects included in the business activity information.

[0056] Specifically, first use a preset natural language model to perform word segmentation on the business activity information to obtain each word segment corresponding to the business activity information. The preset natural language model can specifically be a BERT natural language model. Then input each word segment corresponding to the business activity information into a preset entity recognition model for entity recognition to determine the business object entities included in the business activity information. Among them, the preset entity recognition model can specifically be an LSTM network; there is at least one business object in the business activity information. Specifically, inputting each word segment corresponding to the business activity information into the LSTM network can obtain the probability values of each word segment belonging to different entity categories, and then determine the entity category corresponding to each word segment according to the probability values, and screen out the target business object entities from them. For example: screen out business objects participating in insurance activities such as insurance application forms, insured persons, and insurance types from insurance business object information. Thus, business objects can be identified from the business activity information in the above manner to further determine the attribute information corresponding to the business objects. It should be noted that in a specific application scenario, the preset natural language model can be set on the client side, and the LSTM can be set on the server side, so as to reduce the amount of data queried.

[0057] 203. Use a preset business object attribute word library to extract the attribute information in the business activity information to obtain the attribute information corresponding to the business object.

[0058] Among them, the preset business object attribute word library records the attribute words of different business objects. For example, the words corresponding to the insurance application form, such as insurance application number and insurance company name, are recorded in the preset business object attribute word library. For the embodiments of the present invention, after performing word segmentation on the business activity information, determine the business objects included in the business object information, and then query the preset business object attribute word library according to the business objects to determine the attribute fields corresponding to the business objects. Further, query the business activity information according to the attribute fields. When the attribute fields exist in the business activity information, extract the attribute information corresponding to the attribute fields, so as to be able to split the business activity information into the attribute information corresponding to the business objects, realizing the data processing process from general to specific in the process of standardizing the definition of business data.

[0059] 204. Input the attribute information into a preset data entity classification model for entity classification to obtain the data entity corresponding to the attribute information.

[0060] Among them, the preset data entity classification model is a preset decision tree data entity classification model. For the embodiments of the present invention, in order to determine the data entity category to which the attribute information of the business object belongs, step 204 specifically includes: inputting the attribute information into the preset decision tree data entity classification model to obtain the first probability values of the attribute information belonging to different data entities; screening the first maximum probability value among the first probability values, and determining the data entity corresponding to the first maximum probability value as the data entity corresponding to the attribute information.

[0061] For example, input the attribute information of the insured company name into the preset decision tree entity classification model for entity classification. The probability values of the insured company name belonging to the insurance policy, the insured, and the insurance type are 0.5, 0.3, and 0.2 respectively. Thus, it can be determined that the attribute information of the insured company name belongs to the insurance policy data entity. After determining the data entity to which the attribute information belongs, cluster the attribute information belonging to the same data entity to obtain the attribute information under different data entities, so as to be able to combine the attribute information with similar business logic relationships and realize the data processing process from part to whole in the process of standardizing the definition of business data.

[0062] It should be noted that in the process of constructing the preset decision tree data entity classification model, collect historical business data, label it according to the data entity category to which the business data belongs, use the labeled business data as the training set, and train the training set to construct the preset decision tree entity classification model.

[0063] 205. Input the data entity into a preset subject domain classification model for subject domain classification to obtain the subject domain corresponding to the data entity.

[0064] Among them, the preset subject domain classification model is a preset random forest subject domain classification model. For the embodiments of the present invention, in order to determine the subject domain to which the data entity belongs, step 205 specifically includes: inputting the data entity into the preset random forest subject domain classification model for subject domain classification to obtain the second probability values of the data entity belonging to different subject domains; screening the second maximum probability value among the second probability values, and determining the subject domain corresponding to the second maximum probability value as the subject domain corresponding to the data entity.

[0065] For example, input the basic information of the insurance policy data entity into a preset random forest topic domain classification model for topic domain classification. The probability values that the basic information of the insurance policy belongs to the customer, policy, and claim topic domains are 0.3, 0.5, and 0.2 respectively. From this, it can be determined that the basic information of the insurance policy data entity belongs to the policy topic domain. After determining the topic domain to which the data entity belongs, cluster the data entities belonging to the same topic domain to obtain data entities under different topic domains, so as to further summarize the data entities.

[0066] It should be noted that in the process of constructing the preset random forest topic domain classification model, collect historical business data, determine the historical business data under different data entities, and then label the data entities according to the topic domains corresponding to different data entities. Use the labeled data entities as the training set, and based on this training set, construct the preset random forest topic domain classification model.

[0067] 206. Determine the standardized processing result corresponding to the business activity information according to the data entity and the topic domain.

[0068] For the embodiments of the present invention, in order to collect data according to the defined data standard, after step 206, the method further includes: adjusting the data entity range and the topic domain range respectively according to the data collection scenario; collecting business data based on the adjusted data entity range and topic domain range. Specifically, after defining the data, based on the defined data, the range of attribute information under the data entity and the range of data entities under the topic domain can be adjusted according to the specific scenario, and data collection is performed based on the adjusted range.

[0069] In a specific application scenario, in order to make the collected data meet the corresponding requirements, it is necessary to perform a verification process on the business data using a preset verification rule. Based on this, before collecting the business data based on the adjusted data entity range and topic domain range, the method further includes: determining whether the file identifier corresponding to the business data meets a preset file identifier rule; if it meets the preset file identifier rule, then determining whether the business data meets a preset data verification rule; if it meets the preset data verification rule, then collect the business data based on the adjusted data entity range and topic domain range. Among them, the text identifier can specifically be the file name, or it can also be the hash value or md5 value of the file. The naming rule of the file carrying the business data can be used to determine whether the file name meets the corresponding requirements. If it meets, the business data in the file is further detected using a preset data detection rule. If the detection passes, the business data is collected, and at the same time, the data passing the data detection rule can also be uploaded to the server for query in the server.

[0070] Further, after the relevant business department completes the collection of business data, in order to further ensure that there are no quality problems with the collected business data, it is necessary to perform quality detection on the collected business data. Specifically, corresponding data detection rules can be set according to the data usage requirements, business types, and data standards, and the data detection rules are used to perform quality detection on the collected business data. If the business data meets the preset data detection rules, it indicates that the quality of the business data is problem-free; if the business data does not meet the preset data detection rules, it indicates that the quality of the business data has problems. Based on this, the method includes: performing quality detection on the collected business data using the preset data detection rules; if there are quality problems with the business data, then generating a quality problem report corresponding to the business data based on the type of quality problem corresponding to the business data, and sending the quality problem report to the relevant business personnel terminal so as to correct the business data based on the quality problem report; receiving the corrected business data, and re-performing quality detection on the corrected business data using the preset data detection rules.

[0071] Among them, multiple data detection rules can be set according to the usage requirements, business types, and data standards to comprehensively detect the quality of the collected business data. For example, the data format detection rule is used to detect the format of the collected business data, the sensitive information detection rule is used to detect the sensitivity of the collected business data to prevent the collected business data from containing user privacy and causing the leakage of user privacy, or the data logic detection rule is used to detect the logic of the collected business data to determine whether there are logical errors in the collected business data. For example, the logic detection rule is used to detect whether there is a conflict between the user's age and the insurance application time, which is illogical. After setting the data detection rules, according to the business requirements, select the corresponding script writing tool, such as selecting the notepad++ tool to write the corresponding quality detection script. When receiving the quality detection instruction of the business data, call the corresponding quality detection script to perform data quality detection. If the collected business data does not meet the preset data detection rules, according to the preset data detection rules that the business data fails to pass, determine the type of problem existing in the business data, and then adopt the report template corresponding to the problem type to generate the quality problem report corresponding to the business data, and send the quality problem report to the business personnel. The business personnel analyze the problem causes according to the quality problem report and set the corresponding rectification plan. Based on the rectification plan, the collected business data is corrected, or the rectification plan is re-formulated to collect the business data. Further, the corrected business data is re-sent to the data detection platform, and the data detection platform uses the preset data detection rules to re-detect the corrected business data, repeating the above process until the detected business data meets the preset data detection rules. In this way, a closed-loop management method of rule formulation, problem discovery, cause analysis, and follow-up rectification can be formed according to the above method, so as to continuously optimize the data quality.

[0072] Another method for standardizing business activity information based on the BOR method provided by the embodiments of the present invention can, compared with the current situation where it is impossible to standardize the definition of business activity information, obtain the business activity information to be processed; determine the attribute information corresponding to the business objects in the business activity information; at the same time, input the attribute information into a preset data entity classification model for entity classification to obtain the data entity corresponding to the attribute information; and input the data entity into a preset subject domain classification model for subject domain classification to obtain the subject domain corresponding to the data entity; finally, determine the standardized processing result corresponding to the business activity information according to the data entity and the subject domain. Thus, by extracting the attribute information corresponding to the business objects in the business activity information, clustering the attribute information into data entities, and clustering the obtained data entities into subject domains, the standardization processing of business activity information can be realized, and the high-quality conversion from business activities, business information to data elements can be achieved, which is beneficial to the management and application of business data. Further, by using a preset entity recognition algorithm to extract the attribute information corresponding to the business objects in the business activity information, the extraction efficiency of the attribute information is improved, and the labor cost is reduced. In addition, through the preset subject domain classification model and the preset data entity classification model, the automatic classification of business data is realized, avoiding the problem of inaccurate classification results caused by excessive manual intervention.

[0073] Further, as Figure 1 a specific implementation of Figure 3 it, the embodiments of the present invention provide a device for standardizing business activity information based on the BOR method. As shown in

[0074] Figure [not provided], the device includes: an acquisition unit 31, a first determination unit 32, a first classification unit 33, a second classification unit 34, and a second determination unit 35.

[0075] The acquisition unit 31 can be used to acquire the business activity information to be processed.

[0076] The first determination unit 32 can be used to determine the attribute information corresponding to the business objects in the business activity information.

[0077] The first classification unit 33 can be used to input the attribute information into a preset data entity classification model for entity classification to obtain the data entity corresponding to the attribute information.

[0078] The second classification unit 34 can be used to input the data entity into a preset subject domain classification model for subject domain classification to obtain the subject domain corresponding to the data entity.

[0079] For the embodiments of the present invention, as Figure 4 shown, in order to split the business activity information into the attribute information corresponding to the business object, the first determination unit 32 includes: an identification module 321 and an extraction module 322.

[0080] The identification module 321 can be used to identify the business object in the business activity information by using a preset entity recognition algorithm.

[0081] The extraction module 322 can be used to extract the attribute information in the business activity information by using a preset business object attribute thesaurus, and obtain the attribute information corresponding to the business object.

[0082] Further, in order to identify the business object in the business activity information, the identification module 321 includes: a word segmentation sub-module and an identification sub-module.

[0083] The word segmentation sub-module can be used to perform word segmentation processing on the business activity information to obtain each word segment corresponding to the business activity information.

[0084] The identification sub-module can be used to input each word segment corresponding to the business activity information into a preset entity recognition model for entity recognition, and determine the business object included in the business activity information.

[0085] Further, the preset data entity classification model is a preset decision tree data entity classification model, and the first classification unit 33 includes: an entity classification module 331 and a determination module 332.

[0086] The entity classification module 331 can be used to input the attribute information into the preset decision tree data entity classification model for entity classification, and obtain the first probability value of the attribute information belonging to different data entities.

[0087] The determination module 332 can be used to screen the first maximum probability value in the first probability values, and determine the data entity corresponding to the first maximum probability value as the data entity corresponding to the attribute information.

[0088] Further, the preset theme domain classification model is a preset random forest theme domain classification model, and the second classification unit 34 includes: a theme domain classification module 341 and a determination module 342.

[0089] The theme domain classification module 341 can be used to input the data entity into the preset random forest theme domain classification model for theme domain classification, and obtain the second probability value of the data entity belonging to different theme domains.

[0090] The determining module 342 can be used to screen the second maximum probability value in the second probability values, and determine the subject domain corresponding to the second maximum probability value as the subject domain corresponding to the data entity.

[0091] Further, in order to collect business data, the apparatus further includes an adjustment unit 36 and a collection unit 37.

[0092] The adjustment unit 36 can be used to adjust the data entity range and the subject domain range respectively according to the data collection scenario.

[0093] The collection unit 37 can be used to collect business data based on the adjusted data entity range and subject domain range.

[0094] Further, the apparatus further includes a judgment unit 38. The judgment unit 38 can be used to judge whether the file identifier corresponding to the business data meets a preset file identifier rule.

[0095] The judgment unit 38 can also be used to judge whether the business data meets a preset data verification rule if the preset file identifier rule is met.

[0096] The collection unit 37 can specifically be used to collect business data based on the adjusted data entity range and subject domain range if the preset data verification rule is met.

[0097] It should be noted that for other corresponding descriptions of each functional module involved in the business activity information standardization apparatus based on the BOR method provided in the embodiments of the present invention, reference can be made to Figure 1 the corresponding description of the method shown, which will not be elaborated here.

[0098] Based on the above method as Figure 1 shown, correspondingly, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the following steps are implemented: obtaining business activity information to be processed; determining attribute information corresponding to a business object in the business activity information; inputting the attribute information into a preset data entity classification model for entity classification to obtain a data entity corresponding to the attribute information; inputting the data entity into a preset subject domain classification model for subject domain classification to obtain a subject domain corresponding to the data entity; determining a standardized processing result corresponding to the business activity information according to the data entity and the subject domain.

[0099] Based on the above method as Figure 1 shown and the embodiments of the apparatus as Figure 3 shown, the embodiments of the present invention further provide an entity structure diagram of a computer device, as Figure 5As shown in the figure, the computer device includes: a processor 41, a memory 42, and a computer program stored in the memory 42 and executable on the processor. Both the memory 42 and the processor 41 are provided on a bus 43. When the processor 41 executes the program, the following steps are implemented: obtaining business activity information to be processed; determining attribute information corresponding to a business object in the business activity information; inputting the attribute information into a preset data entity classification model for entity classification to obtain a data entity corresponding to the attribute information; inputting the data entity into a preset subject domain classification model for subject domain classification to obtain a subject domain corresponding to the data entity; and determining a standardized processing result corresponding to the business activity information according to the data entity and the subject domain.

[0100] Through the technical solution of the present invention, the present invention can obtain business activity information to be processed; and determine attribute information corresponding to a business object in the business activity information; meanwhile, input the attribute information into a preset data entity classification model for entity classification to obtain a data entity corresponding to the attribute information; and input the data entity into a preset subject domain classification model for subject domain classification to obtain a subject domain corresponding to the data entity; finally, determine a standardized processing result corresponding to the business activity information according to the data entity and the subject domain. Thus, by extracting attribute information corresponding to a business object in the business activity information, clustering the attribute information into data entities, and clustering the obtained data entities into subject domains, the standardized processing of business activity information can be realized, and the high-quality conversion from business activities, business information to data elements can be achieved, which is beneficial to the management and application of business data.

[0101] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented using a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented with program codes executable by the 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 separately made into individual integrated circuit modules, or multiple modules or steps among them can be made into a single integrated circuit module to be implemented. In this way, the present invention is not limited to any specific combination of hardware and software.

[0102] The above is only the preferred embodiment of the present invention and is not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for standardizing business activity information based on the BOR method, characterized in that, Including: Obtain the business activity information to be processed; Determine the attribute information corresponding to the business object in the business activity information; Input the attribute information into a preset data entity classification model for entity classification to obtain the data entity corresponding to the attribute information, where the attribute information includes the insurance policy number, insurance company name, applicant's name, applicant's gender, insurance type name, and insurance type; Input the data entity into a preset subject domain classification model for subject domain classification to obtain the subject domain corresponding to the data entity, where the data entity includes the applicant's basic information, applicant's address information, insured's basic information, insured's address information, claim information, case registration information, and claim settlement information; Determine the standardized processing result corresponding to the business activity information according to the data entity and the subject domain; Among them, the determining the attribute information corresponding to the business object in the business activity information includes: Use a preset entity recognition algorithm to recognize the business object in the business activity information; Use a preset business object attribute word library to extract the attribute information in the business activity information to obtain the attribute information corresponding to the business object; The using a preset entity recognition algorithm to recognize the business object in the business activity information includes: Perform word segmentation processing on the business activity information to obtain each word segment corresponding to the business activity information; Input each word segment corresponding to the business activity information into a preset entity recognition model for entity recognition to determine the business object included in the business activity information; After determining the standardized processing result corresponding to the business activity information according to the data entity and the subject domain, the method further includes: Adjust the data entity range and subject domain range respectively according to the data collection scenario; Collect business data based on the adjusted data entity range and subject domain range; Use data format detection rules, sensitive information detection rules, and data logic detection rules to detect the collected business data respectively; If the business data does not meet the data format detection rules, or the sensitive information detection rules, or the data logic detection rules, then according to the type of problem existing in the business data, use a report template corresponding to the problem type to generate a quality problem report corresponding to the business data, and send the quality problem report to the business personnel; Before collecting business data based on the adjusted data entity range and subject domain range, the method further includes: Judge whether the file identifier corresponding to the business data meets the preset file identifier rules; If it meets the preset file identifier rules, then judge whether the business data meets the preset data verification rules; If it meets the preset data verification rules, then collect business data based on the adjusted data entity range and subject domain range.

2. The method according to claim 1, wherein The preset data entity classification model is a preset decision tree data entity classification model, and the inputting the attribute information into the preset data entity classification model for entity classification to obtain the data entity corresponding to the attribute information includes: Input the attribute information into a preset decision tree data entity classification model for entity classification to obtain first probability values of the attribute information belonging to different data entities; Screen the first maximum probability value among the first probability values, and determine the data entity corresponding to the first maximum probability value as the data entity corresponding to the attribute information.

3. The method according to claim 1, wherein The preset subject domain classification model is a preset random forest subject domain classification model. The step of inputting the data entity into the preset subject domain classification model for subject domain classification to obtain the subject domain corresponding to the data entity includes: Input the data entity into the preset random forest subject domain classification model for subject domain classification to obtain second probability values of the data entity belonging to different subject domains; Screen the second maximum probability value among the second probability values, and determine the subject domain corresponding to the second maximum probability value as the subject domain corresponding to the data entity.

4. The method according to claim 1, characterized in that, After collecting the business data based on the adjusted data entity range and subject domain range, the method further includes: Use a preset data detection rule to perform quality detection on the collected business data; If there are quality problems with the business data, generate a quality problem report corresponding to the business data based on the type of quality problem corresponding to the business data, and send the quality problem report to relevant business personnel so as to correct the business data based on the quality problem report; Receive the corrected business data, and re-use the preset data detection rule to perform quality detection on the corrected business data; Among them, the step of using the preset data detection rule to perform quality detection on the collected business data includes: Select a corresponding script writing tool according to business requirements; Use the script writing tool to write a detection script corresponding to the preset data detection rule; In response to the quality detection instruction of the business data, call the detection script to perform quality detection on the business data.

5. A business activity information standardization device based on the BOR method, characterized in that It includes: An acquisition unit, configured to acquire business activity information to be processed; A first determination unit, configured to determine the attribute information corresponding to the business object in the business activity information; A first classification unit, configured to input the attribute information into a preset data entity classification model for entity classification to obtain the data entity corresponding to the attribute information, where the attribute information includes an insurance policy number, an insurance company name, an applicant's name, an applicant's gender, a type of insurance and an insurance type; A second classification unit, configured to input the data entity into a preset subject domain classification model for subject domain classification to obtain the subject domain corresponding to the data entity, where the data entity includes basic applicant information, applicant address information, basic insured information, insured address information, claim information, case-filing information and claim settlement information; A second determination unit, configured to determine the standardized processing result corresponding to the business activity information according to the data entity and the subject domain; Among them, the first determination unit includes an identification module and an extraction module; The identification module is configured to identify the business object in the business activity information by using a preset entity identification algorithm; The extraction module is configured to extract the attribute information in the business activity information by using a preset business object attribute thesaurus, so as to obtain the attribute information corresponding to the business object; The recognition module is specifically configured to perform word segmentation processing on the business activity information to obtain each word segment corresponding to the business activity information; input each word segment corresponding to the business activity information into a preset entity recognition model for entity recognition, and determine the business objects included in the business activity information; The adjustment unit is configured to adjust the data entity range and the subject domain range respectively according to the data collection scenario; The collection unit is configured to collect business data based on the adjusted data entity range and subject domain range; The detection unit is configured to detect the collected business data by using a data format detection rule, a sensitive information detection rule, and a data logic detection rule respectively; if the business data does not meet the data format detection rule, or the sensitive information detection rule, or the data logic detection rule, then according to the type of problem existing in the business data, a quality problem report corresponding to the business data is generated by using a report template corresponding to the problem type, and the quality problem report is sent to the business personnel; The determination unit determines whether the file identifier corresponding to the business data meets a preset file identifier rule; if it meets the preset file identifier rule, then it determines whether the business data meets a preset data verification rule; if it meets the preset data verification rule, then the business data is collected based on the adjusted data entity range and subject domain range.

6. A computer device, comprising a memory, a processor, and a computer program stored on 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 4 are implemented.

7. 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 4 are implemented.

Images