Insurance Business Data Collection and Analysis Method, Device, Equipment and Medium

Abstract

The present invention is applicable to the technical field of insurance business data processing, and particularly relates to a method, device, equipment and medium for collecting and analyzing insurance business data. The present invention generates a first recommended collection requirement template according to the current configuration information. If the current configuration information is incomplete, the historical collection requirement template with the highest similarity is used as the second recommended collection requirement template. The first recommended collection requirement template or the second recommended collection requirement template is determined as the final collection requirement template. A collection task is generated according to the final collection requirement template, and the collection task is executed to obtain the first collection data. If the first collection data meets the preset conditions, the first collection data is sent to the RPA robot for analysis to obtain the target data. By collecting and analyzing data through the above method, the data analysis efficiency can be effectively improved, and the problem that the timeliness of data cannot meet the business requirements due to insufficient manpower can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of insurance business data processing, and particularly to an insurance business data collection and analysis method, device, equipment and medium. Background Art

[0002] At present, before each industry conducts business, people increasingly rely on the auxiliary analysis of data and information for decision-making. For example, in the insurance industry, the business department submits a requirements form, and colleagues in the collection and development group analyze the requirements form and write a script program. The script program is run regularly for data collection, and the collected data is sent to business personnel via email. Then, the business personnel analyze the collected data to obtain useful data. When collecting and analyzing data through the above method, if the requirements change, a new requirements form needs to be submitted and a new script program needs to be developed, which requires a large amount of manual intervention. In the case of a large number of collection forms, insufficient manpower will result in the inability to meet the business requirements in terms of data timeliness. Summary of the Invention

[0003] Based on this, it is necessary to provide an insurance business data collection and analysis method, device, equipment and medium for the above technical problems, so as to solve the problem in the prior art that when there are a large number of data collection forms, insufficient manpower will lead to the inability to meet the business requirements in terms of timeliness.

[0004] In a first aspect, an embodiment of the present invention provides an insurance business data collection and analysis method, and the method includes:

[0005] Obtain the current configuration information of the insurance business data collection requirements, and generate a first recommended collection requirements template according to the current configuration information;

[0006] Judge whether the current configuration information is complete. When it is determined that the current configuration information is incomplete, traverse the template database, compare the similarity between the configuration information of each historical collection requirements template in the template database and the current configuration information, and use the historical collection requirements template with the largest similarity as the second recommended collection requirements template;

[0007] Push the first recommended collection requirements template and the second recommended collection requirements template to the user for selection, obtain the selection result of the user, and determine the first recommended collection requirements template or the second recommended collection requirements template as the final collection requirements template according to the selection result of the user;

[0008] Generate a collection task according to the final collection requirements template, execute the collection task, and obtain the first collection data;

[0009] If the first collected data meets the preset conditions, the first collected data is sent to the RPA robot, and the RPA robot is used to analyze the first collected data to obtain the target data.

[0010] In a second aspect, an embodiment of the present invention provides an insurance business data collection and analysis device, and the device includes:

[0011] A template generation module, configured to obtain the current configuration information of the insurance business data collection requirements, and generate a first recommended collection requirements template according to the current configuration information;

[0012] A template recommendation module, configured to determine whether the current configuration information is complete. When it is determined that the current configuration information is incomplete, traverse the template database, and calculate the similarity between the configuration information of each historical collection requirements template in the template database and the current configuration information, and use the historical collection requirements template with the largest similarity as the second recommended collection requirements template;

[0013] A template determination module, configured to push the first recommended collection requirements template and the second recommended collection requirements template to the user for selection, obtain the selection result of the user, and determine the first recommended collection requirements template or the second recommended collection requirements template as the final collection requirements template according to the selection result of the user;

[0014] A data collection module, configured to generate a collection task according to the final collection requirements template, execute the collection task, and obtain the first collected data;

[0015] A data processing module, configured to, if the first collected data meets the preset conditions, send the first collected data to the RPA robot, and use the RPA robot to analyze the first collected data to obtain the target data.

[0016] In a third aspect, an embodiment of the present invention provides a computer device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the insurance business data collection and analysis method as described in the first aspect.

[0017] In a fourth aspect, an embodiment of the present invention provides a computer-readable medium. The computer-readable storage medium stores a computer program, and is characterized in that when the computer program is executed by a processor, it implements the insurance business data collection and analysis method as described in the first aspect.

[0018] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows: The present invention does not require a large amount of manual intervention for the collection and analysis of insurance business data. Only by manually inputting the data requirements of the insurance business by the user can a data collection task be automatically generated, and the first collection data can be obtained. The first collection data is sent to the RPA robot for analysis to obtain the target data. When the manually input configuration information is incomplete, two data collection templates are recommended. One is the template generated according to the current configuration information, and the other is the historical template most similar to the current configuration information, preventing the incomplete configuration information caused by user negligence from affecting the accuracy of data collection. By collecting and analyzing data through the above method, the present invention can effectively improve the data analysis efficiency and solve the problem that the timeliness of data cannot meet the business requirements due to insufficient manpower. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0020] Figure 1 It is a schematic diagram of the application environment of a method for collecting and analyzing insurance business data provided in Embodiment 1 of the present invention;

[0021] Figure 2 It is a schematic flowchart of a method for collecting and analyzing insurance business data provided in Embodiment 1 of the present invention;

[0022] Figure 3 It is a schematic structural diagram of a device for collecting and analyzing insurance business data provided in Embodiment 2 of the present invention;

[0023] Figure 4 It is a schematic structural diagram of a computer device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] In the following description, specific details such as specific system structures and technologies are proposed for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, the detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0025] It should be understood that, as used in the specification of the present invention and the appended claims, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their combinations.

[0026] It should also be understood that the term "and / or" as used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0027] As used in the specification of the present invention and the appended claims, the term "if" may be construed, depending on the context, as "when" or "once" or "in response to determining" or "in response to detecting". Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be construed, depending on the context, as meaning "once determined" or "in response to determining" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]".

[0028] In addition, in the description of the specification of the present invention and the appended claims, the terms "first", "second", "third", etc. are used only for descriptive distinction and should not be construed as indicating or implying relative importance.

[0029] Reference to "one embodiment" or "some embodiments" or the like described in the specification of the present invention means that a particular feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of the present invention. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc., which appear in different places in this specification, are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized.

[0030] Embodiments of the present invention may acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is a theory, method, technology and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results.

[0031] The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation / interaction systems, and mechatronics. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0032] It should be understood that the magnitudes of the sequence numbers of the steps in the following embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0033] In order to illustrate the technical solution of the present invention, the following specific embodiments are used for illustration.

[0034] An insurance business data collection and analysis method provided in Embodiment 1 of the present invention can be applied in an application environment such as Figure 1 , where the client communicates with the server. The client includes, but is not limited to, computer devices such as a palm computer, a desktop computer, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a cloud computer device, and a personal digital assistant (PDA). The server can be implemented by an independent server or a server cluster composed of multiple servers.

[0035] Refer to Figure 2 , which is a schematic flowchart of an insurance business data collection and analysis method provided in Embodiment 1 of the present invention. The above insurance business data collection and analysis method can be applied to the client in Figure 1 . The corresponding computer device connects to the server through the Internet, connects to the insurance business information database on the server side through a preset Application Programming Interface (API), and obtains the first collection data through a collection task. As shown in Figure 2 , the insurance business data collection and analysis method may include the following steps:

[0036] Step S201, obtain the current configuration information of the insurance business data collection requirement, and generate a first recommended collection requirement template according to the current configuration information.

[0037] Among them, the insurance business collection requirements are the data required by insurance business personnel to carry out business. According to the description information of the required data, the current configuration information of the insurance business collection requirements is obtained, and the current configuration information of the insurance business collection requirements is input into the software page of the computer device. According to the input current configuration information, a first recommended collection requirement template is automatically generated. The above collection requirement template includes collection frequency, specific collection time, recipient email, data format, collection fields, and detailed collection conditions.

[0038] Among them, the collection frequency represents the number of collections per day. For example, if the collection frequency is set to 5, it means that 5 collection tasks are executed per day, and the time interval between two adjacent times is the same.

[0039] The specific collection time means that the collection task is executed at the set specific time, and the recipient email is used to receive the first collected data or the target data after being analyzed by the RPA robot.

[0040] The data format means that the collected data is sorted in the set data format. For example, if the data format is set to name + age + gender, then the first collected data is sent in the data format of name + age + gender.

[0041] The collection fields mean which relevant fields are collected during the execution of the collection task. For example, for the data currently required for the insurance business, the relevant fields collected include insurance-related fields, such as keywords like insurance, policyholder, insured, and beneficiary.

[0042] The detailed collection conditions are the rules based on which the collection task is executed. For example, if the detailed collection conditions are set to include the age range of 30 to 40 years old and the gender is male, then only the data that meets the above detailed collection conditions is collected during the data collection process of the collection task.

[0043] In the present invention, according to the above current configuration information, a first recommended collection requirement template is automatically generated. The first collection requirement template is generated according to the configuration information actually filled in by the user. That is, even if the items filled in by the user are incomplete, a first recommended collection requirement template will still be generated according to the filled configuration information. For example, if the user forgets to fill in the gender parameter, then the generated first recommended collection requirement template does not include the gender parameter, and both male and female data are collected during the data collection process.

[0044] Step S202: Determine whether the current configuration information is complete. When it is determined that the current configuration information is incomplete, traverse the template database, compare the similarity between the configuration information of each historical collection requirement template in the template database and the current configuration information, and use the historical collection requirement template with the greatest similarity as the second recommended collection requirement template.

[0045] Optionally, obtain the authentication information of the current user, connect to the historical collection requirement template database corresponding to the current user, and traverse the historical collection requirement templates in the historical collection requirement template database in sequence according to the configuration information filled in by the current user.

[0046] Among them, the configuration information of the historical collection requirement templates corresponding to each user is stored in the template database. After the user logs in to the system, obtain the authentication information of the current user, automatically connect to the historical collection requirement template corresponding to the user in the template database, and traverse the historical collection requirement templates in the historical collection requirement template database in sequence according to the configuration information filled in by the current user to obtain the historical collection requirement template that is most similar to the configuration information filled in by the current user.

[0047] In the present invention, the above step S201 is to generate the first recommended collection requirement template according to the configuration information filled in by the user. Then, when it is determined that the configuration information filled in by the user is incomplete, this step is to compare the similarity between the specific parameters of the configuration information filled in by the user and the configuration information of each historical collection requirement template in the template database, and screen out the historical collection requirement template with the largest similarity as the second recommended collection requirement template. Then, when the user omits to fill in parameters, two collection requirement templates can be obtained for selection, preventing the configuration information from being incomplete due to the user's negligence and affecting the accuracy of data collection.

[0048] Judging whether the current configuration information is complete includes the following steps:

[0049] Obtain the parameter values of the current configuration information, and judge whether the parameter values of the current configuration information are valid data. If all the parameter values of the current configuration information are valid data, it is determined that the current configuration information is complete.

[0050] If there are invalid data among the parameter values of the current configuration information, or there are missing items among the parameter values of the current configuration information, it is determined that the current configuration information is incomplete.

[0051] After the user fills in the parameter values of the current configuration information, the system obtains the parameter values of the current configuration information filled in by the user and compares them with the default value range of each parameter. If all the parameter values of the current configuration information are within the default value range, it is determined that the current configuration information filled in by the user is complete. If there are missing items or the parameter values exceed the parameter default value range among the above parameter values, it is determined that the current configuration information filled in by the user is incomplete.

[0052] For example, the current configuration information includes three items of data: age, gender, and working years. The default value range for the age item is 0 - 120, there are only male and female genders, and the default value range for the working years is 0 - 60. When the user fills in the current configuration information, they mistakenly write the age as 200 or forget to fill in the parameter value for this item. The gender is male, and the working years is 20. Since the parameter value of the age item exceeds the default value range of the parameter value or is missing, it is determined that the current configuration information filled in by the user is incomplete. If all three items of data of the user's current configuration information are filled in and within the parameter default value range, it is determined that the current configuration information filled in by the user is complete.

[0053] Optionally, comparing the similarity between the configuration information of each historical collection requirement template in the template database and the current configuration information, and taking the historical collection requirement template with the highest similarity as the second recommended collection requirement template includes the following steps:

[0054] Obtain the historical configuration information of each historical collection requirement template to obtain the parameter values of each item of the historical configuration information;

[0055] Obtain the current configuration information to obtain the parameter values of each item of the current configuration information, compare the parameter values of each item of the historical configuration information with the parameter values of each item of the current configuration information, and determine the historical collection requirement template corresponding to the configuration information with the largest number of identical parameter values as the historical collection requirement template with the highest similarity, and recommend it as the second recommended collection requirement template.

[0056] When it is determined that the current configuration information is not filled in completely, the second collection requirement template will be recommended according to the parameters of the current configuration information filled in by the user. Obtain the configuration information of each historical collection requirement template corresponding to the user to obtain the parameter values corresponding to each item of the configuration information of each historical collection requirement template, and then obtain the parameter values corresponding to the configuration information of the current collection requirement template filled in by the user. Compare the parameter values corresponding to each item of the configuration information of each historical collection requirement template with the parameter values corresponding to the configuration information of the current collection requirement template, and take the historical collection requirement template corresponding to the configuration information with the largest number of identical parameter values between the parameter values corresponding to the configuration information of the historical collection requirement template and the parameter values corresponding to the configuration information of the current collection requirement template as the second recommended collection requirement template and recommend it to the user for the user to select or correct errors.

[0057] For example, the current configuration information includes three pieces of data: age, gender, and years of work experience. The default value range for the age item is 0 - 120, there are only male and female genders, and the default value range for the years of work experience is 0 - 60. When the user fills in the current configuration information, they miswrite the age as 200 or forget to fill in the parameter value for this item. The gender is male, and the years of work experience is 20. Since the parameter value of the age item exceeds the default value range of the parameter value or is missing, it is determined that the current configuration information filled in by the user is incomplete. Then, the configuration information in the historical collection requirement template library is traversed. If the configuration information with a gender of male and years of work experience of 20 is traversed, the corresponding historical collection requirement template of this configuration information is recommended to the user for selection.

[0058] Step S203: Push the first recommended collection requirement template and the second recommended collection requirement template to the user for selection, obtain the selection result of the user, and determine the first recommended collection requirement template or the second recommended collection requirement template as the final collection requirement template according to the selection result of the user.

[0059] When the current configuration information filled in by the user is incomplete, the system recommends the first recommended collection requirement template and the second recommended collection requirement template to the user. The user selects the first recommended collection requirement template or the second recommended collection requirement template according to their own intention. The user can select the first recommended collection requirement template or the second collection requirement template as the final collection requirement template.

[0060] For example, when the user fills in the current configuration information and there is a missing item, which is determined by the system to be incomplete current configuration information, and this missing item is a deliberately set missing item by the user. Then, although the system recommends the second recommended collection requirement template, this user will still select the first recommended collection requirement template as the final collection requirement template. If the above missing item is caused by the user's negligence and omission, this user will modify the current configuration information according to the second recommended collection requirement template or directly select the second recommended collection requirement template.

[0061] Step S204: Generate a collection task according to the final collection requirement template, execute the collection task, and obtain the first collection data.

[0062] In the present invention, the collection task can be written using Structured Query Language (SQL). SQL is a special-purpose programming language, a database query and programming language used to access data and query, update, and manage relational database systems, and has the functions of data definition, data manipulation, and data control.

[0063] Establish a general data collection task program through the above SQL. The general data collection task program is as follows: The execution methods of the collection task programs are the same. The differences between different collection tasks lie in the different data collection rules included in the collection requirement template. Connect the collection rule parameter ports corresponding to the collection task program to the collection requirement template, and transmit the parameter values included in the final collection requirement template to the general collection task program through the ports of the collection task, automatically configure the parameter values of the general collection task program, and quickly generate a collection task corresponding to the collection requirement template.

[0064] The above method generates a collection task program. The task collection program includes the specific execution time of the task collection program. Execute the collection task according to the specific execution time to obtain the first collection data that meets the final collection requirement template.

[0065] For example, the current configuration information has four items of data: age, gender, working years, and collection time. The collection task program reserves ports for the four items of data: age, gender, working years, and collection time. After the current configuration information is configured, transmit the specific parameter values of the four items of age, gender, working years, and collection time to the general collection task program, thereby generating a collection task program corresponding to the current configuration information. The collection task program executes the collection task according to the set collection time to obtain the first collection data that meets the current configuration information.

[0066] Optionally, if the user's requirements need to be adjusted during the execution of the collection task, the execution of the collection task can be paused at any time, and the data collected before pausing the execution of the collection task is generated as the first temporary collection data;

[0067] Generate a collection task again according to the adjusted collection requirement template by the user. When generating the collection task again, only update the parameter items adjusted by the user, and do not update the parameter items not adjusted by the user.

[0068] In the present invention, the user can adjust the collection requirement template at any time. During the execution of the collection task, the user can pause the collection task, fill in the new collection requirement parameters into the configuration information to generate the adjusted collection requirement template. When generating the collection task according to the adjusted collection requirement template, only update the adjusted parameters to improve the efficiency of generating the collection task.

[0069] Step S205, if the first collection data meets the preset conditions, send the first collection data to the RPA robot, and use the RPA robot to analyze the first collection data to obtain the target data.

[0070] Among them, Robotic Process Automation (RPA) is a software or platform that, according to a preset program, simulates and enhances the interaction process between humans and computers, executes a large number of repeatable tasks based on certain rules, and realizes the automation of work processes.

[0071] In the present invention, based on Cognitive RPA, the machine learning technology in artificial intelligence is used to construct a neural network model. The neural network model in the RPA robot analyzes the first collected data to obtain the target data required by the user, and sends the target data.

[0072] Obtain a set data threshold, compare the size of the first collected data with the set data threshold. If the size of the first collected data is greater than the set data threshold, send the first collected data to the RPA robot, and use the RPA robot to analyze the first collected data to obtain the target data.

[0073] In the present invention, a set data threshold is set. This set threshold can be adjusted by the user himself. After the collection task is completed, the first collected data is obtained, and the size of the first collected data is obtained. Compare the size of the first collected data with the set threshold. If the size of the first collected data is greater than the set threshold, it means that the first collected data is large, and the first collected data needs to be sent to the RPA robot for automated analysis, screen out the data with higher relevance, and delete the data with lower relevance to obtain the target data.

[0074] For example, the user sets the data threshold to 50 megabytes, and the size of the first collected data collected by the collection task is 60 megabytes. Since the size of the first collected data is greater than the set data threshold, the first collected data is sent to the RPA robot for analysis.

[0075] Obtain a set data threshold, compare the size of the first collected data with the set data threshold. If the size of the first collected data is less than or equal to the set data threshold, do not analyze the first collected data and directly send the first collected data.

[0076] In the present invention, a set data threshold is set. This set threshold can be adjusted by the user himself. After the collection task is completed, the first collected data is obtained, and the size of the first collected data is obtained. Compare the size of the first collected data with the set threshold. If the size of the first collected data is less than or equal to the set threshold, it means that the first collected data is small, and the user can directly use this data without sending it to the RPA robot for analysis, and then directly send the first collected data to the user through the email set by the user in the collection requirement template.

[0077] For example, the user sets the data threshold to 50 megabytes. The size of the first collected data collected by the collection task is 20 megabytes. Since the size of the first collected data is less than the set data threshold, the first collected data is directly sent to the user via email.

[0078] Analyzing the first collected data by using an RPA robot to obtain target data includes the following steps:

[0079] Analyze the first collected data through the neural network model built in the RPA robot to obtain target data. The training process of the neural network model is as follows:

[0080] Obtain training samples, where the training samples include: the historical collected data obtained after the execution of the collection tasks of each historical collection requirement template, set the labels of each historical collected data, and the labels of each historical collected data are determined according to the data that meets the requirements of the target data in each historical collected data.

[0081] Train the neural network model, and the loss function uses the cross-entropy loss function.

[0082] In the present invention, for the neural network model built in the RPA robot, analyze the first collected data through the neural network model. The training of the neural network model includes the following steps:

[0083] (1) Construct data, obtain the historical collected data obtained after the execution of the collection tasks of each historical collection requirement template, screen the historical collected data manually, according to the detailed information of the historical collected data, retain the data that meets the requirements of the insurance business, and set the labels of each historical collected data, and delete the data that does not meet the requirements of the insurance business to obtain the training samples required for training the model.

[0084] (2) Select a model, that is, select an algorithm. Under the premise of the same data characteristics, different algorithms bring different effects. In the present invention, determine the algorithm according to the rules for obtaining target data, and select the BackPropagation (BP) neural network model. The BP neural network model includes an input layer, a hidden layer, and an output layer. If the desired output result cannot be obtained in the output layer, then turn to the reverse propagation process of the error signal. Through the alternating execution of these two processes, execute the gradient descent strategy of the error function in the weight vector space, dynamically iterate to search for a set of weight vectors to minimize the network error function, thereby completing the process of information extraction and memory.

[0085] (3) Model training, input the above training database into the established BP neural network model, and output the initial database according to the algorithm of the BP neural network model.

[0086] (4) Model optimization. The process of model optimization is the process of iteratively upgrading the model and data. In the present invention, the difference between the data in the initial database and the ideal data is calculated by the cross entropy loss function, and the parameters of the initial neural network model are adjusted according to the difference until the above difference is within the specified range, thereby obtaining a trained neural network model.

[0087] According to the correlation between various parameters of the target data and the insurance business demand data, the weight values of various parameters of the target data are set, and the weight values of the parameters with higher correlation are set to be greater than the weight values of the parameters with lower correlation. The weight values of various parameters of the above target data are added to the neural network model algorithm.

[0088] For example, the current configuration information includes three data items: age, gender, and years of work experience. According to the business information of previous transactions, age has the highest weight in the medical insurance demand information. Therefore, when constructing the neural network model algorithm, the weight of the age parameter is set to the highest.

[0089] A neural network model is established and trained by the above method to obtain a trained neural network model, and the collected historical data is input into the trained neural network model to output the target data required by the user.

[0090] After sending the target data, the following steps are included:

[0091] Obtain the user's judgment result on the first collected data, and if the judgment result is negative, re-execute the collection task.

[0092] The above target data is sent to the user via email. The user determines whether the target data is correct data based on the business demand information. If the target data is incorrect, the user sends an instruction to re-execute the collection task. After receiving the instruction, the system re-executes the collection task.

[0093] Optionally, a valid database is obtained, the valid database is input into a neural network model of the RPA robot, and the neural network model is self-learned and trained to update the parameters of the neural network model;

[0094] The effective database includes data that users use the target database to conduct business and can facilitate the transaction of insurance business.

[0095] In the present invention, the user carries out insurance business according to the received target database. Some data in the target database can facilitate insurance business transactions, while other data cannot facilitate insurance business transactions. The data that can facilitate insurance business transactions are valid data. All data that can facilitate insurance business transactions are classified into one category to form a valid database. After obtaining the valid database, the neural network model is self-learned and trained again to update the parameters of the neural network model so that the output result of the neural network model is closer to the valid data.

[0096] The insurance business data collection and analysis method according to the embodiment of the present invention has the following advantages:

[0097] (1) The present invention does not require a large amount of manual intervention to collect and analyze insurance business data. It only requires the user to manually input the data requirements of the insurance business, and then it can automatically generate data collection tasks, obtain historical collection data, and send the historical collection data to the RPA robot for analysis to obtain target data. When the user manually inputs incomplete configuration information, two data collection templates are recommended, one is a template generated based on the current configuration information, and the other is a historical template that is most similar to the current configuration information, to prevent incomplete configuration information due to user negligence, which affects the accuracy of data collection.

[0098] (2) The present invention analyzes the collected data through a BP neural network model. The BP neural network can perform self-learning, continuously correct the algorithm, and optimize the analysis results to make the target data more accurate. The analyzed target data is sent to the user via email. The user determines whether the target data is correct. If not, an instruction to re-execute the collection task is sent to re-execute the collection task. The present invention collects and analyzes data through the above method, which can effectively improve the efficiency of data analysis and solve the problem that the timeliness of data cannot meet business needs due to insufficient manpower.

[0099] Regarding the insurance business data collection and analysis method in the above embodiment, Figure 3 The structural block diagram of the insurance business data collection and analysis device provided by the second embodiment of the present invention is shown. The above data processing device is applied to a computer device, and the corresponding computer device is connected to the server through the Internet, and is connected to the insurance business information database on the server side through a preset application programming interface (Application Programming Interface, API), and the first collection data is obtained through the collection task. For the convenience of explanation, only the part related to the embodiment of the present invention is shown.

[0100] See also Figure 3 , the insurance business data collection and analysis device includes:

[0101] A template generation module 31, which is used to obtain the current configuration information of the insurance business data collection requirements and generate a first recommended collection requirements template according to the current configuration information.

[0102] A template recommendation module 32, which is used to determine whether the current configuration information is complete. When it is determined that the current configuration information is incomplete, it traverses the template database, calculates the similarity between the configuration information of each historical collection requirements template in the template database and the current configuration information, and uses the historical collection requirements template with the highest similarity as the second recommended collection requirements template.

[0103] A template determination module 33, which is used to push the first recommended collection requirements template and the second recommended collection requirements template to the user for selection, obtain the user's selection result, and determine the first recommended collection requirements template or the second recommended collection requirements template as the final collection requirements template according to the user's selection result.

[0104] A data collection module 34, which is used to generate a collection task according to the final collection requirements template, execute the collection task, and obtain first collection data.

[0105] A data processing module 35, which is used to, if the first collection data meets the preset conditions, send the first collection data to an RPA robot, and use the RPA robot to analyze the first collection data to obtain target data.

[0106] Optionally, the above template recommendation module 32 includes:

[0107] A configuration information integrity judgment unit, which is used to obtain the parameter values of the current configuration information, determine whether the parameter values of the current configuration information are valid data. If the parameter values of the current configuration information are all valid data, it is determined that the current configuration information is complete.

[0108] If there are invalid data among the parameter values of the current configuration information, or there are missing items among the parameter values of the current configuration information, it is determined that the current configuration information is incomplete.

[0109] Optionally, the above template recommendation module 32 further includes:

[0110] A configuration information similarity comparison unit, which is used to obtain the historical configuration information of each historical collection requirements template, and obtain the parameter values of the historical configuration information.

[0111] Obtain the current configuration information, obtain the parameter values of the current configuration information, compare the parameter values of the historical configuration information with the parameter values of the current configuration information, and use the historical collection requirements template corresponding to the configuration information with the largest number of identical parameter values as the second recommended collection requirements template for recommendation.

[0112] A historical collection requirement template traversal unit is used to obtain the authentication information of the current user, connect to the historical collection requirement template database corresponding to the current user, and sequentially traverse the historical collection requirement templates in the historical collection requirement template database according to the configuration information filled in by the current user.

[0113] Optionally, the above data collection module 34 further includes:

[0114] A collection task secondary generation unit is used to, during the execution of the collection task, when the user's requirements need to be adjusted, the execution of the collection task can be paused at any time, and the data collected before pausing the execution of the collection task is generated into first temporary collection data. According to the adjusted collection requirement template of the user, a collection task is generated again. When generating the collection task again, only the parameter items adjusted by the user are updated, and the parameter items not adjusted by the user are not updated.

[0115] Optionally, the above data processing module 35 includes:

[0116] A first data size comparison unit is used to obtain a set data threshold, compare the size of the first collection data with the set data threshold. If the size of the first collection data is greater than the set data threshold, the first collection data is sent to the RPA robot, and the RPA robot is used to analyze the first collection data to obtain the target data.

[0117] A second data size comparison unit is used to obtain a set data threshold, compare the size of the first collection data with the set data threshold. If the size of the first collection data is less than or equal to the set data threshold, the first collection data is not analyzed and is directly sent.

[0118] A data analysis unit is used to analyze the first collection data through the neural network model built in the RPA robot to obtain the target data.

[0119] A training sample establishment unit is used to obtain training samples. The training samples include: the historical collection data obtained after the execution of the collection tasks of each historical collection requirement template, and set the labels of each historical collection data. The labels of each historical collection data are determined according to the data that meets the requirements of the target data in each historical collection data;

[0120] It should be noted that the information interaction, execution process, etc. between the above modules, due to being based on the same concept as the method embodiment of the present invention, for its specific functions and the technical effects brought, reference can be specifically made to the method embodiment part, and details are not described herein again.

[0121] Figure 4 This is a schematic structural diagram of a computer device provided in Embodiment 4 of the present invention. As Figure 4As shown, the computer device of this embodiment includes: at least one processor ( Figure 4 only one is shown), a memory, and a computer program stored in the memory and executable on at least one processor. When the processor executes the computer program, it implements the steps in any of the above-described embodiments of the method for collecting and analyzing insurance business data.

[0122] The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that Figure 4 this is merely an example of a computer device and does not constitute a limitation on the computer device. The computer device may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include a network interface, a display screen, and an input device, etc.

[0123] The so-called processor may be a CPU, and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0124] The memory includes a readable storage medium, an internal memory, etc. Among them, the internal memory may be the memory of the computer device, and the internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be the hard disk of the computer device, and in some other embodiments, it may also be an external storage device of the computer device. For example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device. Further, the memory may also include both the internal storage unit of the computer device and the external storage device. The memory is used to store the operating system, application programs, boot loaders, data, and other programs, such as the program code of the computer program. The memory may also be used to temporarily store data that has been output or will be output.

[0125] Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0126] Each functional unit and module in the embodiments can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0127] For the specific working process of the units and modules in the above device, reference can be made to the corresponding process in the foregoing method embodiments, which will not be elaborated here. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above method embodiments of the present invention, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented.

[0128] Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0129] To implement all or part of the processes in the above method embodiments of the present invention, it can also be completed by a computer program product. When the computer program product runs on a computer device, it enables the computer device to execute the steps in the above method embodiments.

[0130] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0131] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0132] In the embodiments provided by the present invention, it should be understood that the disclosed device / computer equipment and method can be implemented in other ways. For example, the device / computer equipment embodiments described above are only illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.

[0133] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0134] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. An insurance business data collection and analysis method, characterized in that, The method includes: Obtain the current configuration information of the insurance business data collection requirements, and generate a first recommended collection requirements template according to the current configuration information; Judge whether the current configuration information is complete. When it is determined that the current configuration information is incomplete, traverse the template database, compare the similarity between the configuration information of each historical collection requirements template in the template database and the current configuration information, and use the historical collection requirements template with the largest similarity as the second recommended collection requirements template; Push the first recommended collection requirements template and the second recommended collection requirements template to the user for selection, obtain the user's selection result, and determine the first recommended collection requirements template or the second recommended collection requirements template as the final collection requirements template according to the user's selection result; Generate a collection task according to the final collection requirements template, execute the collection task, and obtain the first collection data; If the first collection data meets the preset conditions, send the first collection data to the RPA robot, and use the RPA robot to analyze the first collection data to obtain the target data; The specific method for obtaining the second recommended collection requirements template includes: Obtain the historical configuration information of each historical collection requirements template, and obtain the parameter values of each item of the historical configuration information; Obtain the current configuration information, obtain the parameter values of each item of the current configuration information, compare the parameter values of each item of the historical configuration information with the parameter values of each item of the current configuration information, and determine the historical collection requirements template corresponding to the configuration information with the largest number of identical parameter values as the historical collection requirements template with the highest similarity, and recommend it as the second recommended collection requirements template; The current configuration information is the configuration information of the current collection requirements template filled in by the current user; the historical configuration information of each historical collection requirements template is the configuration information of each historical collection requirements template corresponding to the current user.

2. The insurance business data collection and analysis method according to claim 1, wherein If the first collection data meets the preset conditions, sending the first collection data to the RPA robot and using the RPA robot to analyze the first collection data to obtain the target data includes: Obtain the set data threshold, compare the size of the first collection data with the set data threshold. If the size of the first collection data is greater than the set data threshold, send the first collection data to the RPA robot, and use the RPA robot to analyze the first collection data to obtain the target data.

3. The insurance business data collection and analysis method according to claim 2, characterized in that, Using the RPA robot to analyze the first collection data to obtain the target data includes: Analyze the first collection data through the neural network model built in the RPA robot to obtain the target data. The training process of the neural network model is as follows: Obtain training samples, where the training samples include: the historical collection data obtained after the execution of the collection tasks of each historical collection requirements template, set the labels of each historical collection data, and the labels of each historical collection data are determined according to the data that meets the requirements of the target data in each historical collection data; The neural network model is trained, and the loss function of the neural network model during the training process adopts a cross entropy loss function.

4. The insurance business data collection and analysis method according to claim 1, wherein Analyzing the first collected data by using the RPA robot to obtain target data includes: Acquire a valid database, input the valid database into the neural network model of the RPA robot, and perform self-learning training on the neural network model to update the parameters of the neural network model; The valid data in the valid database is data that users use the target data to conduct business and facilitate the transaction of insurance business.

5. The insurance business data collection and analysis method according to claim 1, characterized in that Generating a collection task according to the final collection requirement template, executing the collection task, and obtaining the first collection data includes: If the user needs to be adjusted during the execution of the collection task, the collection task can be suspended at any time, and the data collected before the collection task is suspended is used to generate the first temporary collection data; The collection task is generated again according to the collection requirement template adjusted by the user. When the collection task is generated again, only the parameter items adjusted by the user are updated, and the parameter items not adjusted by the user are not updated.

6. The insurance business data collection and analysis method according to claim 1, characterized in that, When it is determined that the current configuration information is incomplete, traversing the template database includes: The authentication information of the current user is obtained, and a historical collection requirement template database corresponding to the current user is connected. According to the configuration information filled in by the current user, the historical collection requirement templates in the historical collection requirement template database are traversed in sequence.

7. An insurance business data collection and analysis device, characterized in that, The device comprises: A template generation module, used to obtain current configuration information of insurance business data collection requirements, and generate a first recommended collection requirement template according to the current configuration information; A template recommendation module, used to determine whether the current configuration information is complete. When it is determined that the current configuration information is incomplete, the template database is traversed to compare the similarity between the configuration information of each historical collection requirement template in the template database and the current configuration information, and the historical collection requirement template with the greatest similarity is used as the second recommended collection requirement template; a template determination module, configured to push the first recommended acquisition requirement template and the second recommended acquisition requirement template to a user for selection, obtain a selection result of the user, and determine the first recommended acquisition requirement template or the second recommended acquisition requirement template as a final acquisition requirement template according to the selection result of the user; A data collection module, used to generate a collection task according to the final collection requirement template, execute the collection task, and obtain first collection data; a data processing module, configured to send the first collected data to the RPA robot if the first collected data meets a preset condition, and use the RPA robot to analyze the first collected data to obtain target data; The template recommendation module is also used to: Obtaining historical configuration information of each historical collection requirement template, and obtaining various parameter values of the historical configuration information; Obtain the current configuration information, obtain the parameter values of the current configuration information, compare the parameter values of the historical configuration information with the parameter values of the current configuration information, and determine the historical collection requirement template corresponding to the configuration information with the largest number of identical parameter values as the historical collection requirement template with the highest similarity, and recommend it as the second recommended collection requirement template; The current configuration information is the configuration information of the current collection requirement template filled in by the current user; the historical configuration information of each historical collection requirement template is the configuration information of each historical collection requirement template corresponding to the current user.

8. A computer device, characterized in that, The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the insurance business data collection and analysis method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the insurance business data collection and analysis method according to any one of claims 1 to 6.

Images