Automatic insurance policy input system and method
Through the insurance policy automatic entry system using a robot process automation platform in the insurance industry, the automatic entry module, rule engine and exception display module are used to solve the accuracy and efficiency problems caused by manual input in insurance policy entry, and efficient and safe information is achieved Enter.
Patent Information
- Application Number
- CN202411455495.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-18
- Publication Date
- 2024-11-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the insurance industry, insurance policy entry requires manual input, resulting in the inability to ensure the accuracy and efficiency of entry when the business volume increases.
The policy automatic entry system running on the robot process automation platform is adopted, including an automatic entry module, a rule engine and an exception display module. The information to be entered is obtained through the automated process, abnormal detection is carried out according to the user-defined business rules, abnormal information is generated or the entry is returned successfully Information, improves entry speed and accuracy, and reduces manual dependence and costs.
It greatly improves the speed and efficiency of policy entry, reduces labor costs, enhances the accuracy and completeness of information, and protects information security through abnormal codes.
Smart Images

Figure CN118982010A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to automation technology, and more particularly to a system and method for automatically entering insurance policies. Background Art
[0002] In the insurance industry, most business processing is based on insurance policies, so policy entry is the basis of business processing.
[0003] In the prior art, employees are required to manually input relevant information to complete the entry of insurance policies. However, with the increase in business volume, the workload of salesmen has increased dramatically, and the accuracy and efficiency of insurance policy entry cannot be guaranteed. Summary of the invention
[0004] The present application provides a system and method for automatically entering insurance policies to improve the accuracy, efficiency and security of insurance policy entry.
[0005] In a first aspect, an embodiment of the present application provides an automatic policy entry system, which runs on a robotic process automation platform and includes: an automatic entry module, a rule engine, and an exception display module;
[0006] The automatic input module, the rule engine and the abnormal display module are sequentially connected in communication;
[0007] The automatic entry module is used to obtain the information to be entered in the insurance policy to be entered, and send the information to be entered to the rule engine;
[0008] The rule engine is used to obtain the business rules defined by the user and perform anomaly detection on the input information according to the business rules. If an anomaly is detected, the anomaly information is generated and sent to the anomaly display module. Otherwise, the successful input information is returned.
[0009] The exception display module is used to obtain exception information, determine the exception code corresponding to the exception information, and return the exception code.
[0010] In a second aspect, the embodiment of the present application further provides a method for automatic policy entry, which runs on a robotic process automation platform, comprising:
[0011] By obtaining the information to be entered in the insurance policy to be entered and sending it to the rule engine;
[0012] The rule engine detects anomalies in input information based on user-defined business rules;
[0013] If an exception is detected, the exception information is generated, and the corresponding exception code is determined according to the exception information, and the exception code is returned;
[0014] Otherwise, return the successful entry information.
[0015] The automatic entry system of the insurance policy of this application runs on the robot process automation platform. Through the automated process, the speed and efficiency of information entry are greatly improved, and the processing time is reduced; the automatic entry module is used to obtain the information to be entered in the insurance policy to be entered, and send the information to be entered to the rule engine, which can automatically obtain the information to be entered, reduce the dependence on the operator, and thus reduce the labor cost related to manual entry; the rule engine is used to obtain the business rules defined by the user, and treat the entered information for abnormal detection according to the business rules. If an abnormality is detected, the abnormal information is generated and sent to the abnormal display module, otherwise, the successful entry information is returned, and the entered information is automatically detected based on the business rules to improve the accuracy and completeness of the information to be entered; the abnormal display module is used to obtain abnormal information, determine the abnormal code corresponding to the abnormal information, and return the abnormal code, and avoid irrelevant personnel from obtaining the information to be entered through the abnormal code, thereby improving the security of the information to be entered. Therefore, through the technical solution of this application, the problem that employees need to manually enter relevant information to complete the entry of the insurance policy and cannot guarantee the accuracy and efficiency of the insurance policy entry is solved, and the accuracy and efficiency of the insurance policy entry are improved, as well as the effect of security. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 This is a schematic diagram of the structure of an automatic policy entry system in Embodiment 1 of the present application;
[0017] Figure 2 It is a structural diagram of an automatic input module in the second embodiment of the present application;
[0018] Figure 3 This is a schematic diagram of the structure of a rule engine in Embodiment 3 of the present application;
[0019] Figure 4 It is a structural schematic diagram of an abnormality display module in the fourth embodiment of the present application;
[0020] Figure 5 This is a flow chart of a method for automatically entering insurance policies in Example 5 of the present application. DETAILED DESCRIPTION
[0021] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.
[0022] It should be noted that the terms "first" and "second" etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0023] Embodiment 1
[0024] Figure 1 This is a structural diagram of an automatic policy entry system provided in Example 1 of the present application. This embodiment can be applied to the automatic entry of electronic policies or paper policies.
[0025] See also Figure 1 The policy automatic entry system shown runs on a robotic process automation platform and includes:
[0026] The automatic entry module 110, the rule engine 120 and the abnormality detection module 130; the automatic entry module 110, the rule engine 120 and the abnormality display module 130 are sequentially connected in communication.
[0027] Robotic process automation (RPA) is a business process automation system based on software robots and artificial intelligence. For a large number of insurance policy entry tasks, the automatic policy entry system can achieve batch processing using RPA technology. Through the automated process in RPA, multiple policies can be processed at the same time, and a large amount of information entry and verification can be completed in a short time. This greatly improves processing efficiency and reduces labor costs. For example, batch import multiple policies in Excel (a professional term, a document format) into the business processing system. The business processing system is used to process the policy information in the automatic policy entry system. The policy information obtained by the automatic policy entry system is input into the business processing system. For example, in the reinsurance industry, the business processing system can be a group finance quotation system.
[0028] The automatic entry module 110 is used to obtain the information to be entered in the insurance policy to be entered, and send the information to be entered to the rule engine 120. The information to be entered may be user information and business information in the insurance policy to be entered. Exemplarily, the information to be entered may be a key-value pair including a parameter type and a corresponding numerical value. For example, the parameter type of the information to be entered may include the policy type, the user type, and the user identity information. Exemplarily, the insurance policy to be entered may be a paper policy or an electronic policy. When entering the policy, it is necessary to identify the location of the information to be entered in the insurance policy to be entered, and identify the content of the information to be entered for entry. After completing the entry of the information to be entered, the information to be entered is sent to the rule engine 120 for rule anomaly detection. Exemplarily, the information to be entered can be identified by at least one of a natural language processing algorithm and a deep learning algorithm.
[0029] The rule engine 120 is used to obtain the business rules defined by the user and perform anomaly detection on the input information according to the business rules. If an anomaly is detected, the anomaly information is generated and sent to the anomaly display module 130. Otherwise, the input success information is returned.
[0030] Business rules can be rules defined by users according to business needs, which are used to detect anomalies in the input information and ensure the accuracy of the input information. For example, business rules can be types of parameter types, as well as business requirements and standard formats corresponding to the types, word lengths, and value ranges of values corresponding to different parameter types. For different types of business, users can determine different business rules and send them to the rule engine 120.
[0031] The rule engine 120 obtains the business rules input by the user, performs anomaly detection on the information to be entered according to the business rules, and if anomalies are detected in the information to be entered, anomaly information is generated according to the anomaly and sent to the anomaly display module 130 for display. Otherwise, that is, no anomaly is detected, the entry success information is returned to complete the entry of the insurance policy. Exceptions may include missing parameter types, out-of-range values, and incorrect word lengths of values. For example, if the business rules stipulate that the user ID is 11 digits, and the user ID in the insurance policy is detected to be 9 digits, it is determined that an anomaly exists and an anomaly information is generated. Exemplarily, the anomaly information may include incorrect parameter types and anomaly types. For example, the user ID word length is missing. Through the preset business rules, it is possible to automatically check whether the information to be entered meets the business requirements and standard formats, and automatically mark the data that does not meet the requirements so that further processing can be performed manually, thereby ensuring the accuracy and completeness of the data to be entered.
[0032] The rule engine 120 can be a lightweight Java-like (professional term, an object-oriented programming language) syntax rule engine, used as an embedded rule engine in the automatic policy entry system, making business rule definition easier and more flexible. The rule engine 120 supports standard Java syntax, and can support custom operation symbols, operation symbol overloading, function definition, macro definition, data delay loading, etc. Users can define business rules more conveniently, lowering the threshold for business rule setting.
[0033] The exception display module 130 is used to obtain exception information, determine the exception code corresponding to the exception information, and return the exception code. The exception code can be a code corresponding to different preset exception information, which is used to protect the security of information in the insurance policy. The exception display module 130 pre-acquires the exception codes corresponding to various exception information set by the user and stores them. After acquiring the exception information sent by the rule engine 120, it matches the corresponding exception code according to the exception information, and displays the successfully matched exception code to the user for easy correction.
[0034] The technical solution of this embodiment is that the automatic policy entry system of this application runs on a robotic process automation platform. Through automated processes, the speed and efficiency of information entry are greatly improved, and processing time is reduced; the automatic entry module is used to obtain the information to be entered in the insurance policy to be entered, and send the information to be entered to the rule engine, which can automatically obtain the information to be entered, reduce dependence on operators, and thus reduce the labor costs associated with manual entry; the rule engine is used to obtain user-defined business rules, and perform anomaly detection on the entered information according to the business rules. If an anomaly is detected, anomaly information is generated and sent to the anomaly display module, otherwise, an entry success message is returned, and the entered information is automatically detected based on the business rules to improve the accuracy and completeness of the information to be entered; the anomaly display module is used to obtain anomaly information, determine the anomaly code corresponding to the anomaly information, and return the anomaly code. The anomaly code is used to prevent irrelevant personnel from obtaining the information to be entered, thereby improving the security of the information to be entered. Therefore, the technical solution of the present application solves the problem that employees need to manually input relevant information to complete the entry of insurance policies, and the accuracy and efficiency of the insurance policy entry cannot be guaranteed, thereby achieving the effect of improving the accuracy and efficiency of insurance policy entry, as well as the security.
[0035] Embodiment 2
[0036] Figure 2 This is a structural diagram of an automatic entry module provided in Example 2 of the present application. The technical solution of this embodiment is further refined on the basis of the above technical solution.
[0037] Furthermore, the automatic entry module 110 includes: an optical character recognizer 111 and an information extraction unit 112; the optical character recognizer 111 is communicatively connected with the information extraction unit 112; the optical character recognizer 111 is used to obtain the insurance policy to be entered imported by the user and send it to the information extraction unit 112; the information extraction unit 112 is used to receive the insurance policy to be entered and extract key information from the insurance policy to be entered to obtain the information to be entered.
[0038] See also Figure 2 The structural diagram of an automatic input module shown includes: an optical character recognizer 111 and an information extraction unit 112; the optical character recognizer 111 is in communication with the information extraction unit 112.
[0039] The optical character recognizer 111 is used to obtain the insurance policy to be entered imported by the user and send it to the information extraction unit 112. The optical character recognizer 111 (Optical Character Recognition, OCR) can check the characters printed on the paper, determine their shapes by detecting dark and light patterns, and then use the character recognition algorithm to translate the shapes into computer text, convert the paper insurance policy into an electronic insurance policy, obtain the insurance policy to be entered, and after obtaining the insurance policy to be entered, send it to the information extraction unit 112 to obtain the information to be entered. Exemplarily, the optical character recognizer 111 can be a scanner or a digital camera, etc.
[0040] In an optional embodiment, the optical character recognizer 111 includes: a scanner and optical character recognition software; the scanner and the optical character recognition software are communicatively connected.
[0041] The scanner is used to scan the paper version of the insurance policy to be recorded to obtain the image to be recorded, and send the image to be recorded to the optical character recognition software. For the paper version of the insurance policy to be recorded, it is necessary to first convert the paper version of the insurance policy to be recorded through the scanner and send it to the optical character recognition software to generate the electronic version of the insurance policy to be recorded. Specifically, for the printed characters in the paper version of the insurance policy to be recorded, the text in the paper version of the insurance policy to be recorded is converted into a black and white dot matrix image file by optical means to obtain the image to be recorded.
[0042] Character recognition software is used to perform character recognition on the image to be entered to obtain the electronic version of the insurance policy to be entered.
[0043] The information extraction unit 112 is used to extract key information from the received insurance policy to be entered to obtain the information to be entered. The insurance policy to be entered sent by the optical character recognizer 111 is received, and key information from the insurance policy to be entered is extracted using a preset keyword recognition algorithm to obtain the information to be entered. In an optional embodiment, the information extraction unit 112 extracts key information based on at least one of a natural language processing algorithm and a machine learning algorithm.
[0044] The technical solution of this embodiment is to obtain the insurance policy to be entered imported by the user through the optical character recognizer 111, and send it to the information extraction unit 112, so as to convert the paper version of the insurance policy to be entered into the electronic version of the insurance policy to be entered, and enrich the application scope of the automatic insurance policy entry system; the information extraction unit 112 is used to receive the insurance policy to be entered, and extract the key information in the insurance policy to be entered, obtain the information to be entered, automatically extract the information to be entered, improve the entry efficiency of the information to be entered, and reduce labor costs.
[0045] Embodiment 3
[0046] Figure 3 The figure shows a schematic diagram of the structure of a rule engine provided in the third embodiment of the present application. The technical solution of this embodiment is further refined on the basis of the above technical solution.
[0047] Furthermore, the rule engine 120 includes: a rule generation unit 121 and a detection unit 122; the rule generation unit 121 and the detection unit 122 are communicatively connected; the rule generation module 121 is used to obtain the business rules input by the user and generate a target rule statement according to the business rules; the detection unit 122 is used to call the target rule statement to perform rule detection on the input information, and if abnormal information is detected, it is sent to the abnormal display module 130, otherwise, the entry success information is returned.
[0048] See also Figure 3 The structural diagram of a rule engine shown includes: a rule generating unit 121 and a detecting unit 122; the rule generating unit 121 and the detecting unit 122 are in communication connection.
[0049] The rule generation module 121 is used to obtain the business rules input by the user and generate target rule statements according to the business rules.
[0050] The user can be a salesperson, who can set business rules based on business needs to ensure the correctness of the information to be entered. Exemplarily, business rules can include general rules and personalized rules. General rules apply to the business used; personalized rules apply to special rules of the corresponding business. For example, general rules can include data cleaning, removing invalid and duplicate data. For example, personalized rules can be types of parameter types. The types of parameter types to be obtained for different businesses are different, so specific personalized rules can be set according to specific businesses.
[0051] The target rule statement can be a compiled Java statement, which can perform corresponding data detection and verification functions when called by the user. The user can use the input page to input business rules, and the rule generation module 121 obtains the business rules input by the user, compiles them, and generates target rule statements. Optionally, basic functions can be provided to the user, and the user can input business rules by dragging the required basic functions to the corresponding positions, thereby improving the convenience of users setting business rules, lowering the user's usage threshold, and improving the versatility of the automatic policy entry system.
[0052] In an optional embodiment, the rule generation module 121 includes a general rule package for storing general business rules. The user can add some general business rules to the general rule package to avoid the user from repeatedly setting business rules. Exemplarily, the general rule package may include deduplication of duplicate data, deletion of invalid data, and word length missing detection and value type validity detection for parameter types with fixed word lengths, etc., which are not specifically limited in this application. For example, the general rule package may include a user identifier as a character type. When the rule is called, if it is detected that the value corresponding to the user identifier is not a character type, it can be determined that the value is invalid.
[0053] The rule generation module 121 includes a general rule package for storing general business rules, which can avoid users from repeatedly setting some general business rules and save labor costs; and can effectively avoid users from missing settings, ensure the comprehensiveness of data detection, and improve the accuracy of information to be entered.
[0054] The detection unit 122 is used to call the target rule statement to perform rule detection on the input information. If abnormal information is detected, it is sent to the abnormal display module 130. Otherwise, the input success information is returned.
[0055] After receiving the information to be entered, the detection unit 122 retrieves the target rule statement and performs rule detection on the information to be entered through the target rule statement. If abnormal information is detected, it is sent to the abnormal display module, otherwise, the successful entry information is returned. The successful entry information can be fed back to the user in the form of text or voice to prompt the user that the entry is successful.
[0056] In an optional embodiment, the automatic policy entry system further includes: a business system interface 140, which is used to communicate with a business system. The business system may be a system for processing the information to be entered. The data to be entered is transmitted to the business system for processing through the business system interface 140, thereby improving the automation of data processing.
[0057] The technical solution of this embodiment is to obtain the business rules input by the user through the rule generation module 121, and generate the target rule statement according to the business rules, automatically generate the target rule statement, improve the convenience of business rule configuration, lower the user's usage threshold, and improve the versatility of the automatic policy entry system; the detection unit 122 is used to call the target rule statement to perform rule detection on the information to be entered. If abnormal information is detected, it is sent to the abnormal display module 130. Otherwise, the entry success information is returned, which can improve the completeness and accuracy of the information to be entered.
[0058] Embodiment 4
[0059] Figure 4 This is a structural schematic diagram of an abnormal display module provided in Example 4 of the present application. The technical solution of this embodiment is further refined on the basis of the above technical solution.
[0060] Furthermore, the exception display module 130 includes: an exception code definition module 131 and an exception code matching module 132; the exception code definition module 131 and the exception code matching module 132 are communicatively connected; the exception code definition module 131 is used to obtain the custom code corresponding to the user-defined exception type and store it in the exception code matching table; the exception code matching module 132 is used to call the exception code matching table in the exception code definition module 131 after obtaining the exception information sent by the rule engine, match the exception information with the exception information in the exception code matching table to obtain the corresponding custom code, and return the custom code as the exception code to the user display interface.
[0061] See also Figure 4 The structural diagram of an abnormality display module shown includes: an abnormality code definition module 131 and an abnormality code matching module 132; the abnormality code definition module 131 and the abnormality code matching module 132 are in communication connection.
[0062] The exception code definition module 131 is used to obtain the custom code corresponding to the user-defined exception type and store it in the exception code matching table. The custom code can be the code corresponding to the user-defined exception type. The user can input the custom code corresponding to the exception type through the user interface, and the exception code definition module 131 receives the custom code corresponding to the exception type, associates the exception type and the corresponding custom code and stores it to obtain the exception code matching table.
[0063] The exception code matching module 132 is used to call the exception code matching table in the exception code definition module 131 after obtaining the exception information sent by the rule engine 120, match the exception information with the exception information in the exception code matching table to obtain the corresponding custom code, and return the custom code as the exception code to the user display interface.
[0064] After detecting the exception information, the rule engine 120 sends it to the exception display module 130. The exception code matching module 132 in the exception display module 130 obtains the exception information, calls the exception code matching table in the exception code definition module 131, matches the exception information with the exception information in the exception code matching table to obtain the corresponding custom code, and returns the custom code as the exception code to the user display interface for display, so as to prompt the user to make corrections.
[0065] The exception code definition module 131 is used to obtain the custom code corresponding to the user-defined exception type and store it in the exception code matching table; the exception code matching module 132 is used to call the exception code matching table in the exception code definition module 131 after obtaining the exception information sent by the rule engine, match the exception information with the exception information in the exception code matching table to obtain the corresponding custom code, and return the custom code as the exception code to the user display interface. The exception information is customized through the user-defined code, and other users cannot know the meaning of the exception code, thereby protecting the security of the information to be entered.
[0066] Embodiment 5
[0067] Figure 5 This is a flow chart of a method for automatic policy entry provided in Example 5 of the present application. This embodiment can be applied to the situation of automatic entry of insurance policies. The method can be executed by an automatic policy entry system and run on a robotic process automation platform.
[0068] See also Figure 5 The automatic policy entry method shown is run on a robotic process automation platform and specifically includes the following steps:
[0069] The technical solution of this embodiment runs on a robotic process automation platform. For a large number of insurance policy entry tasks, the automatic policy entry system can achieve batch processing using RPA technology. Through the automated process in RPA, multiple insurance policies can be processed at the same time, and a large amount of information entry and verification can be completed in a short time. It can greatly improve processing efficiency and reduce labor costs. For example, batch import multiple insurance policies in Excel to the business processing system. The business processing system is used to perform business processing on the insurance policy information in the automatic policy entry system. The insurance policy information obtained by the automatic policy entry system can be input into the business processing system. For example, the business processing system can be a group finance quotation system.
[0070] S210, obtaining the information to be entered in the insurance policy to be entered, and sending it to the rule engine.
[0071] The insurance policy to be entered can be a paper policy or an electronic policy. When entering the policy, it is necessary to identify the location of the information to be entered in the policy and identify the content of the information to be entered. For paper policies, an electronic version of the insurance policy to be entered can be obtained through a scanner and optical character recognition software. For the electronic version of the insurance policy to be entered, key information can be extracted based on at least one of a natural language processing algorithm and a machine learning algorithm to obtain the information to be entered. The information to be entered is sent to the rule engine for anomaly detection.
[0072] S220: The rule engine performs anomaly detection on the input information according to the business rules defined by the user.
[0073] Anomaly detection is used to ensure the accuracy and completeness of the information to be entered. Business rules can be anomaly detection rules that users can define according to business needs. Exemplarily, business rules can be types of parameter types, as well as business requirements and standard formats corresponding to the types, word lengths, and value ranges of numerical values corresponding to different parameter types. The rule engine can be a lightweight Java-like syntax rule engine, used as an embedded rule engine in the automatic policy entry system. Users can define business rules in the rule engine according to business needs, and rely on the rule engine for efficient anomaly detection; and by defining business rules, it can automatically check whether the information to be entered meets business requirements and standard formats, and automatically mark data that does not meet the requirements for further manual processing, ensuring the accuracy and completeness of the data to be entered.
[0074] S230. If an exception is detected, generate exception information, determine a corresponding exception code based on the exception information, and return the exception code.
[0075] The exception may be a situation in which the information to be entered does not conform to the business rules. Exemplarily, the exception may include missing parameter types, numerical values exceeding the range, and numerical word length errors, etc., which are not specifically limited in this application. Exception information is generated according to the specific content of the exception. Exemplarily, the exception information may include incorrect parameter types and exception types. For example, the user identification word length is missing. The exception code may be a code corresponding to various exceptions predefined by the user. If exception information is detected, the corresponding exception code is determined, and the exception code is returned for display.
[0076] In an optional embodiment, determining the corresponding exception code according to the exception information includes: obtaining the exception code corresponding to each candidate exception information; traversing each candidate exception information to determine the exception code corresponding to the exception information.
[0077] The candidate abnormal information may be various abnormal information preset, and the abnormal code may be the code set by the user for each candidate abnormality. After the abnormal information is obtained, each candidate abnormal information is traversed to determine the candidate abnormal information with the same abnormal code, and the abnormal code corresponding to the candidate abnormal information is used as the abnormal code corresponding to the abnormal information.
[0078] By obtaining the exception code corresponding to each candidate exception information; traversing each candidate exception information, determining the exception code corresponding to the exception information, setting the exception code for each candidate exception information in advance, and using the exception code corresponding to each candidate exception information, irrelevant personnel are prevented from obtaining the information to be entered, thereby improving the security of the information to be entered.
[0079] S240: Otherwise, return the entry success information.
[0080] Otherwise, that is, there is no abnormal information, the user's input success information is returned to complete the automatic entry of the insurance policy.
[0081] The technical solution of this embodiment runs on a robotic process automation platform, and greatly improves the speed and efficiency of information entry and reduces processing time through automated processes; by obtaining the information to be entered in the insurance policy to be entered and sending it to the rule engine; the rule engine performs anomaly detection on the information to be entered according to the business rules defined by the user, and automatically detects the information to be entered based on the business rules based on the rule engine, thereby improving the accuracy and completeness of the information to be entered; if an anomaly is detected, the corresponding anomaly code is determined based on the anomaly information, and the anomaly code is returned, and the anomaly code is used to prevent irrelevant personnel from obtaining the information to be entered, thereby improving the security of the information to be entered; otherwise, a successful entry message is returned. Therefore, the technical solution of this application solves the problem that employees need to manually enter relevant information to complete the entry of the insurance policy, and the accuracy and efficiency of the insurance policy entry cannot be guaranteed, thereby achieving the effect of improving the accuracy and efficiency of the insurance policy entry, as well as the security.
[0082] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.
Claims
1. An automatic policy entry system, characterized in that: It runs on the Robotic Process Automation platform, including: automatic entry module, rule engine and exception display module; The automatic entry module, the rule engine and the abnormal display module are sequentially connected in communication; The automatic entry module is used to obtain the information to be entered in the insurance policy to be entered, and send the information to be entered to the rule engine; The rule engine is used to obtain the business rules defined by the user, and perform anomaly detection on the information to be entered according to the business rules. If an anomaly is detected, anomaly information is generated and sent to the anomaly display module; otherwise, an entry success message is returned; The abnormality display module is used to obtain the abnormality information, determine the abnormality code corresponding to the abnormality information, and return the abnormality code.
2. The system according to claim 1, characterized in that The automatic input module includes: an optical character recognizer and an information extraction unit; The optical character recognizer is communicatively connected to the information extraction unit; An optical character recognizer, used for acquiring the insurance policy to be entered imported by the user and sending it to the information extraction unit; The information extraction unit is used to receive the insurance policy to be entered, and extract key information from the insurance policy to be entered to obtain the information to be entered.
3. The system according to claim 2, characterized in that The optical character recognizer comprises: a scanner and character recognition software; Communication connection between scanner and character recognition software; The scanner is used to scan the paper version of the insurance policy to be recorded to obtain the image to be recorded, and send the image to be recorded to the character recognition software; The character recognition software is used to perform character recognition on the image to be entered to obtain an electronic version of the insurance policy to be entered.
4. The system according to claim 2, characterized in that The information extraction unit extracts key information based on at least one of a natural language processing algorithm and a machine learning algorithm.
5. The system according to claim 1, characterized in that The rule engine comprises: Rule generation unit and detection unit; The rule generating unit is in communication with the detecting unit; The rule generation module is used to obtain the business rules input by the user and generate the target rule statement according to the business rules; The detection unit is used to call the target rule statement to perform rule detection on the information to be entered. If abnormal information is detected, it is sent to the abnormal display module; otherwise, the entry success information is returned.
6. The system according to claim 1, characterized in that The rule generation module includes a general rule package for storing general business rules.
7. The system according to claim 1, characterized in that The abnormality display module includes: an abnormality code definition module and an abnormality code matching module; The exception code definition module is communicatively connected with the exception code matching module; The exception code definition module is used to obtain the custom code corresponding to the user-defined exception type and store it in the exception code matching table; The exception code matching module is used to call the exception code matching table in the exception code definition module after obtaining the exception information sent by the rule engine, match the exception information with the exception information in the exception code matching table to obtain the corresponding custom code, and return the custom code as the exception code to the user display interface.
8. The system according to claim 1, characterized in that Also includes: Business system interface, The business system interface is used to communicate with the business system.
9. A method for automatically entering an insurance policy, characterized in that: Runs on the Robotic Process Automation platform, including: By obtaining the information to be entered in the insurance policy to be entered and sending it to the rule engine; The rule engine performs anomaly detection on the information to be entered according to the business rules defined by the user; If an exception is detected, the exception information is generated, and the corresponding exception code is determined according to the exception information, and the exception code is returned; Otherwise, return the successful entry information.
10. The method according to claim 9, characterized in that Determining the corresponding exception code according to the exception information includes: Obtain the exception code corresponding to each candidate exception information; Each candidate exception information is traversed to determine the exception code corresponding to the exception information.
Citation Information
Patent Citations
Logging method, device, computer equipment and storage medium of policy information
CN107688772A
Abnormality handling method and device, computer device, and storage medium
CN109376025A
Online whole-process method and system based on insurance extension
CN114037404A
Robot abnormal information processing method, terminal equipment, server and processing system
CN114298347A
Abnormity detection method, device and equipment based on cross-system data transmission
CN114331689A
