CN117291731A

CN117291731A - Receipt generation method and related equipment based on commission calculation and evaluation

Info

Publication number: CN117291731A
Application number: CN202311196127.0A
Authority: CN
Inventors: 侯倩
Original assignee: Ping An Health Insurance Company of China Ltd
Current assignee: Ping An Health Insurance Company of China Ltd
Priority date: 2023-09-15
Filing date: 2023-09-15
Publication date: 2023-12-26

Abstract

The application belongs to the field of artificial intelligence and financial science and technology, and relates to a receipt generation method and related equipment based on commission calculation and evaluation, wherein the method comprises the steps of obtaining a target policy, obtaining scene characteristics of the policy according to the target policy, and carrying out standardized processing on the scene characteristics of the policy to obtain standard scene characteristics; inputting the standard scene characteristics into the trained SVM calculation evaluation model for classification evaluation, and outputting calculation classification results; inputting the target policy into the handling fee calculation model to calculate the handling fee when the calculation classification result is that the handling fee needs to be calculated, so as to obtain the handling fee; and generating a charge bill based on the procedure charge and the target policy, and sending the charge bill to a service terminal corresponding to the target policy. In addition, the present application relates to blockchain technology, and target policies may be stored in the blockchain. The method and the device can improve judging accuracy and efficiency, reduce redundant steps, improve computing efficiency, reduce computing error rate, reduce code redundancy and improve system performance.

Description

Receipt generation method and related equipment based on commission calculation and evaluation

Technical Field

The application relates to the technical field of artificial intelligence and financial science and technology, in particular to a receipt generation method and related equipment based on commission calculation and evaluation.

Background

With the increasing satisfaction of the material conditions of people, the demands of people for safety are increasing, and more people choose to purchase different insurance products so as to avoid the loss caused by accidents. With the rapid development of the insurance finance field, especially in the current internet economic age with rapid development, in order to meet the demands of people on insurance products, the more various the insurance product forms are, the more complex the calculation rule of the commission is.

The cost is seriously affected by the fact that the calculation is correct or not as a branch item of an insurance company. In the traditional method, each insurance product or insurance index is set with corresponding commission calculation rules for calculation. If an insurance product or an insurance scene is newly added, a corresponding commission calculation rule of the insurance product or the insurance scene needs to be additionally newly added. In this way, the number of calculation rules for configuration increases due to the variety of insurance products or insurance scenes, which results in code redundancy and affects system performance. In addition, the newly added insurance products or insurance scenes also need to be manually adjusted, the process is repeated and tedious, the efficiency is low, and errors are easy to occur.

Disclosure of Invention

The embodiment of the application aims to provide a receipt generation method and related equipment based on commission calculation and evaluation, so as to solve the technical problems that the types of insurance products in related technologies are increased, commission rules are increased, code redundancy is caused, and system performance is affected.

In order to solve the above technical problems, the embodiment of the present application provides a bill generating method based on handling fee calculation and evaluation, which adopts the following technical scheme:

acquiring a target policy, acquiring policy scene characteristics according to the target policy, and carrying out standardized processing on the policy scene characteristics to acquire standard scene characteristics;

inputting the standard scene characteristics into a trained SVM calculation evaluation model for classification evaluation, and outputting a calculation classification result;

inputting the target policy into the commission fee calculation model to calculate commission fee when the calculation classification result is that commission fee is required to be calculated, so as to obtain commission fee;

and generating a charge bill based on the procedure charge and the target policy, and sending the charge bill to a service terminal corresponding to the target policy.

Further, before the step of inputting the standard scene features into the trained SVM calculation evaluation model for evaluation, the method further comprises:

Acquiring all historical insurance policies, and establishing a sample set according to scene characteristic parameters and cost calculation identifiers of each historical insurance policy, wherein the cost calculation identifiers are used as labels of the sample set;

dividing the sample set into a training set and a testing set according to a preset proportion;

constructing an SVM classifier, and inputting the training set into the SVM classifier to obtain a calculation prediction result;

adjusting classification parameters of the SVM classifier based on the calculation prediction result and the cost calculation mark, and continuing to perform iterative training until convergence to obtain a trained SVM classifier;

inputting the test set into the trained SVM classifier for verification to obtain classification accuracy;

and outputting the trained SVM classifier as an SVM calculation evaluation model when the classification precision is greater than or equal to a preset threshold value.

Further, the step of constructing an SVM classifier includes:

constructing an SVM classification function and a constraint condition of the SVM classification function;

optimizing the SVM classification function through the constraint condition to obtain a Lagrangian function;

constructing an SVM kernel function, and optimizing the Lagrangian function through the SVM kernel function to obtain an SVM target classification function and a target constraint condition;

And obtaining an SVM classifier based on the SVM target classification function and the target constraint condition.

Further, the step of inputting the target policy into the commission fee calculation model to calculate commission fee, and obtaining commission fee includes:

inputting the target policy into the commission fee calculation model, and calling a fee information input table corresponding to the commission fee calculation model;

extracting a cost field in the cost information input table, and matching the cost field with the target policy according to the cost field to obtain cost data;

inputting the expense data into the corresponding expense information input table;

and inputting the fee information input table input with the fee data into the commission fee calculation model to calculate, thereby obtaining commission fee.

Further, after the step of inputting the target policy into the commission fee calculation model to calculate commission fee, the method further includes:

acquiring a policy identifier of the target policy, and acquiring standard expense according to the policy identifier;

comparing and verifying the procedure cost with the standard cost;

if the comparison is consistent, the verification is passed, and the procedure cost is output;

If the comparison is inconsistent, the verification is not passed, and the procedure cost of the target policy is recalculated.

Further, the step of generating a fee receipt based on the procedure fee and the target policy includes:

acquiring a corresponding bill template according to the bill type of the expense bill;

acquiring field data corresponding to each field in the bill template from the target policy according to the bill template;

and recording the insurance policy expense and the field data to the corresponding position of the bill template to generate an expense bill.

Further, the step of performing standardization processing on the policy scene features to obtain standard scene features includes:

obtaining a standard characteristic value table, wherein the standard characteristic value table is a mapping relation table of the security scene characteristics and characteristic standard values;

and carrying out standardization processing on the policy scene features according to the mapping relation of the standard feature value table to obtain standard scene features.

In order to solve the technical problems, the embodiment of the application also provides a bill generation device based on the handling fee calculation and evaluation, which adopts the following technical scheme:

the acquisition module is used for acquiring a target policy, acquiring the scene characteristics of the policy according to the target policy, and carrying out standardized processing on the scene characteristics of the policy to acquire standard scene characteristics;

The classification module is used for inputting the standard scene characteristics into the trained SVM calculation evaluation model for classification evaluation and outputting calculation classification results;

the calculation module is used for inputting the target policy into the commission fee calculation model to calculate commission fee when the calculation classification result is that commission fee is required to be calculated, so as to obtain commission fee;

and the bill generation module is used for generating a cost bill based on the procedure cost and the target policy and sending the cost bill to a service terminal corresponding to the target policy.

In order to solve the above technical problems, the embodiments of the present application further provide a computer device, which adopts the following technical schemes:

the computer device comprises a memory having stored therein computer readable instructions which when executed by the processor implement the steps of the receipt generation method based on the commission calculation evaluation as described above.

In order to solve the above technical problems, embodiments of the present application further provide a computer readable storage medium, which adopts the following technical solutions:

the computer readable storage medium has stored thereon computer readable instructions which when executed by a processor implement the steps of the document generation method based on a commission calculation evaluation as described above.

Compared with the prior art, the embodiment of the application has the following main beneficial effects:

according to the method, the target policy is obtained, the policy scene characteristics are obtained according to the target policy, the standard scene characteristics are obtained through standardized processing of the policy scene characteristics, the standard scene characteristics which can be identified by the model are obtained through standardized processing of the policy scene characteristics, and the model processing efficiency is improved; the standard scene features are input into the trained SVM calculation evaluation model for classification evaluation, a calculation classification result is output, whether the operation fee calculation is needed or not is judged through the SVM calculation evaluation model, the judgment accuracy and efficiency can be improved, and redundant steps are reduced; when the calculation classification result is that the commission fee needs to be calculated, inputting the target policy into a commission fee calculation model to calculate the commission fee, so as to obtain the commission fee, and automatically calculating the commission fee of the policy through the commission fee calculation model, thereby improving the calculation efficiency, reducing the calculation error rate, reducing the code redundancy, improving the system performance and reducing the labor cost; and generating a fee receipt based on the procedure fee and the target policy, transmitting the fee receipt to a service terminal corresponding to the target policy, and transmitting the generated fee receipt to the corresponding service terminal to improve settlement efficiency and avoid loss to enterprises.

Drawings

For a clearer description of the solution in the present application, a brief description will be given below of the drawings that are needed in the description of the embodiments of the present application, it being obvious that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.

FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;

FIG. 2 is a flow chart of one embodiment of a method of document generation based on a commission calculation evaluation according to the present application;

FIG. 3 is a flow chart of one embodiment of step S202 of FIG. 2;

FIG. 4 is a schematic structural view of one embodiment of a bill generation apparatus based on a commission calculation evaluation according to the present application;

FIG. 5 is a schematic structural diagram of one embodiment of a computer device according to the present application.

Detailed Description

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description and claims of the present application and in the description of the figures above are intended to cover non-exclusive inclusions. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

In order to better understand the technical solutions of the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings.

The application provides a receipt generation method based on commission calculation and evaluation, which relates to artificial intelligence, and can be applied to a system architecture 100 shown in fig. 1, wherein the system architecture 100 can comprise terminal devices 101, 102 and 103, a network 104 and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.

The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.

The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.

It should be noted that, the bill generation method based on the commission fee calculation and evaluation provided in the embodiment of the present application is generally executed by the server/terminal device, and accordingly, the bill generation device based on the commission fee calculation and evaluation is generally disposed in the server/terminal device.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to FIG. 2, a flow chart of one embodiment of a method of document generation based on a commission calculation evaluation according to the present application is shown, comprising the steps of:

Step S201, obtaining a target policy, obtaining the scene characteristics of the policy according to the target policy, and performing standardized processing on the scene characteristics of the policy to obtain standard scene characteristics.

In this embodiment, the target policy may be received through a wired connection or a wireless connection. It should be noted that the wireless connection may include, but is not limited to, 3G/4G connections, wiFi connections, bluetooth connections, wiMAX connections, zigbee connections, UWB (ultra wideband) connections, and other now known or later developed wireless connection means.

The target policy is a policy to be subjected to handling fee calculation, wherein the handling fee is sales channel of the insurance agency as the insurance company, the insurance agency sells the policy, and the insurance company sells sales fee to the agency.

Policy scenario features are scenario factors that affect the calculation of commission, including, but not limited to, product code, product type, scenario code, pay-for-items, security services, whether to give away insurance, year of policy, payment (i.e., payment mode), sales channel, source of business, whether to deduct commission, whether to be an intermediary, whether to be premium exemption, etc.

The process of converting the non-digitized policy scene characteristics into numerical values is standardized processing. By way of example, the scenes include an application, a claim, a underwriting, a value added service, etc., the scene code of the application scene may be set to 1001, the scene code of the claim can be set to 1002, and so on. The policy scene is characterized by whether to give away or not, and can be represented by '1' and '0'.

And acquiring the policy identifier of the target policy, and acquiring all the scene characteristics of the policy corresponding to the target policy according to the policy identifier, wherein the policy identifier is used for uniquely identifying the policy and can be a policy number.

It is emphasized that the target policy may also be stored in a blockchain node in order to further ensure the privacy and security of the target policy.

The blockchain referred to in the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.

Step S202, inputting the standard scene characteristics into the trained SVM calculation evaluation model for classification evaluation, and outputting calculation classification results.

In this embodiment, standard scene features are input into a trained SVM calculation evaluation model, and classified by an SVM classification algorithm to obtain a calculation classification result, where the calculation classification result is that a commission fee needs to be calculated or a commission fee does not need to be calculated.

The SVM is a supervised learning model and is suitable for data classification and regression analysis, the SVM is mapped from low dimension to high dimension through a feature space, and then hyperplane is used for classifying data in the high-order feature space. Before classifying an evaluation model by using SVM calculation, training is needed to improve the accuracy of the model.

In some optional implementations, before the step of inputting the standard scene features into the trained SVM calculation evaluation model for evaluation, the method further includes:

step S301, acquiring all historical insurance policies, and establishing a sample set according to scene characteristic parameters and cost calculation identifiers of each historical insurance policy, wherein the cost calculation identifiers are used as labels of the sample set;

step S302, dividing a sample set into a training set and a test set according to a preset proportion;

step S303, constructing an SVM classifier, and inputting a training set into the SVM classifier to obtain a calculation prediction result;

step S304, adjusting classification parameters of the SVM classifier based on the calculation prediction result and the cost calculation mark, and continuing iterative training until convergence to obtain a trained SVM classifier;

step S305, inputting the test set into a trained SVM classifier for verification to obtain classification accuracy;

And step S306, when the classification precision is greater than or equal to a preset threshold value, outputting the trained SVM classifier as an SVM calculation evaluation model.

And acquiring a characteristic value corresponding to each historical policy as a scene characteristic parameter according to a preset scene factor, acquiring a cost calculation identifier of each historical policy, and forming a sample set from the scene characteristic parameters and the corresponding cost calculation identifiers of all the historical policies.

Dividing the sample set into a training set and a testing set according to a preset proportion, wherein the training set is exemplified: test set = 7:3. The preset proportion can be selected according to actual conditions.

In this embodiment, input: training set t= { (x) ₁ ，y ₁ )，(x ₂ ，y ₂ )，……，(x _n ，y _n ) X, where x _i Feature vector, y composed of scene feature parameters of ith historical policy in training set _i Is x _i Corresponding fee calculation identifier, when y _i When=0, x _i The corresponding policy does not need to calculate the commission fee; when y is _i When=1, x _i The corresponding policy requires calculation of the commission.

And (3) outputting: the maximum separation separates the hyperplane and the classification decision function.

The step of constructing an SVM classifier includes:

constructing a constraint condition of the SVM classification function; optimizing the SVM classification function through constraint conditions to obtain a Lagrangian function; constructing an SVM kernel function, and optimizing a Lagrangian function through the SVM kernel function to obtain an SVM target classification function and a target constraint condition; and obtaining the SVM classifier based on the SVM target classification function and the target constraint condition.

Specifically, the SVM classification function is as follows:

wherein ω represents a normal vector of the hyperplane; c represents punishment parameters, when the value of C is large, punishment on misclassification is increased, and when the value of C is small, punishment on misclassification is reduced; zeta type toy _i Represents the i-th history policy (x) _i ，y _i ) Is a relaxation variable of (a).

The constraint conditions of the objective function are as follows:

wherein x is _i Feature vector, y composed of scene feature parameters of ith historical policy in training set _i Is x _i Corresponding fee calculation identification; phi (x) _i ) Is x _i Mapping to a high-dimensional feature vector; ω represents the normal vector of the hyperplane; b represents the intercept of the hyperplane. Thus, the dividing hyperplane may be determined by the normal vector ω and the intercept b.

The objective of the SVM classification function is to find the appropriate ω and b such that (ω.x _i The predictions given for +b) are suitable for most samples.

To solve the constrained optimal problem, the classification problem of the SVM is converted into a Lagrangian function, so that the solving of the classification hyperplane becomes the solving of the Lagrangian operator alpha _i Offset b problem.

And merging constraint conditions into the SVM classification function to obtain a Lagrangian function, wherein the Lagrangian function is specifically as follows:

wherein alpha is _i The lagrangian multiplier for the i-th history policy.

In order to map an original input sample to a high-dimensional feature space, convert a nonlinear problem into a linearly separable problem, so that the sample is correctly classified, a Gaussian kernel function (SVM kernel function) is introduced, and the formula is as follows:

wherein k (x _i ,x _j ) Represents x _i To x _j Is the euclidean distance of (2); beta represents a trimming variable, lambda represents a distance parameter, and according to the actual setting, when the distance between two samplesWhen the infinity is trended, the Gaussian kernel function is not equal to 0 any more, and partial eigenvalue failure in the sample set can be avoided.

By introducing the Gaussian kernel function into the SVM formula, an SVM target classification function based on the Gaussian kernel can be obtained, and the expression is as follows:

target constraint:

solving through the formula to obtain an optimal separation hyperplane:

wherein sign represents performing a symbolic operation; n represents the total number of samples;an optimal lagrangian multiplier representing the i-th sample point; y is _i Represents x _i Corresponding fee calculation identification; k (x) _i ,x _j ) Represents x _i To x _j Is the euclidean distance of (2); b ^* Representing the optimal hyperplane intercept.

By training the support vector machine model by using the algorithm, the optimal separation hyperplane is found, the feature space is divided into two parts, one part is the fee required to be calculated, and the other part is the fee not required to be calculated, so that the data are classified.

In the embodiment, the scene characteristic parameters and the commission fee of the policy belong to nonlinear mapping, the SVM algorithm is well represented in a nonlinear and high-dimensional characteristic space, and the high-dimensional sample set in the commission fee can be effectively classified based on the SVM classification algorithm, so that whether the commission fee is required to be calculated for the samples is better, and the classification accuracy and efficiency are improved.

In this embodiment, after the SVM classifier is constructed, the training set is input into the SVM classifier to obtain a calculation prediction result, and classification parameters of the SVM classifier are adjusted based on the calculation prediction result and the fee calculation identifier. Specifically, a loss function is calculated based on a calculation prediction result and a cost calculation identifier, and classification parameters of the SVM classifier are adjusted according to the loss function, wherein the classification parameters are a penalty parameter C in the SVM classifier, a gamma parameter in a Gaussian kernel function and a Lagrange multiplier,0≤α _i ≤C。

and continuing training the SVM classifier after adjustment until convergence to obtain the trained SVM classifier to be verified, wherein the condition for meeting the convergence can be that the loss function does not change significantly or the iteration times reach the preset number.

The test set is input into a trained SVM classifier for verification, so that classification accuracy is obtained, and a calculation formula of the classification accuracy is as follows:

Where N is the number of test set samples, y _i ^′ Is the predictive expense calculation identification, y _i Is the actual cost calculation mark; 1 (y) _i ^′ ＝y _i ) The sample count is 1, which indicates that the predicted cost calculation flag is identical to the actual cost calculation flag.

In this embodiment, the classification accuracy is used to evaluate the prediction accuracy of the SVM classifier, and if the classification accuracy is greater than or equal to a preset threshold, it is explained that the prediction accuracy of the model meets the expectations, the SVM classifier to be tested can be used as a final SVM calculation evaluation model; if the classification accuracy is smaller than the preset threshold, the prediction accuracy of the model is not high, the expected model cannot be met, the number of samples is required to be increased, or parameters are modified and retrained to improve the classification accuracy.

Through training and verifying the SVM classifier, the fee calculation identification recognition task can be completed more quickly, the processing efficiency is improved, and meanwhile, the fee calculation identification classification accuracy can be improved under the condition of reducing misjudgment and missed judgment.

In step S203, when the calculation classification result is that the handling fee needs to be calculated, the handling fee is calculated by inputting the target policy into the handling fee calculation model, and the handling fee is obtained.

In this embodiment, after the SVM calculation evaluation model determines that the target policy requires calculation of the commission fee, the target policy is input into the commission fee calculation model, and the commission fee calculation is automatically performed by the commission fee calculation model.

Specifically, inputting the target policy into a commission fee calculation model, and calling a fee information input table corresponding to the commission fee calculation model; extracting a cost field in a cost information input table, and matching with a target policy according to the cost field to obtain cost data; inputting the fee data into a corresponding fee information input table; and inputting the fee information input table with the fee data input into a commission fee calculation model to calculate, thereby obtaining commission fee.

In one specific example, the commission calculation model is sequentially integrated by 12 timing tasks, respectively commission calculation, contract withdrawal and full withdrawal logic processing (contract withdrawal timing tasks), orphan single timing task (withdrawal renewing virtual business person), activity plus commission tasks, total subtotal handling (total subtotal handling fee calculation), fractional subtotal handling (fractional subtotal handling fee calculation), intermediate handling (intermediate handling fee calculation), technical service handling (technical service fee calculation), total subtotal handling finance pushing, fractional subtotal handling finance pushing, and technical service fee pushing finance.

The 12 tasks are required to be executed sequentially, each timing task corresponds to a handling fee calculation, and a corresponding calculation rule is configured, for example, total handling fee, split handling fee, intermediate handling fee and technical service fee are generated according to different sales channels, the types are only different, the calculation formulas are all premium proportion, only one general formula is required to be set, and the calculation is carried out according to the sales channels by taking the respective corresponding proportion; as for the orphan single timing task, special logic is adopted, namely, the fractional proportion is 0.5% as long as the orphan single total to total proportion is 0%; the contract withdrawal timing task is to calculate no commission for the policy refund of hesitation and withdrawal.

And (3) inputting the target policy into a handling fee calculation model, calling a fee information input table corresponding to 12 timing tasks in the handling fee calculation model, extracting a fee field required by calculating the handling fee according to the fee information input table, and matching the fee field with the target policy, for example, the premium field, and matching the premium in the target policy to obtain a specific premium value as fee data.

And (3) inputting the cost data to a position corresponding to the cost information input table, inputting the cost information input table into a commission cost calculation model, sequentially executing cost calculation according to 12 timing tasks, and comprehensively outputting the final commission cost, namely the commission cost of the target policy.

The calculation efficiency can be improved, the calculation error rate can be reduced, the labor cost can be reduced, meanwhile, the operation fee calculation is performed through the operation fee calculation model, the repeated setting of related calculation rules is avoided, the code redundancy is reduced, and the system performance is improved.

And step S204, generating a fee receipt based on the procedure fee and the target policy, and sending the fee receipt to the service terminal corresponding to the target policy.

Specifically, according to the bill type of the expense bill, a corresponding bill template is obtained; acquiring field data corresponding to each field in the bill template from the target policy according to the bill template; and recording the insurance policy expense and the field data to the corresponding position of the bill template to generate an expense bill.

In this embodiment, before the target policy is acquired, a fee calculation request for the target policy is received, where the fee calculation request carries information such as the target policy and a request initiation terminal.

And acquiring a corresponding terminal identifier (namely a request initiating terminal) according to the target policy, wherein the terminal identifier comprises a service terminal interface, a terminal IP address and the like, and sending the expense bill to the corresponding service terminal so as to facilitate the payment of the commission according to the expense bill.

In this embodiment, a document template corresponding to a fee document is pre-configured in the template database. Specifically, extracting a feature field corresponding to each document type, acquiring position information of each feature field, namely a field to be verified, generating a document template corresponding to each document type according to the feature field and the position information corresponding to the feature field, configuring a template number corresponding to the document template, storing the document template in a preset template database based on the template number, wherein the template number has uniqueness, and can be used as index information of the document template in the template database.

The bill template is used for generating the expense bill, so that the bill generation efficiency can be improved, the bill generation flow is simplified, excessive and complicated operations are avoided, and the system performance is improved.

According to the method and the device, the standard scene characteristics which can be identified by the model are obtained through standardized processing of the policy scene characteristics, so that the model processing efficiency is improved; judging whether the operation fee calculation is needed or not through the SVM calculation evaluation model, so that the accuracy and the efficiency of the judgment can be improved, and redundant steps are reduced; the operation fee of the policy is automatically calculated through the operation fee calculation model, so that the calculation efficiency is improved, the calculation error rate is reduced, the labor cost is reduced, meanwhile, the code redundancy is reduced, and the system performance is improved; and the expense bill is generated and sent to the corresponding service terminal, so that the settlement efficiency is improved, and the loss to enterprises is avoided.

In some optional implementations of this embodiment, the step of inputting the target policy into the commission fee calculation model to calculate the commission fee further includes:

acquiring a policy identifier of a target policy, and acquiring standard expense according to the policy identifier;

comparing and verifying the procedure cost with the standard cost;

For example, assuming that the general logic of the standard fee is a proportion of the commission amount=the real fee, after the commission is calculated, the real fee of the target policy and the commission proportion of the corresponding scene are obtained, the corresponding general logic is called to calculate to obtain the standard fee, and the commission fee is compared with the standard fee to obtain the corresponding comparison result.

For example, if the new insurance premium is 100, the intermediate fee of the current insurance policy=100×30% =30, and if the final result output procedure fee is 30, the comparison is consistent, and the verification is passed; if the target policy is the insurance policy, the business rule adopts a special proportion of 0, and if the new policy is taken to 30%, the target policy is considered to be wrong, namely the comparison is inconsistent, and the calculation is needed to be adjusted again.

According to the method and the device, whether the calculated commission is correct or not is automatically checked, so that the cost of manual intervention and repeated processing can be reduced, meanwhile, the accuracy of data is improved, the additional cost caused by data errors and inconsistencies is reduced, and the cost expenditure of enterprises can be reduced.

In some optional implementations, the step of normalizing the policy scene feature to obtain a standard scene feature includes:

obtaining a standard characteristic value table, wherein the standard characteristic value table is a mapping relation table of the characteristics of the policy scene and the characteristic standard values;

and carrying out standardization processing on the security scene features according to the mapping relation of the standard feature value table to obtain standard scene features.

Mapping non-digitized policy scene characteristics and fee calculation identifications into numerical values to realize standardized processing, taking a scene code 1001 as an example, wherein the policy scene characteristics are scene codes, payment items, whether to give away insurance, policy year, whether to sell directly, whether to deduct commission, whether to be intermediaries and whether to be fee exemption, and in a standard characteristic value table, the payment items are represented by 0 or 1 corresponding to receipt and payment identifications, and 1 represents payment and 0 represents payment; the present risk mark is 0 or 1,1 represents present risk, and 0 represents non-present risk; year of policy, 1 means 1 year, 2 means 2 years, and so on; straight pin designation 0 or 1,1 indicating a straight pin, 0 indicating a non-straight pin; deducting a commission flag of 0 or 1,0 indicating deduction of the commission, 1 indicating no deduction of the commission; the intermediary is identified as 0 or 1,0 indicating that it is an intermediary, 1 indicating that it is not an intermediary; the premium exemption mark is 0 or 1,0 indicates that the insurance is not exemption insurance, and 1 indicates that the insurance is exemption insurance.

It should be understood that the feature standard values corresponding to the features of the insurance scene are merely examples, and may be specifically set according to actual situations.

And the standard scene characteristics which can be identified by the model are obtained through standardized processing of the policy scene characteristics, so that the model processing efficiency is improved, and the accuracy of model identification is further ensured.

The subject application is operational with numerous general purpose or special purpose computer system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by computer readable instructions stored in a computer readable storage medium that, when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

With further reference to fig. 4, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a bill generating apparatus based on commission calculation evaluation, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.

As shown in fig. 4, the receipt generation device 400 based on the calculation and evaluation of the commission fee according to the present embodiment includes: an acquisition module 401, a classification module 402, a calculation module 403, and a document generation module 404.

Wherein:

the acquiring module 401 is configured to acquire a target policy, acquire a policy scene feature according to the target policy, and perform standardized processing on the policy scene feature to obtain a standard scene feature;

the classification module 402 is configured to input the standard scene feature into a trained SVM calculation evaluation model for classification evaluation, and output a calculation classification result;

the calculation module 403 is configured to input the target policy into the commission fee calculation model to calculate commission fee when the calculation classification result is that commission fee needs to be calculated, so as to obtain commission fee;

the bill generation module 404 is configured to generate a cost bill based on the procedure cost and the target policy, and send the cost bill to a service terminal corresponding to the target policy.

Based on the receipt generation device 400 based on the commission calculation and evaluation, standard scene characteristics which can be identified by the model are obtained through standardized processing of the security scene characteristics, so that the model processing efficiency is improved; judging whether the operation fee calculation is needed or not through the SVM calculation evaluation model, so that the accuracy and the efficiency of the judgment can be improved, and redundant steps are reduced; the operation fee of the policy is automatically calculated through the operation fee calculation model, so that the calculation efficiency is improved, the calculation error rate is reduced, the labor cost is reduced, meanwhile, the code redundancy is reduced, and the system performance is improved; and the expense bill is generated and sent to the corresponding service terminal, so that the settlement efficiency is improved, and the loss to enterprises is avoided.

In some alternative implementations, the bill generation apparatus 400 based on the commission calculation evaluation further includes a training module including:

the establishing sub-module is used for acquiring all the historical insurance policies, and establishing a sample set according to scene characteristic parameters and cost calculation identifiers of each historical insurance policy, wherein the cost calculation identifiers are used as labels of the sample set;

the training sub-module is used for constructing an SVM classifier, and inputting the training set into the SVM classifier to obtain a calculation prediction result;

the iteration sub-module is used for adjusting the classification parameters of the SVM classifier based on the calculation prediction result and the cost calculation identification, and continuing to carry out iteration training until convergence to obtain a trained SVM classifier;

the verification sub-module is used for inputting the test set into the trained SVM classifier for verification to obtain classification accuracy;

and the output sub-module is used for outputting the trained SVM classifier as an SVM calculation evaluation model when the classification precision is greater than or equal to a preset threshold value.

In some optional implementations of the present embodiment, the training submodule includes a building unit configured to:

The SVM classifier is constructed to realize an SVM classification algorithm, so that a high-dimensional sample set in the commission can be effectively classified, whether the sample is required to be subjected to the commission classification or not can be better facilitated, and the classification accuracy and efficiency are improved.

In the present embodiment, the calculation module 403 includes:

the calling sub-module is used for inputting the target policy into the commission fee calculation model and calling a fee information input table corresponding to the commission fee calculation model;

the matching sub-module is used for extracting a cost field in the cost information input table, and matching the cost field with the target policy to obtain cost data;

the input sub-module is used for inputting the expense data into the corresponding expense information input table;

and the calculation sub-module is used for inputting the fee information input table input with the fee data into the commission fee calculation model to calculate so as to obtain commission fee.

In some alternative implementations, the bill generation apparatus 400 based on the commission calculation evaluation further includes a verification module including:

the expense acquisition sub-module is used for acquiring the policy identifier of the target policy and acquiring standard expense according to the policy identifier;

the verification sub-module is used for comparing and verifying the procedure cost with the standard cost; if the comparison is consistent, the verification is passed, and the procedure cost is output; if the comparison is inconsistent, the verification is not passed, and the procedure cost of the target policy is recalculated.

The method can reduce the cost of manual intervention and repeated processing by automatically checking whether the calculated handling fee is correct or not, improve the accuracy of data, reduce the extra cost caused by data errors and inconsistencies, and reduce the cost expenditure of enterprises.

In some alternative implementations of the present embodiment, the document generation module 404 includes:

The template acquisition sub-module is used for acquiring a corresponding bill template according to the bill type of the expense bill;

the field acquisition sub-module is used for acquiring field data corresponding to each field in the bill template from the target policy according to the bill template;

and the generation sub-module is used for inputting the insurance policy expense and the field data to the corresponding position of the bill template to generate an expense bill.

In some alternative implementations, the acquisition module 401 includes:

the acquisition sub-module is used for acquiring a standard characteristic value table, wherein the standard characteristic value table is a mapping relation table of the characteristics of the policy scene and the characteristic standard values;

and the standardized sub-module is used for carrying out standardized processing on the policy scene features according to the mapping relation of the standard feature value table to obtain standard scene features.

In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 5, fig. 5 is a basic structural block diagram of a computer device according to the present embodiment.

The computer device 5 comprises a memory 51, a processor 52, a network interface 53 which are communicatively connected to each other via a system bus. It should be noted that only the computer device 5 with components 51-53 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculations and/or information processing in accordance with predetermined or stored instructions, the hardware of which includes, but is not limited to, microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASICs), programmable gate arrays (fields-Programmable Gate Array, FPGAs), digital processors (Digital Signal Processor, DSPs), embedded devices, etc.

The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.

The memory 51 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 51 may be an internal storage unit of the computer device 5, such as a hard disk or a memory of the computer device 5. In other embodiments, the memory 51 may also be an external storage device of the computer device 5, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 5. Of course, the memory 51 may also comprise both an internal memory unit of the computer device 5 and an external memory device. In this embodiment, the memory 51 is generally used to store an operating system and various application software installed on the computer device 5, such as computer readable instructions of a bill generation method based on a fee calculation evaluation. Further, the memory 51 may be used to temporarily store various types of data that have been output or are to be output.

The processor 52 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 52 is typically used to control the overall operation of the computer device 5. In this embodiment, the processor 52 is configured to execute computer readable instructions stored in the memory 51 or process data, such as computer readable instructions for executing the bill generation method based on the calculation and evaluation of the commission fee.

The network interface 53 may comprise a wireless network interface or a wired network interface, which network interface 53 is typically used to establish communication connections between the computer device 5 and other electronic devices.

According to the bill generation method based on the handling fee calculation evaluation, the steps of the bill generation method based on the handling fee calculation evaluation in the embodiment are realized when a processor executes computer readable instructions stored in a memory, and standard scene characteristics which can be identified by a model are obtained through standardized processing of the security scene characteristics, so that the model processing efficiency is improved; judging whether the operation fee calculation is needed or not through the SVM calculation evaluation model, so that the accuracy and the efficiency of the judgment can be improved, and redundant steps are reduced; the operation fee of the policy is automatically calculated through the operation fee calculation model, so that the calculation efficiency is improved, the calculation error rate is reduced, the labor cost is reduced, meanwhile, the code redundancy is reduced, and the system performance is improved; and the expense bill is generated and sent to the corresponding service terminal, so that the settlement efficiency is improved, and the loss to enterprises is avoided.

The application also provides another embodiment, namely, a computer readable storage medium is provided, the computer readable storage medium stores computer readable instructions, the computer readable instructions can be executed by at least one processor, so that the at least one processor executes the steps of the bill generation method based on the commission calculation evaluation, and standard scene characteristics which can be identified by a model are obtained through standardized processing of the policy scene characteristics, and the model processing efficiency is improved; judging whether the operation fee calculation is needed or not through the SVM calculation evaluation model, so that the accuracy and the efficiency of the judgment can be improved, and redundant steps are reduced; the operation fee of the policy is automatically calculated through the operation fee calculation model, so that the calculation efficiency is improved, the calculation error rate is reduced, the labor cost is reduced, meanwhile, the code redundancy is reduced, and the system performance is improved; and the expense bill is generated and sent to the corresponding service terminal, so that the settlement efficiency is improved, and the loss to enterprises is avoided.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method described in the embodiments of the present application.

It is apparent that the embodiments described above are only some embodiments of the present application, but not all embodiments, the preferred embodiments of the present application are given in the drawings, but not limiting the patent scope of the present application. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a more thorough understanding of the present disclosure. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing, or equivalents may be substituted for elements thereof. All equivalent structures made by the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the protection scope of the application.

Claims

1. The receipt generation method based on the handling charge calculation and evaluation is characterized by comprising the following steps of:

2. The bill generation method based on commission calculation evaluation according to claim 1, further comprising, before the step of inputting the standard scene feature into a trained SVM calculation evaluation model for evaluation:

3. The bill generation method based on commission calculation evaluation according to claim 2, wherein the step of constructing an SVM classifier includes:

4. The receipt generation method based on the operation fee calculation evaluation according to claim 1, wherein the step of inputting the target policy into the operation fee calculation model to calculate the operation fee, and obtaining the operation fee comprises:

5. The receipt generation method based on a calculation evaluation of a commission fee according to claim 1, wherein the step of inputting the target policy into the commission fee calculation model to calculate a commission fee, further comprises, after the step of obtaining a commission fee:

comparing and verifying the procedure cost with the standard cost;

6. The receipt generation method based on a commission calculation evaluation according to claim 1, wherein the step of generating a fee receipt based on the commission fee and the target policy includes:

7. The bill generation method based on commission calculation and evaluation according to any one of claims 1 to 6, wherein the step of performing standardization processing on the policy scene features to obtain standard scene features includes:

8. A bill generation device based on a commission calculation evaluation, characterized by comprising:

9. A computer device comprising a memory having stored therein computer readable instructions which when executed implement the steps of the bill generation method based on commission calculation evaluation according to any one of claims 1 to 7.

10. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of a bill generation method based on a commission calculation evaluation according to any one of claims 1 to 7.