Data quantification processing method and device, electronic equipment and storage medium
By classifying and statistically processing the user data of insurance business, the indicators of key operation nodes are automatically generated, and the processing difficulties caused by large amounts of data are solved, the accuracy and efficiency of data processing are improved, and the business can quickly adjust its operation strategy.
Patent Information
- Application Number
- CN202510108828.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-23
- Publication Date
- 2025-05-06
AI Technical Summary
The amount of data for insurance business users is large, and it is difficult to process and analyze it quickly and accurately, resulting in errors in operational strategies. How to improve the accuracy and efficiency of data processing has become an urgent problem.
By obtaining business data, classifying and processing statistics, user data is automatically efficiently classified, and the indicators of key nodes of operation are output based on business attributes, and key data output that fits business operations is achieved.
It improves the accuracy and efficiency of data quantitative processing, helps the business quickly adjust its operational strategy, and improves its ability to predict operational data in the next week.
Smart Images
Figure CN119941414A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of data quantization processing, and in particular to a data quantization processing method, device, electronic device and storage medium. Background Art
[0002] The total amount of insurance business user data exceeds 300 million, and the number of operational users increases. The manual processing of relevant business data and profit statistics through documents is slow and prone to errors. In order to enable the business to adjust its operation strategy faster and plan the operation plan for the next week, an automatic statistical prediction system is needed to calculate and predict the operational data for the next week based on the 300 million users, operation data and profit situation.
[0003] Half of the data output needs to be manually achieved through office software such as wps. The large amount of data will cause the software to crash and the processing speed to be slow. Errors may occur during the manual processing and pasting process, leading to errors in operational strategies. How to improve the accuracy and efficiency of data processing is an issue that needs to be solved urgently. Summary of the invention
[0004] The purpose of some embodiments of the present application is to provide a data quantification processing method, device, electronic device and storage medium. Through the technical scheme of the embodiments of the present application, business data is obtained; the business data is classified to obtain business operation data and transaction index data corresponding to the business data, and statistical processing is performed on the business operation data and the transaction index data respectively to obtain statistical results corresponding to the business data. The user-related operation data and profit data are generated by the telemarketing platform, and indicators of key operation nodes are generated according to business attributes, and key data that fits the business operation is generated. The user data is automatically and efficiently classified, which facilitates the rapid operation of users in line with the business indicators, thereby improving the accuracy and efficiency of data quantification processing.
[0005] In a first aspect, some embodiments of the present application provide a data quantization processing method, including:
[0006] Get business data;
[0007] Classifying the business data to obtain business operation data and transaction index data corresponding to the business data;
[0008] Statistical processing is performed on the business operation data and the transaction index data respectively to obtain statistical results corresponding to the business data.
[0009] Some embodiments of the present application use the user-related operational data and profit data generated by the telemarketing platform to generate indicators of key operational nodes according to business attributes, generate key data that fits business operations, and automatically and efficiently classify user data, so as to facilitate rapid operation of users in line with business indicators and improve the accuracy and efficiency of data quantification processing.
[0010] Optionally, the business operation data includes at least data coverage, connection rate, transfer rate to manual agent and connection submission rate.
[0011] Optionally, the transaction index data at least includes a connection transaction rate, a connection upgrade rate and a connection insurance rate.
[0012] Optionally, the business operation data and the transaction index data are statistically processed respectively to obtain statistical results corresponding to the business data, including: determining the profit results and labor expenditure data within a preset operation cycle based on the data coverage rate, the connection rate, the transfer rate to manual seats, the connection submission rate, the connection transaction rate, the connection upgrade rate and the connection insurance addition rate.
[0013] In some embodiments of the present application, relevant users are classified according to relevant indicators, and the supported labor and output profits are calculated based on the data volume corresponding to each classified user and the relevant connection rate and transfer rate, and the daily operations are arranged evenly in one operation cycle.
[0014] In a second aspect, some embodiments of the present application provide a data quantization processing device, including:
[0015] Acquisition module, used to acquire business data;
[0016] A classification module, used to classify the business data to obtain business operation data and transaction index data corresponding to the business data;
[0017] The statistical module is used to perform statistical processing on the business operation data and the transaction index data respectively to obtain statistical results corresponding to the business data.
[0018] Some embodiments of the present application use the user-related operational data and profit data generated by the telemarketing platform to generate indicators of key operational nodes according to business attributes, generate key data that fits business operations, and automatically and efficiently classify user data, so as to facilitate rapid operation of users in line with business indicators and improve the accuracy and efficiency of data quantification processing.
[0019] Optionally, the business operation data includes at least data coverage, connection rate, transfer rate to manual agent and connection submission rate.
[0020] Optionally, the transaction index data at least includes a connection transaction rate, a connection upgrade rate and a connection insurance rate.
[0021] Optionally, the statistics module is used to:
[0022] The profit result and labor expenditure data within a preset operation cycle are determined based on the data coverage rate, the connection rate, the transfer rate to manual seats, the connection submission rate, the connection transaction rate, the connection upgrade rate and the connection insurance addition rate.
[0023] In some embodiments of the present application, relevant users are classified according to relevant indicators, and the supported labor and output profits are calculated based on the data volume corresponding to each classified user and the relevant connection rate and transfer rate, and the daily operations are arranged evenly in one operation cycle.
[0024] In a third aspect, some embodiments of the present application provide an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the data quantization processing method as described in any embodiment of the first aspect can be implemented.
[0025] In a fourth aspect, some embodiments of the present application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can implement the data quantization processing method as described in any embodiment of the first aspect.
[0026] In a fifth aspect, some embodiments of the present application provide a computer program product, wherein the computer program product includes a computer program, wherein when the computer program is executed by a processor, it can implement the data quantization processing method as described in any embodiment of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] In order to more clearly illustrate the technical solutions of some embodiments of the present application, the drawings required for use in some embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0028] Figure 1 A flowchart of a data quantization processing method provided in an embodiment of the present application;
[0029] Figure 2 A flowchart of another data quantization processing method provided in an embodiment of the present application;
[0030] Figure 3A schematic diagram of the structure of a data quantization processing device provided in an embodiment of the present application;
[0031] Figure 4 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0032] The technical solutions in some embodiments of the present application will be described below in conjunction with the drawings in some embodiments of the present application.
[0033] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0034] The total amount of insurance business user data exceeds 300 million, and the number of operational users increases. The manual processing of relevant business data and profit statistics through documents is slow and prone to errors. In order to enable the business to adjust its operation strategy faster and plan the operation plan for the next week, an automatic statistical prediction system is needed to calculate and predict the operational data for the next week based on the 300 million users, operation data and profit situation. Half of the data output needs to be achieved manually through office software such as wps. Large amounts of data can cause software crashes and slow processing speeds. Errors may occur during manual processing and pasting, leading to operational strategy errors. How to improve the accuracy and efficiency of data processing is a problem that needs to be solved urgently. In view of this, some embodiments of the present application provide a data quantification processing method, which includes acquiring business data; classifying the business data to obtain business operation data and transaction index data corresponding to the business data, performing statistical processing on the business operation data and transaction index data respectively to obtain statistical results corresponding to the business data, and generating user-related operation data and profit data through the telemarketing platform, generating indicators of key operation nodes according to business attributes, generating key data that fits business operations, and automatically and efficiently classifying user data to facilitate business-fitting indicators to quickly operate users, thereby improving the accuracy and efficiency of data quantification processing.
[0035] like Figure 1 As shown, an embodiment of the present application provides a data quantization processing method, the method comprising:
[0036] S101, obtaining business data;
[0037] Specifically, the terminal device can obtain business data from a pre-stored database, can be downloaded from the network, or can be obtained from other devices. The business data can be insurance industry data. For example, the sources of insurance industry data mainly include:
[0038] 1. Customer information: The customer's personal information, contact information, occupational status, etc. are the basic information for insurance.
[0039] 2. Policy information: including the insured amount, premium, policy type, insurance period, etc., which are the specific details of the insurance contract.
[0040] 3. Claim information: including the accident or loss of the insured, claim amount and claim time, etc., which is the basis for insurance claims;
[0041] 4. Business data: including insurance product sales, premium income, fees and commission expenses, etc., which reflects the operating conditions of the insurance company.
[0042] S102, classifying the business data to obtain business operation data and transaction index data corresponding to the business data;
[0043] Specifically, the terminal device can classify the business data with a pre-trained classification model to obtain the business operation data and transaction index data corresponding to the business data. The business operation data at least includes data coverage, connection rate, transfer rate to manual agent and connection submission rate, and the transaction index data at least includes connection transaction rate, connection upgrade rate and connection insurance rate. Among them, classification models are usually used for tasks whose output variables are categorical or discrete values, for example, judging whether an email is spam or non-spam, or predicting whether a patient has a certain disease. During the training process, the classification model will learn from the labeled training data how to judge which category a sample belongs to, and then make predictions based on the learned knowledge when facing new data.
[0044] The classification module can adopt the following network model, which is not specifically limited in this application:
[0045] For example, 1. Logistic regression:
[0046] Logistic regression is a classic binary classification model that is suitable for scenarios where data is linearly separable. Its core idea is to map samples to a real number range through a linear function and map them to between 0 and 1 through a sigmoid function, thereby obtaining the probability that the sample belongs to category 1. Logistic regression model parameters can be optimized using methods such as gradient descent. Parameter estimation is fast and easy and is routinely applied. The prediction results are highly interpretable.
[0047] 2. Decision Tree
[0048] Decision tree is a classification model based on tree structure, which can handle both discrete and continuous features. Its core idea is to continuously divide data into different subsets by selecting the optimal features and partitioning points until a certain stopping condition is reached. The decision tree establishment process can use algorithms such as ID3, C4.5, and CART. Decision trees are easy to explain and understand, and can handle missing values. In addition, decision trees can also handle nonlinear separable problems.
[0049] 3. Support Vector Machine
[0050] Support vector machine is a classification model that can handle linearly separable and nonlinearly separable data. Its core idea is to divide samples into two categories through a hyperplane and maximize the distance of the samples closest to the hyperplane. The parameters of the support vector machine can be optimized using methods such as SMO. The support vector machine can handle high-dimensional data and nonlinear data and has good generalization performance.
[0051] 4. Random Forest
[0052] Random forest is an ensemble learning algorithm based on decision trees that can handle high-dimensional and nonlinear data. Its core idea is to reduce overfitting by building multiple decision trees, and finally obtain classification results by voting or averaging. Random forest can handle large-scale and high-dimensional data and has good generalization performance.
[0053] 5. AdaBoost
[0054] AdaBoost is an ensemble learning algorithm based on weighted classifiers. Its core idea is to continuously adjust the weights of samples so that each weak classifier can focus on misclassified samples, thereby building a classifier with higher accuracy. AdaBoost has good generalization performance and is relatively robust to outliers.
[0055] 6. Perceptron
[0056] The perceptron is a simple linear classification model that is suitable for linearly separable data. Its core idea is to find an optimal hyperplane by continuously adjusting the weights to divide the data into two categories.
[0057] Advantages: The perceptron has a fast convergence speed and is suitable for large-scale data sets.
[0058] 7. K Nearest Neighbors
[0059] K-nearest neighbor is a non-parametric classification model based on distance measurement, which can handle continuous and discrete features. Its core idea is to calculate the distance between the sample to be classified and different samples in the training set, and select K nearest samples to determine the category of the sample to be classified. K-nearest neighbor can handle nonlinear problems and noisy data, and has good generalization performance.
[0060] 8. Naive Bayes
[0061] Naive Bayes is a classification model based on probability statistics, which is suitable for discrete data. Its core idea is to estimate the prior probability and conditional probability based on the training data, and then use Bayes' theorem to calculate the posterior probability to obtain the final classification result. Naive Bayes is simple to calculate, requires a small amount of training data, and has good generalization performance.
[0062] S103: Perform statistical processing on the business operation data and the transaction index data respectively to obtain statistical results corresponding to the business data.
[0063] Specifically, the terminal device performs statistical processing based on the data coverage rate, connection rate, transfer rate to manual seats and connection submission rate in the service operation data, as well as the connection transaction rate, connection upgrade rate and connection insurance rate in the transaction indicator data, to obtain statistical results corresponding to the business data.
[0064] Some embodiments of the present application use the user-related operational data and profit data generated by the telemarketing platform to generate indicators of key operational nodes according to business attributes, generate key data that fits business operations, and automatically and efficiently classify user data, so as to facilitate rapid operation of users in line with business indicators and improve the accuracy and efficiency of data quantification processing.
[0065] Another embodiment of the present application further supplements the data quantization processing method provided in the above embodiment.
[0066] like Figure 2 As shown, optionally, the business operation data includes at least data coverage, connection rate, transfer rate to manual agent and connection submission rate.
[0067] Optionally, the transaction index data includes at least a connection transaction rate, a connection upgrade rate and a connection insurance rate.
[0068] Optionally, statistical processing is performed on the business operation data and transaction index data respectively to obtain statistical results corresponding to the business data, including: determining the profit results and labor expenditure data within a preset operation cycle based on data coverage, connection rate, transfer rate to manual agent, connection submission rate, connection transaction rate, connection upgrade rate and connection insurance addition rate.
[0069] In some embodiments of the present application, relevant users are classified according to relevant indicators, and the supported labor and output profits are calculated based on the data volume corresponding to each classified user and the relevant connection rate and transfer rate, and the daily operations are arranged evenly in one operation cycle.
[0070] Specifically, the terminal device integrates relevant business data from the business database into the data warehouse. Java develops analysis programs and the data warehouse computing engine to produce business operation indicators and profit indicators based on the business data. Business indicators include data coverage, connection rate, transfer rate to human agent, connection submission rate, etc. Transaction indicators include connection transaction rate, connection upgrade rate, connection plus insurance rate, etc. Relevant users are classified according to relevant indicators, and the supported labor is calculated based on the corresponding data volume of each classified user and the relevant connection rate and transfer rate to human agents, and the profit is produced, which is evenly distributed in an operation cycle to arrange daily operations.
[0071] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.
[0072] Another embodiment of the present application provides a data quantization processing device, which is used to execute the data quantization processing method provided in the above embodiment.
[0073] like Figure 3 , which is a schematic diagram of the structure of a data quantization processing device provided in an embodiment of the present application. The data quantization processing device includes an acquisition module 301, a classification module 302 and a statistical module 303, wherein:
[0074] The acquisition module 301 is used to acquire business data;
[0075] The classification module 302 is used to classify the business data and obtain the business operation data and transaction index data corresponding to the business data;
[0076] The statistical module 303 is used to perform statistical processing on the business operation data and the transaction index data respectively to obtain statistical results corresponding to the business data.
[0077] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0078] Some embodiments of the present application use the user-related operational data and profit data generated by the telemarketing platform to generate indicators of key operational nodes according to business attributes, generate key data that fits business operations, and automatically and efficiently classify user data, so as to facilitate rapid operation of users in line with business indicators and improve the accuracy and efficiency of data quantification processing.
[0079] Another embodiment of the present application further supplements the data quantization processing device provided in the above embodiment.
[0080] Optionally, the business operation data includes at least data coverage, connection rate, transfer rate to human agent and connection submission rate.
[0081] Optionally, the transaction index data includes at least a connection transaction rate, a connection upgrade rate and a connection insurance rate.
[0082] Optionally, a statistics module is used to:
[0083] Determine the profit results and labor expenditure data within the preset operating cycle based on data coverage, connection rate, transfer rate to human agent, connection submission rate, connection transaction rate, connection upgrade rate and connection insurance addition rate.
[0084] In some embodiments of the present application, relevant users are classified according to relevant indicators, and the supported labor and output profits are calculated based on the data volume corresponding to each classified user and the relevant connection rate and transfer rate, and the daily operations are arranged evenly in one operation cycle.
[0085] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0086] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.
[0087] An embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the operation of the method corresponding to any embodiment of the data quantization processing method provided in the above embodiments can be implemented.
[0088] An embodiment of the present application further provides a computer program product, wherein the computer program product includes a computer program, wherein when the computer program is executed by a processor, it can implement the operations of the method corresponding to any embodiment of the data quantization processing method provided in the above embodiments.
[0089] like Figure 4 As shown, some embodiments of the present application provide an electronic device 400, which includes: a memory 410, a processor 420, and a computer program stored in the memory 410 and executable on the processor 420, wherein the processor 420 can implement a method of any embodiment included in the above-mentioned data quantization processing method when reading the program from the memory 410 through a bus 430 and executing the program.
[0090] Processor 420 can process digital signals and can include various computing structures, such as complex instruction set computer structure, reduced instruction set computer structure, or a structure that implements a combination of multiple instruction sets. In some examples, processor 420 can be a microprocessor.
[0091] The memory 410 may be used to store instructions executed by the processor 420 or data related to the execution of instructions. These instructions and / or data may include codes for implementing some or all functions of one or more modules described in the embodiments of the present application. The processor 420 of the disclosed embodiment may be used to execute instructions in the memory 410 to implement the method shown above. The memory 410 includes a dynamic random access memory, a static random access memory, a flash memory, an optical memory, or other memory known to those skilled in the art.
[0092] The above are only embodiments of the present application and are not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.
[0093] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0094] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
Claims
1. A data quantization processing method, characterized in that: The method comprises: Get business data; Classifying the business data to obtain business operation data and transaction index data corresponding to the business data; Statistical processing is performed on the business operation data and the transaction index data respectively to obtain statistical results corresponding to the business data.
2. The data quantization processing method according to claim 1, characterized in that: The business operation data at least includes data coverage rate, connection rate, transfer rate to human agent and connection submission rate.
3. The data quantization processing method according to claim 2, characterized in that: The transaction index data at least includes the connection transaction rate, the connection upgrade rate and the connection insurance rate.
4. The data quantization processing method according to claim 3, characterized in that: The statistical processing of the business operation data and the transaction index data is performed respectively to obtain statistical results corresponding to the business data, including: The profit result and labor expenditure data within a preset operation cycle are determined based on the data coverage rate, the connection rate, the transfer rate to manual seats, the connection submission rate, the connection transaction rate, the connection upgrade rate and the connection insurance addition rate.
5. A data quantization processing device, characterized in that: The device comprises: Acquisition module, used to acquire business data; A classification module, used to classify the business data to obtain business operation data and transaction index data corresponding to the business data; The statistical module is used to perform statistical processing on the business operation data and the transaction index data respectively to obtain statistical results corresponding to the business data.
6. The data quantization processing device according to claim 5, characterized in that: The business operation data at least includes data coverage rate, connection rate, transfer rate to human agent and connection submission rate.
7. The data quantization processing device according to claim 6, characterized in that: The transaction index data at least includes the connection transaction rate, the connection upgrade rate and the connection insurance rate.
8. The data quantization processing device according to claim 7, characterized in that: The statistics module is used to: The profit result and labor expenditure data within a preset operation cycle are determined based on the data coverage rate, the connection rate, the transfer rate to manual seats, the connection submission rate, the connection transaction rate, the connection upgrade rate and the connection insurance addition rate.
9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor can implement the data quantization processing method described in any one of claims 1 to 4 when executing the program.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the program, when executed by a processor, can implement the data quantization processing method described in any one of claims 1 to 4.