CN114358641A - A forecasting method, device, equipment and medium for budget approval - Google Patents

Abstract

The application discloses a prediction method, a prediction device, equipment and a medium for budget approval, wherein the method comprises the following steps: constructing automatic approval parameters; determining budget approval data based on user operation, and judging whether to enable the automatic approval parameter; if yes, acquiring historical budget approval data in a preset time period; the historical budget approval data comprises historical budget dimensions, historical budget money and historical approval results; training an initial model of a support vector machine through the historical budget approval data to construct a support vector machine model; and predicting whether the budget approval data passes the approval through the support vector machine model and the budget approval data. The method and the device can realize autonomous inspection of approval submitted by budget, improve the accuracy of prediction, scientifically form an approval standard and improve the efficiency of an approval process.

Description

A forecasting method, device, equipment and medium for budget approval

technical field

The present application relates to the technical field of data management, and in particular, to a forecasting method, apparatus, device and medium for budget approval.

Background technique

Comprehensive budget is an application method for overall management of business indicators, various expenses, and asset status. In order to improve the customer's control over the project, according to the process of the enterprise project, the resources, personnel and other costs are adjusted so as to provide a more reasonable guiding role for the enterprise.

At present, after preparing the budget, the enterprise will submit the prepared report to the superior for approval. With the continuous development of the enterprise, the number of reviewers and management decision-making levels also increase accordingly, which will lead to a lot of time for daily preparation, review and approval. Manually read the budget approval data of previous years to approve the current budget data received. Too much reliance on experience leads to low accuracy of budget approval results.

SUMMARY OF THE INVENTION

Embodiments of the present application provide a forecasting method, device, device, and medium for budget approval, which are used to solve the problem of low accuracy of budget approval results.

The embodiment of the present application adopts the following technical solutions:

On the one hand, an embodiment of the present application provides a method for predicting budget approval. The method includes: constructing automatic approval parameters; determining budget approval data based on user operations, and judging whether to enable the automatic approval parameters; if yes, obtaining Historical budget approval data within a preset time period; the historical budget approval data includes historical budget dimensions, historical budget amounts, and historical approval results; the support vector machine initial model is trained through the historical budget approval data, and a support vector machine model is constructed; According to the support vector machine model and the budget approval data, it is predicted whether the budget approval data is approved or not.

In an example, the initial model of the support vector machine is trained by the historical budget approval data, and the construction of the support vector machine model specifically includes: determining a regular term expression and a loss function term expression; Lagrangian transformation is performed on the expression of the loss function term, and the initial model of the support vector machine is constructed; according to the initial model of the support vector machine, an initial prediction function is determined; the historical budget approval data is input into the initial support vector machine The model is trained to determine the values corresponding to the normal vector and the offset respectively in the initial prediction function; the values corresponding to the normal vector and the offset respectively are input into the initial prediction function to generate a prediction function.

In an example, predicting whether the budget approval data is approved by using the support vector machine model and the budget approval data specifically includes: inputting the budget approval data into the prediction function to generate a predicted value; Whether the predicted value satisfies the preset approval condition, and if so, it is determined that the budget approval data is approved.

In one example, the method further includes: if the predicted value does not meet a preset approval condition, calculating the similarity between the budget approval data and the historical budget approval data; calculating the similarity between the budget approval data and the budget approval data; The approval result corresponding to the highest historical budget approval data is used as the reference approval result of the budget approval data; if the budget approval data is inconsistent with the reference approval result, verify whether the budget approval data is abnormal to the user; If not, the budget approval data will be rejected.

In one example, the method further includes: if the budget approval data is abnormal, acquiring updated budget approval data sent by the user; re-inputting the updated budget approval data into the forecast function to generate an updated forecast value; It is judged whether the updated predicted value satisfies the preset approval condition; if not, the budget approval data is rejected.

In an example, after the budget approval data is rejected, the method further includes: adding the budget approval data to a rejection result queue; in the rejection result queue, within the preset time period, Group multiple rejected budget approval data according to the budget period to obtain multiple groups of rejected budget approval data; extract the budget amount corresponding to the same budget organization from each group of rejected budget approval data; in the budget organization, determine the corresponding budget The average value of the amount, compares a plurality of the budget organizations according to the average value, and determines the budget organization with the highest average value in the rejected budget approval data of each group; summarizes the budget organization with the highest average value, and determines the budget organization with the highest occurrence frequency Budget organization; feeding back the budget organization with the highest frequency to the user, so that the user can verify the operation status of the budget organization with the highest frequency.

In one example, the method further includes: if the automatic approval parameter is not enabled, determining a budget organization corresponding to the budget approval data; retrieving a mapping rule table corresponding to the budget organization in a preset approval database; Review the budget approval data through the mapping rule table to determine abnormal data in the budget approval data; send the abnormal data to the user, so that the user can determine the budget based on the abnormal data Approval data for review.

On the other hand, an embodiment of the present application provides an apparatus for predicting budget approval. The apparatus includes: a building module for building automatic approval parameters; a judgment module for determining budget approval data based on user operations, and judging whether to enable the Automatic approval parameters; the acquisition module, if yes, acquires historical budget approval data within a preset time period; the historical budget approval data includes historical budget dimensions, historical budget amounts, and historical approval results; training module, through the historical budget approval The data trains the initial model of the support vector machine, and constructs the support vector machine model; the prediction module, through the support vector machine model and the budget approval data, predicts whether the budget approval data is approved or not.

On the other hand, an embodiment of the present application provides a forecasting device for budget approval, the device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores data that can be instructions executed by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: construct automatic approval parameters; determine budget approval data based on user operations; and determine Whether to enable the automatic approval parameters; if so, obtain historical budget approval data within a preset time period; the historical budget approval data includes historical budget dimensions, historical budget amounts, and historical approval results; training through the historical budget approval data The initial model of the support vector machine is used to construct a support vector machine model; through the support vector machine model and the budget approval data, it is predicted whether the budget approval data is approved or not.

On the other hand, an embodiment of the present application provides a forecasting non-volatile computer storage medium for budget approval, which stores computer-executable instructions, where the computer-executable instructions are set to: construct automatic approval parameters; based on user operations, Determine budget approval data, and determine whether to enable the automatic approval parameter; if yes, obtain historical budget approval data within a preset time period; the historical budget approval data includes historical budget dimensions, historical budget amounts, and historical approval results; The historical budget approval data trains an initial support vector machine model to construct a support vector machine model; through the support vector machine model and the budget approval data, it is predicted whether the budget approval data is approved or not.

The above-mentioned at least one technical solution adopted in the embodiments of the present application can achieve the following beneficial effects:

The embodiment of the present application can enter the automatic approval mode by constructing the automatic approval parameters, train the initial model of the support vector machine through the historical budget approval data, and construct the support vector machine model, so that the budget approval data can be automatically processed through the support vector machine model and the budget approval data. Approval can realize independent inspection of the approval of budget submission, improve the accuracy of prediction, and form an approval standard scientifically, and at the same time can improve the efficiency of the approval process.

Description of drawings

In order to illustrate the technical solutions of the present application more clearly, some embodiments of the present application will be described in detail below with reference to the accompanying drawings. In the accompanying drawings:

1 is a schematic flowchart of a forecasting method for budget approval provided by an embodiment of the present application;

FIG. 2 is a schematic structural diagram of a prediction device for budget approval provided by an embodiment of the present application;

FIG. 3 is a schematic structural diagram of a prediction device for budget approval provided by an embodiment of the present application.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present application more clear, the technical solutions of the present application will be described clearly and completely below with reference to specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

Some embodiments of the present application will be described in detail below with reference to the accompanying drawings.

FIG. 1 is a schematic flowchart of a forecasting method for budget approval provided by an embodiment of the present application. Certain input parameters or intermediate results in the process allow for manual intervention adjustments to help improve accuracy.

The implementation of the analysis method involved in the embodiments of the present application may be a terminal device or a server, which is not particularly limited in the present application. For the convenience of understanding and description, the following embodiments take a server as an example for detailed description.

It should be noted that the server may be a single device, or may be a system composed of multiple devices, that is, a distributed server, which is not specifically limited in this application.

The flow in Figure 1 can include the following steps:

S101: Build automatic approval parameters.

In some embodiments of the present application, the user adds a new parameter on the server based on the budget approval, that is, the automatic approval parameter. The approval manager, that is, after the user turns on the automatic approval parameter function, will enter the automatic approval parameter. Approval mode, if the user does not enable the function of automatic approval parameters, enter the manual approval mode.

S102: Determine budget approval data based on a user's operation, and determine whether to enable the automatic approval parameter.

In some embodiments of the present application, when a user performs budget approval, since the budget approval data is a kind of multi-dimensional data, the dimensions of different forms are different, for example, (budget organization, budget indicator, budget period, budget amount), According to this structure, for example, (office, USD, 2019, 200) means that the budget of the office in 2019 is $200. Therefore, the user will predefine the budget approval scheme, and when defining the budget approval scheme, determine whether to enable the automatic approval parameter. For example, when a user defines a budget approval scheme and clicks Save, he or she will select whether to enable the automatic approval parameter.

S103: If yes, obtain historical budget approval data within a preset time period; the historical budget approval data includes historical budget dimensions, historical budget amounts, and historical approval results.

In some embodiments of the present application, if the user chooses to activate the automatic approval parameters, the server will determine to activate the automatic approval parameters and enter the automatic approval mode. Since it is the automatic approval mode, the budget approval model needs to automatically approve the budget approval data. Thus, it is automatically judged whether the current budget approval data can be approved.

Based on this, after the server enters the automatic approval mode, it will start to obtain historical budget approval data within a preset time period, and generate a budget approval model by training the historical budget approval data.

Further, if the user does not choose to activate the automatic approval parameter, the server will enter the manual approval mode, and in order to reduce the user's manual review cost, the budget approval data will be preliminarily reviewed.

Specifically, the budget organization corresponding to the budget approval data is first determined, and the mapping rule table corresponding to the budget organization is retrieved in a preset approval database. Among them, the mapping rule table includes the constraints of the budget organization. For example, the budget amount of the 2019 office must not exceed $200.

Review the budget approval data through the mapping rule table, determine abnormal data in the budget approval data, and finally send the abnormal data to the user, so that the user can review the budget approval data based on the abnormal data, that is, the user can refer to The results of the review are then reviewed for budget approval data.

S104: Train an initial support vector machine model by using the historical budget approval data, and construct a support vector machine model.

In some implementations of this application, since the support vector machine is an algorithm for limited samples, it can perform training by minimizing the actual output value and the predicted output value under the limited sample, and it is expected to obtain good training parameters, and finally Good results are obtained during prediction and accurate prediction results are achieved. In addition, support vector machine is a quadratic convex problem, so it can be solved quickly, and a unique optimal value can be obtained, avoiding the occurrence of local optimal values. Case.

Based on this, the support vector machine can obtain an optimal hyperplane through training, and use the hyperplane to judge whether the new decision is approved or not. Its structure is mainly divided into two parts: regularization term and loss function term. Support vector machines reduce the structural risk of the model by using the minimization regularization term, and reduce the empirical risk by using the loss function term.

Therefore, the support vector machine can be trained by the historical budget approval data of previous years. Since its loss function is Hinge loss, which is a convex function, it can be solved relatively quickly and unique values can be obtained. When the model is applied to a comprehensive budget review, it can more concisely and accurately predict whether the budget approval data meets the conditions, so that it can be automatically approved or returned for review.

It should be noted that the basic framework of the support vector machine is as follows:

st, y _i (w ^T X _i +b)≥1-L _i , L _i ≥ 0

为正则项表达式，

为损失函数项表达式，L_i＝max[0，1-y_i(ω^TX_i+b)]为具体的损失函数。in,

is the regular term expression,

is the loss function term expression, and L _i =max[0,1-y _i (ω ^T X _i +b)] is a specific loss function.

Among them, Xi is the data corresponding to the historical budget dimension, _yi is the historical approval result, _w is the normal vector, b is the bias, and C' is a constant greater than 0.

Further, Lagrangian transformation is performed on the regular term expression and the loss function term expression to construct the initial model of the support vector machine.

The initial model of the support vector machine is as follows:

Among them, ξ, λ, μ are Lagrange multipliers.

Through the above initial model of the vector machine, the initial prediction function can be obtained. In the initial prediction function, the values corresponding to the normal vector and the offset are unknown. The initial prediction function is as follows:

w ^T x+b=0

Substitute the historical budget approval data into the initial model of the support vector machine for training, so that the corresponding values of the normal vector and the offset in the initial prediction function can be obtained.

The values corresponding to the normal vector and the offset are input into the initial prediction function, and a specific prediction function can be generated to construct a support vector machine model for budget approval.

S105: Predict whether the budget approval data is approved by using the support vector machine model and the budget approval data.

In some implementations of the present application, the forecast value is generated by inputting the budget approval data into the forecast function, and then it is judged whether the forecast value satisfies the preset approval conditions, and if so, it is determined that the budget approval data is approved. For example, if the predicted value is +1, it means that the approval is passed, and if the predicted value is -1, it means that the approval is not passed.

Further, since the user may input the budget approval data incorrectly, if the approval is directly rejected, the automatic approval parameters need to be restarted, and the process takes a long time. In order to improve the efficiency of budget approval, it is possible to verify whether the budget approval data is abnormal to the user in time.

Specifically, when the predicted value does not meet the preset approval conditions, the server calculates the similarity between the budget approval data and the historical budget approval data, and uses the approval result corresponding to the historical budget approval data with the highest similarity to the budget approval data as the budget approval The reference approval result of the data. If the budget approval data is inconsistent with the reference approval result, the user will be verified whether the budget approval data is abnormal. If not, the budget approval data will be rejected.

Further, when the budget approval data is abnormal, the updated budget approval data sent by the user is obtained, and the updated budget approval data is input into the prediction function again to generate an updated prediction value. Then, it is judged whether the updated predicted value satisfies the preset approval condition.

In order to improve security, when the updated forecast value does not meet the preset approval conditions, verification is no longer performed, and the budget approval data is directly rejected.

Furthermore, after the budget approval data is rejected, the predicted budget approval data includes the budget amount of each budget organization in each period and the corresponding approval result. Then there is a situation where the department develops rapidly due to certain needs. For example, the department needs to expand its scale. However, during this process, the actual progress of the department's development cannot be monitored in real time, and there may be excessive expansion.

Therefore, a budget organization that can extract the budget excess in each budget period is performed, so as to be a sensitive object, and the development of each budget organization can be balanced in time.

Specifically, the budget approval data is added to the rejection result queue, and in the rejection result queue, within a preset time period, multiple groups of rejected budget approval data are grouped according to the budget period to obtain multiple groups of rejected budget approval data.

Then, the budget amount corresponding to the same budget organization is extracted from the rejected budget approval data of each group. In the budget organization, the average value of the corresponding budget amount is determined, and multiple budget organizations are compared according to the average value to determine the average value in the rejected budget approval data of each group. highest budget organization.

Finally, the budget organization with the highest average value is aggregated to determine the budget organization with the highest frequency, so that the budget organization with the highest frequency is fed back to the user, so that the user can verify the operation status of the budget organization with the highest frequency.

It should be noted that, although steps S101 to S105 are sequentially introduced and described in this embodiment of the present application with reference to FIG. 1 , this does not mean that steps S101 to S105 must be performed in strict order. The reason why the embodiments of the present application describe steps S101 to S105 in sequence according to the sequence shown in FIG. 1 is to facilitate those skilled in the art to understand the technical solutions of the embodiments of the present application. In other words, in this embodiment of the present application, the sequence between steps S101 to S105 may be appropriately adjusted according to actual needs.

Through the method in Figure 1, by constructing automatic approval parameters, it is possible to enter the automatic approval mode, train the initial model of the support vector machine through the historical budget approval data, and construct the support vector machine model, so that the budget can be automatically adjusted through the support vector machine model and the budget approval data. Approval of the approval data can realize the independent inspection of the approval of the budget submission, improve the accuracy of the forecast, and at the same time form an approval standard scientifically, and at the same time can improve the efficiency of the approval process.

Based on the same idea, some embodiments of the present application also provide apparatuses, devices, and non-volatile computer storage media corresponding to the above methods.

FIG. 2 is a schematic structural diagram of a forecasting apparatus for budget approval provided by an embodiment of the present application, and the apparatus includes:

Building module 201, building automatic approval parameters;

The judgment module 202, based on the user's operation, determines the budget approval data, and judges whether to enable the automatic approval parameter;

The obtaining module 203, if yes, obtains historical budget approval data within a preset time period; the historical budget approval data includes historical budget dimension, historical budget amount, and historical approval result;

The training module 204 trains the initial model of the support vector machine through the historical budget approval data, and constructs the support vector machine model;

The predicting module 205, through the support vector machine model and the budget approval data, predicts whether the budget approval data is approved or not.

FIG. 3 is a schematic structural diagram of a prediction device for budget approval provided by an embodiment of the present application, and the device includes:

at least one processor; and,

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

Build automatic approval parameters;

Based on the user's operation, determine budget approval data, and determine whether to enable the automatic approval parameter;

If so, obtain historical budget approval data within a preset time period; the historical budget approval data includes historical budget dimensions, historical budget amounts, and historical approval results;

Train the initial model of the support vector machine through the historical budget approval data, and construct the support vector machine model;

According to the support vector machine model and the budget approval data, it is predicted whether the budget approval data is approved or not.

A forecasting non-volatile computer storage medium for budget approval provided by the embodiment of the present application stores computer-executable instructions, and the computer-executable instructions are set to:

Build automatic approval parameters;

Based on the user's operation, determine budget approval data, and determine whether to enable the automatic approval parameter;

If so, obtain historical budget approval data within a preset time period; the historical budget approval data includes historical budget dimensions, historical budget amounts, and historical approval results;

Train the initial model of the support vector machine through the historical budget approval data, and construct the support vector machine model;

According to the support vector machine model and the budget approval data, it is predicted whether the budget approval data is approved or not.

The various embodiments in this application are described in a progressive manner, and the same and similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the apparatus, device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for related parts.

The devices, devices, and media provided in the embodiments of the present application are in one-to-one correspondence with the methods. Therefore, the devices, devices, and media also have similar beneficial technical effects to their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above Therefore, the beneficial technical effects of the apparatus, equipment and medium will not be repeated here.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each process and/or block in the flowchart illustrations and/or block diagrams, and combinations of processes and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

Memory may include non-persistent memory in computer readable media, random access memory (RAM) and/or non-volatile memory in the form of, for example, read only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media includes both persistent and non-permanent, removable and non-removable media, and storage of information may be implemented by any method or technology. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, excludes transitory computer-readable media, such as modulated data signals and carrier waves.

It should also be noted that the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device comprising a series of elements includes not only those elements, but also Other elements not expressly listed, or which are inherent to such a process, method, article of manufacture, or apparatus are also included. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article of manufacture or device that includes the element.

The above descriptions are merely examples of the present application, and are not intended to limit the present application. Various modifications and variations of this application are possible for those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the technical principles of this application shall fall within the protection scope of this application.

Claims (10)

1. A forecasting method for budget approval, wherein the method comprises: Build automatic approval parameters; Based on the user's operation, determine budget approval data, and determine whether to enable the automatic approval parameter; If so, obtain historical budget approval data within a preset time period; the historical budget approval data includes historical budget dimensions, historical budget amounts, and historical approval results; Train the initial model of the support vector machine through the historical budget approval data, and construct the support vector machine model; According to the support vector machine model and the budget approval data, it is predicted whether the budget approval data is approved or not. 2. The method according to claim 1, wherein the initial model of the support vector machine is trained by the historical budget approval data, and the support vector machine model is constructed, specifically comprising: Determine the regular term expression and the loss function term expression; Lagrangian transformation is performed on the regular term expression and the loss function term expression to construct the initial model of the support vector machine; According to the initial model of the support vector machine, determine the initial prediction function; Inputting the historical budget approval data into the support vector machine initial model for training, to determine the values corresponding to the normal vector and the offset in the initial prediction function respectively; The values corresponding to the normal vector and the offset are input into the initial prediction function to generate a prediction function. 3. The method according to claim 2, wherein the predicting whether the budget approval data is approved by using the support vector machine model and the budget approval data specifically comprises: inputting the budget approval data into the forecast function to generate a forecast value; It is judged whether the predicted value satisfies the preset approval condition, and if so, it is determined that the budget approval data is approved. 4. The method according to claim 3, wherein the method further comprises: If the predicted value does not meet the preset approval conditions, calculating the similarity between the budget approval data and the historical budget approval data; Taking the approval result corresponding to the historical budget approval data with the highest similarity to the budget approval data as the reference approval result of the budget approval data; If the budget approval data is inconsistent with the reference approval result, verifying to the user whether the budget approval data is abnormal; If not, the budget approval data is rejected. 5. The method according to claim 4, wherein the method further comprises: If the budget approval data is abnormal, obtain updated budget approval data sent by the user; re-inputting the updated budget approval data into the forecast function to generate an updated forecast value; judging whether the updated predicted value satisfies the preset approval condition; If not, the budget approval data is rejected. 6. The method according to claim 4, wherein after the budget approval data is rejected, the method further comprises: adding the budget approval data to the rejection result queue; In the rejection result queue, within the preset time period, group a plurality of rejected budget approval data according to the budget period to obtain multiple groups of rejected budget approval data; Extract the budget amount corresponding to the same budget organization for each group of rejected budget approval data; In the budget organization, determine the average value of the corresponding budget amounts, compare a plurality of the budget organizations according to the average value, and determine the budget organization with the highest average value among the groups of rejected budget approval data; Summarize the budget organization with the highest average value to determine the budget organization with the highest frequency; The budget organization with the highest frequency is fed back to the user, so that the user can verify the operation status of the budget organization with the highest frequency. 7. The method of claim 1, wherein the method further comprises: If the automatic approval parameter is not enabled, determine the budget organization corresponding to the budget approval data; In a preset approval library, retrieve the mapping rule table corresponding to the budget organization; Examining the budget approval data through the mapping rule table to determine abnormal data in the budget approval data; The abnormal data is sent to the user, so that the user can review the budget approval data based on the abnormal data. 8. A forecasting device for budget approval, characterized in that the device comprises: Building modules, building automatic approval parameters; a judgment module, based on the user's operation, to determine the budget approval data, and to judge whether to enable the automatic approval parameter; an acquisition module, if yes, acquire historical budget approval data within a preset time period; the historical budget approval data includes historical budget dimensions, historical budget amounts, and historical approval results; A training module, which trains the initial model of the support vector machine through the historical budget approval data, and constructs a support vector machine model; The prediction module, through the support vector machine model and the budget approval data, predicts whether the budget approval data is approved or not. 9. A forecasting device for budget approval, characterized in that the device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Build automatic approval parameters; Based on the user's operation, determine budget approval data, and determine whether to enable the automatic approval parameter; If so, obtain historical budget approval data within a preset time period; the historical budget approval data includes historical budget dimensions, historical budget amounts, and historical approval results; Train the initial model of the support vector machine through the historical budget approval data, and construct the support vector machine model; According to the support vector machine model and the budget approval data, it is predicted whether the budget approval data is approved or not. 10. A forecast non-volatile computer storage medium for budget approval, storing computer-executable instructions, wherein the computer-executable instructions are set to: Build automatic approval parameters; Based on the user's operation, determine budget approval data, and determine whether to enable the automatic approval parameter; If so, obtain historical budget approval data within a preset time period; the historical budget approval data includes historical budget dimensions, historical budget amounts, and historical approval results; Train the initial model of the support vector machine through the historical budget approval data, and construct the support vector machine model; According to the support vector machine model and the budget approval data, it is predicted whether the budget approval data is approved or not.

Images