CN112750059A

CN112750059A - Evaluation method of industry support policy, processing method of industry support result and related product

Info

Publication number: CN112750059A
Application number: CN201911065562.3A
Authority: CN
Inventors: 王鹏; 郑志彬; 聂贤政; 黄敬
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2019-10-31
Filing date: 2019-10-31
Publication date: 2021-05-04

Abstract

The embodiment of the application provides an industry support policy evaluation method, an industry support result processing method and related products, and the industry support policy evaluation method comprises the following steps: predicting the supporting effect of an enterprise to be supported by using a prediction model to obtain a prediction result, wherein the enterprise to be supported is screened from a plurality of enterprises according to a preset industry supporting policy; and obtaining an evaluation result of the industry support policy according to the prediction result. The embodiment of the application is beneficial to achieving the optimal industry supporting effect.

Description

Evaluation method of industry support policy, processing method of industry support result and related product

Technical Field

The application relates to the technical field of artificial intelligence, in particular to an evaluation method of an industry support policy, a processing method of an industry support result and a related product.

Background

The industry policy support fund is the policy type invested fund used by the government to support a certain industry or a certain type of enterprises, and has important strategic significance on economic development. As a result, governments devote significant supporting capital to industry and businesses each year. For example, two industry support policies in 2017 of xx city are detailed below: 1. the scientific and technological small giant supports that the annual income growth rate of the national high and new technology enterprises with the annual income of more than 2 million yuan and local statistics is more than 20 percent, 60 ten thousand yuan is supported at one time, the annual income growth rate of two continuous years is more than 15 percent, and 100 ten thousand yuan is supported at one time. 2. The emerging industrial enterprises have high growth support, and 30 ten thousand yuan support is provided for industries which are established for more than three years, enter the enterprise statistical range of more than the market scale, and engage in seven strategic emerging industries or five future industries of the market and the important development of the market, such as financial science and technology, big data and the like, and the annual average growth rate of income in recent two years reaches more than 30%.

Wherein, industry policy support mainly includes the following process: policy making → policy publishing, publicity → eligible enterprise application policy support → approval and appropriation support funds. However, after the supporting fund is paid by the enterprise, the enterprise uses the supporting fund by itself, so that the influence of the paid supporting fund on the development of the enterprise cannot be known, the supporting effect of the supporting fund cannot be evaluated, the establishment of an industrial supporting policy is influenced, and the implementation of the industrial supporting policy is not facilitated.

Disclosure of Invention

The embodiment of the application discloses an evaluation method of an industry support policy, a processing method of an industry support result and related products, which are beneficial to providing a reference direction for adjusting and making the industry support policy so as to realize an optimal industry support result and further promote economic development.

In a first aspect, an embodiment of the present application provides an industry support policy evaluation method, including:

predicting the supporting effect of an enterprise to be supported by using a prediction model to obtain a prediction result, wherein the enterprise to be supported is screened from a plurality of enterprises according to a preset industry supporting policy;

and obtaining an evaluation result of the industry support policy according to the prediction result.

The supporting results of the enterprises to be supported are predicted through the prediction model, so that the supporting result of each enterprise to be supported is obtained; and evaluating the advantages and disadvantages of the currently made industry support policy according to the support result so as to adjust the currently made industry support policy, thereby enabling the finally made industry support policy to achieve the optimal support effect.

In some possible embodiments, before predicting the supporting effect of the enterprise to be supported by using the prediction model, the method further includes:

constructing the predictive model using historical support data for the M supported enterprises, wherein the predictive model includes one or more of a first predictive model corresponding to an enterprise development dimension, a second predictive model corresponding to an enterprise growth dimension, and a third predictive model corresponding to a support benefit dimension,

the building the predictive model using historical support data for the M supported enterprises includes:

determining a historical support result A of each supported enterprise in a dimension A according to the historical support data of each of the M supported enterprises, wherein the dimension A is one of the enterprise development dimension, the enterprise growth dimension and the support benefit dimension;

predicting the supporting effect of each supported enterprise according to the historical supporting data of each supported enterprise to obtain a supporting result A' of each supported enterprise on the dimension A;

and constructing a prediction model corresponding to the dimension A according to the support result A and the support result A' of each supported enterprise.

Therefore, the prediction model is constructed through the historical support data, and the plurality of prediction models are constructed in multiple dimensions, so that the prediction model is provided for the prediction of the support effect, and an evaluation tool is provided for the advantages and disadvantages of the support policy, so that the formulated industry support policy can achieve the optimal support effect.

In some possible embodiments, the historical support data includes support funds, revenue acceleration rate, employee acceleration rate, revenue amount and tax intake amount in the t year, and revenue acceleration rate, employee acceleration rate, revenue amount and tax intake amount in the t + k year, wherein the t year is the year of support acquisition, and k is an integer greater than or equal to 1;

the determining the historical support result A of each supported enterprise in the dimension A according to the historical support data of each of the M supported enterprises includes:

when the dimension A is the enterprise development dimension, obtaining a support result A of each supported enterprise on the enterprise development dimension according to the revenue acceleration and employee acceleration of each supported enterprise in the t year and the revenue acceleration and employee acceleration in the t + k year;

when the dimension A is the enterprise growth dimension, obtaining a supporting result A of each supported enterprise on the enterprise growth dimension according to the revenue acceleration and the revenue quota of each supported enterprise in the t year and the revenue acceleration and the revenue quota in the t + k year;

and when the dimension A is the supporting benefit dimension, obtaining a supporting result A of each supported enterprise on the supporting benefit dimension according to the supporting fund obtained by each supported enterprise, the taxreceiving amount in the t year and the taxreceiving amount in the t + k year.

In some possible embodiments, the obtaining, according to the prediction result, an evaluation result of the industry support policy includes:

obtaining an evaluation result of the industry support policy according to the support result corresponding to the prediction result;

wherein, when the predictive model comprises one of the first predictive model, the second predictive model, and the third predictive model, the support outcome comprises a support outcome corresponding to the predictive model;

when the prediction model includes two of the first prediction model, the second prediction model, and the third prediction model, the support outcome includes one or both of two support outcomes corresponding to the two prediction models;

when the predictive model includes the first predictive model, the second predictive model, and the third predictive model, the support outcome includes one or more of a first support outcome, a second support outcome, and a third support outcome;

wherein the first support outcome is determined from a first prediction outcome corresponding to the first prediction model, the second support outcome is determined from a second prediction outcome corresponding to the second prediction model, and the third support outcome is determined from a third prediction outcome corresponding to the third prediction model.

It can be seen that, because a plurality of prediction models are constructed in a plurality of dimensions, when the support result is predicted, one or a plurality of prediction models can be freely selected and used to predict the support result in one or a plurality of dimensions, so that the flexibility of the support result prediction is improved; in addition, comprehensive processing can be carried out on the supporting results in multiple dimensions, so that the obtained supporting results are closer to real supporting results, and the reasonability of industrial supporting policy adjustment is further improved.

In some possible embodiments, when the first predicted result is greater than 0, the first support result belongs to a first support level, and the larger the first predicted result is, the better the support effect corresponding to the first support result is;

when the first prediction result is smaller than 90 degrees, the first support result belongs to a second support level, and the larger the first prediction result is, the better the support effect corresponding to the first support result is;

when the first prediction result is larger than 90 degrees, the first support result belongs to a third support level, and the larger the first prediction result is, the better the support effect corresponding to the first support result is;

when the first prediction result is smaller than 0, the first support result belongs to a fourth support level, and the larger the first prediction result is, the better the support effect corresponding to the first support result is;

wherein the supporting effects corresponding to the first supporting level, the second supporting level, the third supporting level and the fourth supporting level are reduced in sequence.

Therefore, the evaluation model of the support result is constructed for the development dimension of the enterprise, so that the specific support result of any enterprise to be supported in the dimension can be predicted, data support is provided for evaluating the development condition of the enterprise after receiving the support fund, persuasion of support effect prediction is improved, and data reference is provided for making and adjusting the industrial support policy.

In some possible embodiments, when the second predicted result is greater than 0, the second support result belongs to the first support level, and the larger the second predicted result is, the better the support effect corresponding to the second support result is;

when the second prediction result is smaller than 90 degrees, the second support result belongs to a second support level, and the larger the second prediction result is, the better the support effect corresponding to the second support result is;

when the second prediction result is smaller than 0, the second support result belongs to a third support level, and the larger the second prediction result is, the better the support effect corresponding to the second support result is;

wherein the supporting effects corresponding to the first supporting level, the second supporting level and the third supporting level are reduced in sequence.

Therefore, the evaluation model of the support result is constructed for the growth dimension of the enterprise, so that the specific support result of any enterprise to be supported in the dimension can be predicted, data support is provided for evaluating the development condition of the enterprise after receiving the support fund, persuasion of support effect prediction is improved, and data reference is provided for making and adjusting the industrial support policy.

In some possible embodiments, when the third predicted result is greater than 0, the third support result belongs to the first support level, and the larger the third predicted result is, the better the support effect corresponding to the third support result is;

when the third prediction result is smaller than 90 degrees, the third support result belongs to a second support level, and the larger the third prediction result is, the better the support effect corresponding to the third support result is;

when the third prediction result is smaller than 0, the third support result belongs to a third support level, and the larger the third prediction result is, the better the support effect corresponding to the third support result is;

when the third prediction result is greater than 90 degrees, the third support result belongs to a fourth support level, and the larger the third prediction result is, the better the support effect corresponding to the third support result is;

Therefore, an evaluation model of the support result is constructed for the support benefit dimension, so that a specific support result of any enterprise to be supported in the dimension can be predicted, data support is provided for evaluating the development condition of the enterprise after receiving the support fund, persuasion of support effect prediction is improved, and data reference is provided for making and adjusting an industrial support policy.

In a second aspect, an embodiment of the present application provides a method for processing an industry support result, including:

determining a historical support result between the t year and the t + k year according to the historical support data of each year from the t year to the t + k year;

and displaying the historical support result on a visual interface.

Therefore, the historical support result is determined according to the historical support data of the supported enterprise in the scheme, and the historical support result is visually displayed, so that the historical support situation is known, and reference is provided for making a future support policy.

In some possible embodiments, the support results include a first support result corresponding to an enterprise development dimension, a second support result corresponding to an enterprise growth dimension, and a third support result corresponding to a support benefits dimension, the historical support data includes one or more of enterprise data for each supported enterprise, and the determining historical support results between the t year and the t + k year from historical support data for each of the t year to the t + k year includes:

determining a historical support result of each supported enterprise in a dimension A according to enterprise data of each supported enterprise, wherein the dimension A is one of the enterprise development dimension, the enterprise growth dimension and the support benefit dimension;

and determining the historical support result in the dimension A between the t year and the t + k year according to the historical support result of each supported enterprise in the dimension A.

It can be seen that in the scheme, the historical support results of each supported enterprise in each dimension are determined according to the historical support data of the supported enterprise, and the historical support results of each dimension are visually displayed, so that the historical support situation of each dimension is known, and reference is provided for formulation of the industry support policy of each dimension.

In some possible embodiments, the enterprise data includes supported funds, revenue acceleration, employee acceleration, revenue amount, and tax amount obtained by each supported enterprise, and the determining the historical support result of each supported enterprise in dimension a according to the enterprise data of each supported enterprise includes:

when the dimension A is the enterprise development dimension, obtaining a first historical support result of each supported enterprise according to the revenue acceleration and employee acceleration of each supported enterprise in the t year and the revenue acceleration and employee acceleration in the t + k year;

when the dimension A is the enterprise growth dimension, obtaining a second historical supporting result of each supported enterprise according to the revenue increasing rate and the revenue income amount of each supported enterprise in the t year and the revenue increasing rate and the revenue income amount of each supported enterprise in the t + k year;

and when the dimension A is the supporting benefit dimension, obtaining a third history supporting result of each supported enterprise according to the supporting fund obtained in the t year, the taxes amount in the t year and the taxes amount in the t + k year of each supported enterprise.

In some possible embodiments, the historical support data includes support fund usage information, and the determining the historical support result between the tth year and the t + k year according to the historical support data of each year from the tth year to the t + k year includes:

obtaining a historical supporting result of the r year according to supporting fund use information of the r year, wherein the r year is a year between the t year and the t + k year;

the historical support results include: the investment ratio of the supporting funds is the ratio of the supporting funds actually used in the r-th year to the supporting funds input in the budget of the r-th year.

It can be seen that according to the scheme, historical support data of each supported enterprise is obtained, so that industry support situations of governments over years are determined, and support situations of various industry fields are known, so that reference directions are provided for government to make support policies in the future.

In a third aspect, an embodiment of the present application provides an apparatus for evaluating an industry support policy, including:

the prediction unit is used for predicting the supporting effect of the enterprise to be supported by using the prediction model to obtain a prediction result, and the enterprise to be supported is screened from a plurality of enterprises according to a preset industry supporting policy;

and the determining unit is used for obtaining an evaluation result of the industry support policy according to the prediction result.

In some possible embodiments, the evaluation device further comprises: a training unit, configured to construct a prediction model using historical support data of the M supported enterprises before the prediction unit predicts the support effect of the enterprise to be supported using the prediction model, wherein the prediction model includes one or more of a first prediction model corresponding to an enterprise development dimension, a second prediction model corresponding to an enterprise growth dimension, and a third prediction model corresponding to a support benefit dimension,

in respect of constructing the prediction model using historical support data of M supported enterprises, the training unit is specifically configured to:

determining a support result A of each supported enterprise in a dimension A according to the historical support data of each of the M supported enterprises, wherein the dimension A is one of the enterprise development dimension, the enterprise growth dimension and the support benefit dimension;

in terms of determining a support result a of each supported enterprise in dimension a according to the historical support data of each of the M supported enterprises, the training unit is specifically configured to:

In some possible embodiments, in terms of obtaining an evaluation result of the industry support policy according to the prediction result, the determining unit is specifically configured to:

In a fourth aspect, an embodiment of the present application provides an apparatus for processing an industry support result, including:

the determining unit is used for determining a historical support result between the t year and the t + k year according to the historical support data of each year from the t year to the t + k year;

and the display unit is used for displaying the history support result on a visual interface.

In some possible embodiments, the support results include a first support result corresponding to an enterprise development dimension, a second support result corresponding to an enterprise growth dimension, and a third support result corresponding to a support benefit dimension, the historical support data includes one or more of the enterprise data for each supported enterprise,

in terms of determining the historical support result between the tth year and the t + k year according to the historical support data of each year from the tth year to the t + k year, the determining unit is specifically configured to:

In some possible embodiments, the enterprise data includes supporting funds, revenue acceleration, employee acceleration, revenue amount, and tax amount obtained by each supported enterprise,

in terms of determining the historical support result of each supported enterprise in the dimension a according to the enterprise data of each supported enterprise, the determining unit is specifically configured to:

In some possible embodiments, the historical support data includes support fund usage information, and in terms of determining the historical support result of each supported enterprise in the dimension a according to the enterprise data of each supported enterprise, the determining unit is specifically configured to:

In a fifth aspect, an embodiment of the present application provides an apparatus for evaluating an industry-supported policy, including:

the device comprises a processor, a communication interface and a memory, wherein the processor, the communication interface and the memory are connected through electric signals;

the processor is used for predicting the supporting effect of the enterprise to be supported by using the prediction model to obtain a prediction result, and the enterprise to be supported is screened from a plurality of enterprises according to a preset industry supporting policy;

and the processor is also used for obtaining an evaluation result of the industry support policy according to the prediction result.

In a sixth aspect, an embodiment of the present application provides an apparatus for processing an industry support result, including:

the device comprises a processor, a communication interface, a memory and a display, wherein the processor, the communication interface, the memory and the display are connected through electric signals;

the processor is used for determining a historical support result between the t year and the t + k year according to the historical support data from the t year to the t + k year;

and the processor is used for controlling the display to display the historical support result on a visual interface.

In a seventh aspect, this application embodiment further provides a computer-readable storage medium, where a computer program is stored, where the computer program is executed by hardware (for example, a processor, etc.), and part or all of the steps of any one of the methods executed by the industry support result evaluation device in this application embodiment, or part or all of the steps of any one of the methods executed by the industry support result processing device in this application embodiment.

In an eighth aspect, embodiments of the present application provide a computer program product including instructions, which, when running on a lane line tracking device, causes an industry support result evaluation device to perform part or all of the steps of the above method for evaluating an industry support policy of the first aspect, or part or all of the steps of the method for processing an industry support result of the second aspect.

Drawings

Some drawings to which embodiments of the present application relate will be described below.

FIG. 1 is a diagram of an industry support system architecture according to an embodiment of the present disclosure;

fig. 2A is a schematic flowchart of an evaluation method of an industry support policy according to an embodiment of the present disclosure;

FIG. 2B is a schematic diagram of an enterprise screened using industry-supported policies according to an embodiment of the present application;

fig. 3 is a schematic flowchart of a method for constructing a prediction model according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a supporting result for determining a development dimension of an enterprise according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a supporting result for determining a growth dimension of an enterprise according to an embodiment of the present application;

FIG. 6 is a schematic diagram of a support result for determining a support benefit dimension according to an embodiment of the present application;

FIG. 7 is a flowchart illustrating a method for processing industry support results according to an embodiment of the present disclosure;

fig. 8 is a schematic diagram of an evaluation model for evaluating a supporting effect of an enterprise development dimension according to an embodiment of the present application;

fig. 9 is a schematic diagram of an evaluation model for evaluating a supporting effect of an enterprise growth dimension according to an embodiment of the present application;

fig. 10 is a schematic diagram of an evaluation model for evaluating a support effect of a support benefit dimension according to an embodiment of the present application;

fig. 11 is a schematic view illustrating a supporting effect according to an embodiment of the present disclosure;

FIG. 12 is a schematic diagram illustrating the use of funds held according to an embodiment of the present application;

FIG. 13 is a schematic diagram illustrating the use of supporting capital sub-enterprises according to an embodiment of the present application;

FIG. 14 is a schematic diagram of an industrial policy image according to an embodiment of the present application;

fig. 15 is a schematic diagram of an apparatus for evaluating an industry support policy according to an embodiment of the present disclosure;

FIG. 16 is a schematic diagram of an apparatus for processing industrial support results provided by an embodiment of the present application;

FIG. 17 is a schematic diagram of another apparatus for evaluating industry support policies according to an embodiment of the present disclosure;

fig. 18 is a schematic view of another industrial support result processing device according to an embodiment of the present disclosure.

Detailed Description

The industry policy support mainly comprises the following processes: policy making → policy publishing, publicity → eligible enterprise application policy support → approval and appropriation support funds. Currently, the formulation of industry support policy and enterprise screening are generally executed by government departments such as trust committee, reform committee, and scientific creation committee, the payment of support funds is executed by financial committee, and all the departments execute respective related work flows. It can be seen that the whole industry policy support process lacks evaluation and observation of the support effect, that is, after the support fund is paid, the enterprise uses the support fund by itself, and does not investigate and acquire the influence of the support fund on the development of the enterprise, so that the support effect brought by the support fund is unknown. For example, it is not known whether business revenue, taxes, employee numbers, etc. have increased due to the investment of supporting funds. And moreover, the support effect is evaluated, whether the establishment of the support policy is reasonable can be clearly known, and data reference is provided for the establishment of the subsequent support policy, so that the subsequently established support policy can bring better support effect.

Therefore, a solution for analyzing and predicting the supporting effect caused by the supporting of the industrial policy is urgently needed.

Fig. 1 is a system architecture diagram for industry support according to an embodiment of the present application, including:

the data access platform 100 is used for acquiring original business data from platforms of various government departments related to an industry support policy, wherein the original business data comprise industry policy data of industry policy making departments such as a commission to change, a commission to credit and the like, policy support fund payment data of a financial commission, tax payment data of a supported enterprise of a tax bureau, operation data of the supported enterprise of a statistical bureau, value-added data and the like related to the enterprise, data of the supported enterprise payment social security staff of a human-society bureau, and the like; after the original data is obtained, the data access platform 100 synthesizes and fuses data information of each support enterprise at each department through a data exchange sharing function, so as to obtain support data of each support enterprise.

And the data processing platform 110 is used for cleaning and processing the original business data acquired from each government department, eliminating invalid data, repeated data and the like in the original business data, classifying and sorting the eliminated business data, and forming a finally usable data set.

And the original library 120 is used for uniformly inputting the data sets subjected to the treatment by the data treatment platform into the original library to form various library tables. For example, a policy base corresponding to the policy content, an enterprise base corresponding to the basic enterprise information, a tax base corresponding to the tax payment data of the enterprise, a revenue base corresponding to the revenue data of the enterprise, and an employee base corresponding to the employee data of the enterprise.

And the service library 130 is used for providing data support for the service visualization presentation layer 160. Namely, the data required by the service visualization presentation layer 160 is from the service library 130, for example, the data in the "held fund use service library" needs to be used for visualization presentation of "industry held fund used condition analysis over years", the data in the "fund industry input service library" needs to be used for visualization presentation of "industry held fund used analysis over industry", the data in the "held effect evaluation service library" needs to be used for visualization presentation of "evaluation of the policy held effect over years", and the data in the "historical policy observation service library" needs to be used for visualization presentation of "whole picture of the policy over years"; the visual presentation of "decision suggestions for future industrial policy making" requires the use of data in the "future decision assistance business repository".

The data in the business repository 130 comes from the raw repository 120 and the big data analytics platform 140. The business library 130 extracts different data from various types of library tables of different original libraries 120 according to business requirements to form a database table that can support the visual presentation layer 160. In addition, the business data formed by modeling the analysis results of the big data in the business repository 130 comes from the big data analysis platform 140.

The big data analysis platform 140 is used for modeling the evaluation of the support effect and the establishment of the auxiliary industry support policy, performing data mining analysis and continuous optimization adjustment of the model according to the obtained data, so that the predicted and determined result of the support evaluation is closest to the real situation, so that a reference direction is provided for the establishment of the industry support policy according to the predicted result, the industry support policy is optimized, the decision proposal for the establishment of the policy is more objective and accurate, and the optimal industry support effect is achieved.

And the data instance management 150 is used for performing service opening on the analysis result of the big data analysis platform 140, and performing management and unified opening on the analysis result obtained by the big data analysis platform 140 through comparison collision, mining analysis and algorithm model in a data interface service instance mode.

And the business visual presentation layer 160 is used for realizing visual presentation of the business. The business visualization presentation layer 160 extracts different business data from the business library 130 based on actual presentation requirements, and performs business presentation in the form of a visualization chart. The terminal used in the visual presentation can be an LED large screen, a PC, a notebook, a PAD, a smart phone and the like.

It can be seen that, in the embodiment of the application, the system architecture can analyze the industry support results of the supported enterprises to obtain the support results of the supported enterprises in the past year, so as to evaluate the industry support policies in the past year and provide direction reference for making and adjusting the future industry support policies; in addition, the supporting effect of the enterprise to be supported can be predicted so as to adjust the currently made industry supporting strategy, so that the made industry supporting policy can achieve the optimal supporting effect.

Fig. 2A is a schematic flowchart of a method for evaluating an industry-supported policy according to an embodiment of the present application, where the method includes, but is not limited to, the following steps:

201: and predicting the supporting effect of the enterprise to be supported by using the prediction model to obtain a prediction result.

The enterprise to be supported is screened from a plurality of enterprises according to a preset industry support policy.

As shown in fig. 2B, the enterprise to be supported is screened from the plurality of enterprises using a preset policy model and preset industry support policies. The industry supports policies such as the size of the enterprise revenue, whether the enterprise is a national high enterprise, and the like.

It should be noted that, the prediction model can be used to predict the supporting effect of a plurality of enterprises to be supported. In the application, only one enterprise to be supported is used for describing the prediction of the supporting effect in detail, and the prediction modes of other enterprises to be supported are consistent with the prediction process of the enterprise to be supported, so that detailed description is omitted.

The method comprises the steps of predicting the supporting effect of the enterprise to be supported in one or more evaluation dimensions to obtain one or more prediction results of the enterprise to be supported in the one or more evaluation dimensions, and obtaining the supporting effect of the enterprise to be supported in the one or more evaluation dimensions according to the one or more prediction results.

Optionally, the prediction of the support effect is specifically described by taking an enterprise development dimension, an enterprise growth dimension, and a support benefit dimension as examples in the present application, but the evaluation dimension is not limited in the present application.

Optionally, each evaluation dimension corresponds to one prediction model, wherein an enterprise development dimension corresponds to the first prediction model, an enterprise growth dimension corresponds to the second prediction model, and a support benefit dimension corresponds to the third prediction model, and each prediction model is used for predicting a support effect of the evaluation dimension corresponding to the prediction model. In practical applications, the prediction model may be one or more of the first prediction model, the second prediction model, and the third prediction model, that is, the supporting effect of the enterprise to be supported may be predicted by using one or more of the three prediction models.

The number of prediction models is not limited in the present application, and one prediction model may be used for prediction, or a plurality of prediction models may be used for prediction.

202: and obtaining an evaluation result of the industry support policy according to the prediction result.

The number of prediction models is different, the number of prediction results obtained is also different, and the manner of evaluating the industry support policy is also different.

Specifically, when one of the three prediction models is used to predict the support effect of the enterprise to be supported, the prediction result (i.e., the predicted support effect) corresponding to the prediction model is used to evaluate the industry support policy to obtain an evaluation result; when any two prediction models in the three prediction models are used for predicting the supporting effect of an enterprise to be supported, the prediction result of any one prediction model in the two prediction models can be used for evaluating the industry supporting policy to obtain an evaluation result, the two prediction results of the two prediction models can also be subjected to comprehensive treatment to obtain a final prediction result, and the final prediction result is used for evaluating the industry supporting policy to obtain an evaluation result; when the three prediction models are used for predicting the support effect of an enterprise to be supported, the prediction result of any one of the three prediction models can be used for evaluating the industry support policy to obtain an evaluation result, the two prediction results of any two of the three prediction models can also be used for evaluating the industry support policy to obtain an evaluation result, the three prediction results of the three prediction models can also be used for being integrated to obtain a final integrated result, and the industry support policy is evaluated according to the integrated result to obtain an evaluation result.

It can be seen that, in the embodiment of the application, the support result of the enterprise to be supported is predicted through the trained prediction model, so as to obtain the support result of each enterprise to be supported; and evaluating the advantages and disadvantages of the currently made industry support policy according to the support result so as to adjust the currently made industry support policy, thereby enabling the made industry support policy to achieve the optimal support effect.

It can be understood that before the supporting effect of the enterprise to be supported is predicted by using the prediction model, the prediction model (i.e., the first prediction model, the second prediction model, and the third prediction model described above) needs to be constructed by using the historical supporting data of M supported enterprises, where the supported enterprise is also referred to as a supported enterprise in this application.

Fig. 3 is a schematic flowchart of a method for constructing a prediction model according to an embodiment of the present application, where the method includes, but is not limited to, the following steps:

301: and determining a supporting result A of each supported enterprise in the dimension A according to the historical supporting data of each of the M supported enterprises.

The historical support data comprises support funds, revenue acceleration rate, employee acceleration rate, revenue amount and tax intake amount of each supported enterprise in the t year, and revenue acceleration rate, employee acceleration rate, revenue amount and tax intake amount in the t + k year, wherein the t year is the year of obtaining support, and k is an integer greater than or equal to 1.

The dimension a is any one of the enterprise development dimension, the enterprise growth dimension and the support benefit dimension, and the support result a is an actual support result, namely a real support result, corresponding to the dimension a, obtained according to the historical support data of each supported enterprise in the t year and the historical support data in the t + k year, wherein the actual support result includes a support level and a support effect.

The manner in which the actual support results are determined is described in detail below.

As shown in fig. 4, when the dimension a is a business development dimension, the supporting level and the supporting effect of each supported business in the business development dimension can be obtained according to the revenue speed increasing rate X1 and the employee speed increasing rate Y1 of each supported business in the t year, and the revenue speed increasing rate X2 and the employee speed increasing rate Y2 of the t + k year, where X in fig. 3 is X2-X1, and Y is Y2-Y1.

As shown in fig. 5, when the dimension a is a business growth dimension, the supporting level and the supporting effect of each supported business in the business growth dimension can be obtained according to the revenue increasing rate X1 and the revenue amount Y1 of the t-th year and the revenue increasing rate X2 and the revenue amount Y2 of the t + k-th year of each supported business, where X is 2-X1 and Y is 2-Y1 in fig. 4.

As shown in fig. 6, when the dimension a is a supporting benefit dimension, a supporting level and a supporting effect of each supported enterprise in the supporting benefit dimension can be obtained according to the supporting fund X1 obtained by each supported enterprise, the taxes amount Y1 in the t year, and the taxes amount Y2 in the t + k year;

among them, in FIG. 6

It can be seen that through the historical support data and the calculation formulas shown in fig. 4, 5, and 6, the support score in each dimension is calculated, the support effect corresponding to each support level can be obtained through the support score corresponding to the support level, the support effect in the support level is better when the support score is larger, and the support effects corresponding to the first support level, the second support level, the third support level, and the fourth support level are sequentially reduced.

It can be understood that the support grade is only a qualitative expression of the support result, and for the training of the prediction model, after the actual support result is obtained, only the support effect (support score) in the actual support result is used for model training.

302: and predicting the supporting effect of each supported enterprise according to the historical supporting data of each supported enterprise to obtain the supporting result A' of each supported enterprise in the dimension A.

The support result a' is a predicted support result obtained by predicting the support effect of each supported enterprise in the dimension a according to the historical support data of each supported enterprise in the year t, that is, assuming that the enterprise is supported in the year t, the support result of the enterprise may appear in the year t + k.

Before the supporting effect of the supported enterprises is predicted, firstly, a multivariate linear equation corresponding to each evaluation dimension is constructed through a stepwise regression algorithm, and then, the supporting effect of each supported enterprise is predicted by using the multivariate linear equation.

The idea of the stepwise regression algorithm is to introduce independent variables into the regression equation in sequence according to the significance of the effect of the independent variable X on the dependent variable Y. And when the first introduced independent variable becomes no longer significant due to the introduction of the subsequent independent variable, removing the independent variable from the regression equation until the independent variable which has no significant effect can be introduced at last and the independent variable which has no insignificant effect needs to be removed, and constructing a multivariate linear equation by using the retained variables.

In the application, 20 enterprise characteristics in table 1 are selected as independent variables X, the supporting effect is taken as dependent variables Y, and then, through a stepwise regression algorithm, the effect significance degree of the 20 enterprise characteristics on the supporting effect is known to be reduced in sequence according to the sequence that lower corner marks are sequentially increased. Determining p enterprise features from the 20 enterprise features through a stepwise regression algorithm, and constructing a multivariate linear equation between the support effect and the p enterprise features by using the p enterprise features:

y＝b₀+b₁*x₁+b₂*x₂+…+b_p*x_p；

table 1:

in the present application, x₁₄Increase the speed of revenue from the t year to the t + k year, x₁₅For increasing the increase in value from year t to year t + k, x₁₆For the speedup of the staff from the t year to the t + k year, x₁₇The tax payment acceleration from the t year to the t + k year, x₁₈For increasing the patent applications from year t to year t + k, x₁₉For the increase of social security payment amount from the t year to the t + k year, x₂₀The water and electricity consumption is increased from the t year to the t + k year.

Then, the enterprise data corresponding to the p enterprise characteristics of each supported enterprise is substituted into the multiple regression equation to obtain the predicted support effect of each supported enterprise

Then, rewriting the M supporting effects of the M supported enterprises into vectors, the following expression forms can be obtained:

wherein the content of the first and second substances,

predicted support effect, x, of an individual supported enterprise_ijEnterprise data corresponding to a jth enterprise feature for an ith one of the M supported enterprises.

303: and constructing a prediction model corresponding to the dimension A according to the support result A and the support result A' of each supported enterprise.

And constructing a prediction model of each evaluation dimension according to the actual support result and the prediction support result of each supported enterprise.

In particular, assume that

Actual support effect

Calculating the difference value sum of squares Q of the actual supporting effect and the predicted supporting effect of the M supported enterprises in each evaluation dimension, and then

Then, Q is respectively paired with b₀、b₁，…，b_pPartial derivatives are calculated, and each calculated partial derivative is equal to 0, and the following equation set can be obtained through simplification:

finally, solving the above equation set can solve b₀、b₁，…，b_pB is solved by₀、b₁，…，b_pThe multiple regression equation is substituted to obtain the target multiple regressionAnd the equation takes the target multiple regression equation as a prediction model of the dimension A. When the dimension A represents different dimensions in the three evaluation dimensions, a prediction model corresponding to each dimension can be obtained.

In some possible embodiments, after obtaining the target regression equation, a significance check is performed on the target regression equation to determine whether the predicted support effect has a linear relationship with the selected P business features. Wherein, the significance test can use an F test, which is as follows:

wherein the content of the first and second substances,

to normalize the variable regression equation, M is the number of samples.

And when the significance level a is 0.05, if F is more than Fa to indicate that the target regression equation is significant, taking the target regression equation as a prediction model corresponding to the dimension A, if F is less than or equal to Fa to indicate that the target regression equation is not significant, reselecting the independent variable X, namely reselecting the enterprise characteristics for model training, wherein the training process is consistent with the training process and is not described any more.

It can be understood that after the prediction model corresponding to each evaluation dimension is obtained, the current enterprise data of each enterprise to be supported can be input into the prediction model, the prediction result (support score) of the enterprise to be supported on the evaluation dimension is determined, then, the support level at which the support result corresponding to the prediction result is located is determined qualitatively according to the prediction result, and then, the support effect of the support result under the support level is determined quantitatively according to the prediction result; and finally, evaluating the industry support policy according to the qualitative support level and the quantitative support effect to obtain an evaluation result corresponding to the evaluation dimension.

The following describes a specific implementation manner for determining the support result of each evaluation dimension in combination with fig. 4, 5 and 6.

When the supporting effect of each enterprise to be supported is predicted in the enterprise development dimension, namely the supporting effect of each enterprise to be supported is predicted by using the first prediction model, a first prediction result corresponding to the enterprise development dimension can be obtained, and the first supporting result corresponding to the enterprise development dimension is determined according to the first prediction result.

Specifically, when the first prediction result is greater than 0, that is, the first prediction result is not an angle of a triangle and is greater than 0, as shown in fig. 4, the first support result belongs to a first support level, and when the first support result is located at the first support level, the larger the first prediction result is, the better the support effect corresponding to the first support result is, that is, the first support result is qualitatively evaluated according to the data type of the first prediction result, and the first support result is quantitatively evaluated according to the data size of the first prediction result;

when the first prediction result is smaller than 90 degrees, namely the first prediction result is a triangular angle, and the angle is smaller than 90 degrees, the first support result belongs to the second support level, and the larger the first prediction result is, the better the corresponding support effect is when the first support result belongs to the second support level;

when the first prediction result is greater than 90 degrees, namely the first prediction result is a triangle angle, and the angle is greater than 90 degrees, the first support result belongs to a third support level, and the larger the first prediction result is, the better the corresponding support effect is when the first support result is located at the third support level; when the first prediction result is less than 0, that is, the first prediction result is not a triangle angle and is less than 0, the first support result belongs to a fourth support level, and the larger the first prediction result is, the better the corresponding support effect is when the first support result belongs to the fourth support level.

When the supporting effect of each enterprise to be supported is predicted in the enterprise growth dimension, namely the supporting effect of each enterprise to be supported is predicted by using the second prediction model, a second prediction result corresponding to the enterprise growth dimension is obtained, and the second supporting result corresponding to the enterprise growth dimension is determined according to the second prediction result.

Specifically, when the second prediction result is greater than 0, that is, the second prediction result is not an angle of a triangle and is greater than 0, as shown in fig. 5, the second support result belongs to the first support level, and when the second support result is located at the first support level, the larger the second prediction result is, the better the support effect corresponding to the second support result is, that is, the second support result is qualitatively evaluated according to the data type of the second prediction result, and the second support result is quantitatively evaluated according to the data size of the second prediction result;

in addition, when the second prediction result is greater than 90 °, that is, the second prediction result is a triangle angle, and the angle is greater than 90 °, the second support result belongs to a second support level, and the larger the second prediction result is, the better the corresponding support effect is when the second support result is located at the second support level;

when the second prediction result is smaller than 0, that is, the second prediction result is not a triangle angle and is smaller than 0, the second support result belongs to a third support level, and the larger the second prediction result is, the better the corresponding support effect is when the second support result belongs to the third support level.

When the supporting effect of each enterprise to be supported is predicted in the supporting benefit dimension, namely the supporting effect of each enterprise to be supported is predicted by using the third prediction model, a third prediction result corresponding to the supporting benefit dimension is obtained, and a third supporting result corresponding to the enterprise development dimension is determined according to the third prediction result.

Specifically, when the third prediction result is greater than 0, that is, the third prediction result is not an angle of a triangle and is greater than 0, as shown in fig. 6, the third support result belongs to the first support level, and when the third support result is located at the first support level, the larger the third prediction result is, the better the support effect corresponding to the third support result is, that is, the third support result is qualitatively evaluated according to the data type of the third prediction result, and the third support result is quantitatively evaluated according to the data size of the third prediction result;

when the third prediction result is smaller than 90 degrees, that is, the third prediction result is a triangle angle, and the angle is smaller than 90 degrees, the third support result belongs to the second support level, and the larger the third prediction result is, the better the corresponding support effect is when the third support result belongs to the second support level;

when the third prediction result is greater than 90 degrees, that is, the third prediction result is a triangle angle, and the angle is greater than 90 degrees, the third support result belongs to a third support level, and the larger the third prediction result is, the better the corresponding support effect is when the third support result is located at the third support level;

when the third prediction result is less than 0, that is, the third prediction result is not a triangle angle and is less than 0, the third support result belongs to a fourth support level, and the larger the third prediction result is, the better the corresponding support effect is when the third support result belongs to the fourth support level.

In some possible embodiments, a mapping relationship between the preset support result and the evaluation result of the industry policy may be used to determine the evaluation result of the industry support policy according to the predicted support result and the mapping relationship.

For example, when the support result of any one evaluation dimension belongs to the first support level, it is determined that the evaluation result of the industry support policy in the evaluation dimension is "good", and to what extent the specific "good" is reflected by the support score corresponding to the support result. For example, if the supporting score of the first enterprise to be supported is 10 and the supporting score of the second enterprise to be supported is 20, it can be known that the supporting effect of the industry supporting policy on the first enterprise to be supported and the second enterprise to be supported is good, but the supporting effect on the second enterprise to be supported is better than that of the first enterprise to be supported; in addition, when the support result of any one evaluation dimension belongs to the second support level, determining that the evaluation result of the industry support policy in the evaluation dimension is "middle", and to what extent, reflecting the evaluation result by the support score corresponding to the support result; when the support result of any evaluation dimension belongs to the third support level, determining the evaluation result of the industry support policy as 'general' and the degree of 'general', and reflecting the evaluation result by the support score corresponding to the support result; when the support result of any one evaluation dimension belongs to the fourth support level, the evaluation result of the industry support policy is determined to be 'poor', and the degree of 'poor' is reflected by the support score corresponding to the support result.

It should be noted that the mapping relationship is only an example, and the present application is not limited thereto; in addition, for different evaluation dimensions, the preset mapping relations may be different or the same, which is not limited in the present application.

Furthermore, after the evaluation result of the industry support policy is obtained, the currently formulated industry support policy can be adjusted according to the evaluation result, and the enterprises to be supported are re-screened through the adjusted industry support policy, so that the formulated industry support policy can achieve the optimal support result. As shown in fig. 2B, after the evaluation result is determined, if the evaluation result reflects that the industry support policy is poor, the screening condition shown in fig. 2B is reset.

For example, when the support result in the support benefit dimension is a first support level, then the industry support policy is determined to be recommended as: recommending support, namely recommending support to the enterprise to be supported screened by the method shown in FIG. 2B, wherein the support index is

When the support result in the support benefit dimension is the second support level, the suggestion of the industry support policy is determined to be cautious support, that is, cautious support to the enterprise to be supported screened by fig. 2B, and the support index is

When the support result in the support benefit dimension is the third support level, the recommendation of the industry support policy is determined as resisting to support, namely resisting to support the enterprise to be supported screened by the method shown in FIG. 2BAnd a support index of

When the support result in the support benefit dimension is the fourth support level, it is determined that the proposal of the industry support policy is to attempt support, that is, to attempt to support the enterprise to be supported screened by fig. 2B, and the support index is

If the evaluation result is obtained by predicting the supporting effect of a plurality of enterprises to be supported, the proportion of each evaluation result in the evaluation result to all the evaluation results can be obtained, and when the proportion of the evaluation result which is 'good' is greater than the proportion of other evaluation results, the currently formulated industry supporting policy is better, adjustment is not needed, the industry policy can be used for screening the enterprises to be supported, and supporting funds are allocated to the screened enterprises to be supported; when the proportion of the evaluation result is 'middle' is larger than the proportion of other evaluation results, the currently made industry support policy is still operated, the industry support policy can be used for screening the enterprises to be supported, then the support fund is allocated to part of the screened enterprises to be supported in the enterprises to be supported for trial operation, if the support effect is good, the industry support policy can be continuously adopted for screening the enterprises to be supported, and if the support effect is not good, the industry support policy needs to be adjusted; in addition, when the ratio of the evaluation result "poor" is larger than the ratios of the other evaluation results, the industry support policy needs to be adjusted immediately, and the conditions for screening the enterprises to be supported need to be reset.

The support result of each enterprise in each dimension is obtained, and the screening condition shown in fig. 2B, that is, the formulated industry support policy, is adjusted according to the support result, so that the support result of the screened enterprise in each evaluation dimension falls into the first support level, and the support result of the industry support policy is optimized.

The industrial policy adjustment method is only an example, and the present application is not limited thereto.

The mode can predict the future supporting effect of the enterprise to be supported based on the construction of the model, evaluate the industry supporting policy through the predicted supporting result, and provide a reference direction for the specification and adjustment of the future industry supporting policy. Of course, errors inevitably occur in the prediction, and these errors cannot be seen manually. Therefore, statistical analysis is performed on the use of the supporting funds over the years, the supporting items, the historical supporting data and the like, the advantages and disadvantages of the historical industry supporting policy are determined from the real historical supporting result, and the method is an indispensable technical scheme for making the future industry supporting policy.

Fig. 7 is a schematic flowchart of a method for processing an industry support result according to an embodiment of the present application, which is the same as the embodiment shown in fig. 2A and fig. 3, and a description thereof will not be repeated here. The method includes, but is not limited to, the steps of:

701: and determining the historical support result between the t year and the t + k year according to the historical support data of the years from the t year to the t + k year.

The historical support results include actual support results for the supported enterprises, which can be determined in the above-mentioned manner and will not be described herein.

In addition, after a certain enterprise is supported in the t year, the historical supporting data of the enterprise in the t +1 th to t + k th year is continuously counted, and the historical supporting effect (the historical supporting level) of each supported enterprise is determined by using a pre-constructed evaluation model. Namely, a pre-constructed quadrant model is used along with the historical support data to determine the quadrant in which each of the supported enterprises is located in each of the evaluation dimensions.

Specifically, fig. 8 shows an evaluation model corresponding to the development dimension of a business, and as shown in fig. 8, a quadrant in which each supported business is located is determined according to the revenue increase rate of the t + k th year and the revenue increase rate of the t th year, and the employee increase rate of the t + k th year, where k is 1,2,3 …, and the origin of the coordinate axis (X is the origin) shown in fig. 8 (X is the origin of the coordinate axis)₀,Y₀) The average value corresponding to all the supported enterprises. I.e. obtaining each of the supported objectsThe method comprises the steps of enabling a company to increase revenue speed Y2 in t + k years and the revenue speed Y1 in the t-th year, then obtaining all difference values Y of all supported companies, averaging all difference values Y, and taking the average value as Y₀Similarly, all the revenue acceleration difference values X are averaged, and the average value is defined as X₀。

Further, when a supported enterprise is located in the first threshold, it is indicated that the development of the supported enterprise is in the growth stage, and it is indicated that the supporting effect on the supported enterprise is good; when the supported enterprise is located in the second quadrant, the development of the supported enterprise is in the potential period; when the supported enterprise is located in the third quadrant, the development of the supported enterprise is in a decline stage, and the supporting effect on the enterprise is poor; and when the supported enterprise is located in the fourth quadrant, the development of the supported enterprise is in the mature stage, and the supporting significance of the supporting funds on the enterprise is small.

Therefore, the supported enterprises in the t + k year can be evaluated in the enterprise development dimension to obtain the quadrant of each supported enterprise, and a satellite cloud graph corresponding to the enterprise development dimension is obtained, and then the satellite cloud graph is visually displayed to observe the supporting effect of each supported enterprise in the enterprise development dimension in the past year, so that data reference is provided for the establishment and adjustment of the future industrial supporting policy.

Fig. 9 shows an evaluation model corresponding to the growth dimension of the enterprise, and as shown in fig. 9, the quadrant in which each supported enterprise is located is determined according to the revenue increasing rate of the t + k year and the revenue increasing rate of the t year, and the revenue amount of the t + k year and the revenue amount of the t year, where k is 1,2, and 3 …, and the origin of the coordinate axis shown in fig. 9 is (X is: (X))₀,Y₀) Obtaining the difference Y between the revenue Y2 of each supported enterprise in t + k year and the revenue Y1 of t year, then obtaining all the differences Y of all the supported enterprises, taking the average value of all the differences Y, and taking the average value as Y₀Similarly, all the revenue acceleration difference values X are averaged, and the average value is defined as X₀。

Furthermore, when a certain supported enterprise is located in the first quadrant, the growth metaphor of the supported enterprise can be the south China tiger type, which indicates that the supporting effect on the supported enterprise is better; when the supported enterprise is in the second quadrant, the growth metaphor of the supported enterprise can be "large and stupid"; when the supported enterprise is located in the third quadrant, the growth metaphor of the supported enterprise can be a 'cat type', and the supporting effect on the enterprise is very poor; when the supported enterprise is located in the fourth quadrant, the growth of the supported enterprise can be compared with that of a "unicorn animal type", which shows that the growth of the enterprise is stable and the supporting funds do not contribute much to the growth of the enterprise.

Therefore, the supported enterprises in the t + k year can be evaluated in the enterprise growth dimension to obtain the quadrant in which each supported enterprise is located, the star cloud graph corresponding to the enterprise growth dimension can be obtained, the star cloud graph is visually displayed to observe the supporting effect of each supported enterprise in the enterprise development dimension in the past year, and data reference is further provided for the formulation and adjustment of the future industrial supporting policy.

Fig. 10 shows an evaluation model corresponding to the benefit dimension of support. As shown in fig. 10, the quadrant of each supported enterprise is determined according to the taxes of the t + k year, the taxes of the t year and the supporting funds obtained in the t year, k is 1,2,3 …, and the ordinate axis Y shown in fig. 10 is the input-output ratio of the t + k year to the t year, that is, the input-output ratio of the t + k year to the t year

Wherein Y2 is the tax payment amount of the t + k year, Y1 is the tax payment amount of the t year, X is the supporting fund, and the ordinate axis X is the tax payment acceleration rate of the t + k year relative to the t year, namely the tax payment composite acceleration rate in the k year. Similarly, the origin of the coordinate axes shown in FIG. 10 is (X)₀,Y₀) Obtaining the average value corresponding to all the supported enterprises, namely obtaining the input-output ratio Y of the t + k year to the t year of each supported enterprise, then obtaining all the Y of all the supported enterprises, taking the average value of all the Y, and taking the average value as Y₀The average value of all tax rate-increasing X is calculated and the average value is used as X₀。

Furthermore, when a certain supported enterprise is located in the first quadrant, the supporting benefit metaphor of the supported enterprise can be a "Zhao cloud type", which indicates that the supporting effect on the supported enterprise is better; when the supported enterprise is in the second quadrant, the supporting benefits of the supported enterprise may be compared to a "model of a cane-chasing"; when the supported enterprise is positioned in the third quadrant, the supporting benefit of the supported enterprise can be compared with that of the 'fighting type', and the supporting effect on the enterprise is very poor; when the supported enterprise is located in the fourth quadrant, the supporting benefit of the supported enterprise can be compared to the "welfare type", which means that the supporting significance of the supporting fund to the enterprise is not great.

Therefore, the supported enterprises in the t + k year can be analyzed in the supporting benefit dimension to obtain the quadrant in which each supported enterprise is located, the star cloud graph corresponding to the supporting benefit dimension is obtained, the star cloud graph is visually displayed to observe the supporting effect of each supported enterprise in the supporting benefit dimension, and data reference is provided for making and adjusting the supporting policy of the future industry.

702: and displaying a history support result on a visual interface.

Fig. 11 shows a schematic view of a star cloud diagram of a holding effect. The method comprises the steps of obtaining a quadrant of each supported enterprise in a target year by using an evaluation model corresponding to each evaluation dimension, determining a star cloud image of each evaluation dimension according to the quadrant, and displaying the star cloud image of each evaluation dimension on a visual interface, wherein the target year is a historical year selected by a user. Fig. 11 shows only a star cloud diagram in the enterprise development dimension, and other star cloud diagrams are consistent with the star cloud diagram and are not described again.

In addition, as shown in fig. 11, the added value of the supported enterprise can be analyzed to count the trend of the enterprise added value of each supported enterprise after being supported; and analyzing and displaying the enterprise tax tendency of each supported enterprise, analyzing the number of the staff of each supported enterprise to obtain the number tendency of the staff of each supported enterprise, and the like.

Through statistics and analysis of the planet cloud pictures of the supported enterprises, the use correctness of the historical supported funds is judged conveniently, and a reference direction is provided for the use of the subsequent industry supported funds conveniently.

In some possible embodiments, as shown in fig. 12, the usage of the held funds may be analyzed, that is, information such as budget held funds invested each year, actually used held funds, industry projects held each year, number of enterprises held each year, etc. is counted, and then the usage analysis result of the held funds of the year is displayed according to the visual interface of the selected year.

In some possible embodiments, as shown in fig. 12, the usage of the supporting funds may also be analyzed and the results of the analysis visually displayed. For example, the budget investment of the supporting funds in x years and the ratio of the budget investment relative to the annual financial income are counted and visually displayed in a statistical chart manner; similarly, the amount of the actually paid support money in x years, the quantity of the obtained support items in each area, the execution rate of the support funds (the ratio of the actually paid support funds in each year to the budget investment) and the use of the support funds are counted, and each statistical result is visually displayed.

By carrying out statistical analysis on the use of the historical support fund, the historical support situation is known, and a reference is provided for the subsequent support policy.

In some possible embodiments, as shown in fig. 13, the use of the supporting funds can be analyzed by industry and visualized in a statistical chart manner. For example, enterprise information of an enterprise with a holding amount at TOP10 is obtained and visually displayed; acquiring the industry field supported by the supporting fund, acquiring the proportion of the supporting fund acquired by each industry, and performing visual display; in addition, a trend chart of economic growth of the supporting enterprise relative to economic growth of the whole market is obtained and displayed; in addition, the change of the number of supported enterprises in k years can be acquired, so that the growth change of the number of supported enterprises can be acquired, and the government fund investment is clear.

By carrying out statistical analysis on the supporting capital sub-industries, the heading of historical supporting capital is clarified, and a reference direction is provided for supporting which industries go in the future.

In some possible embodiments, as shown in fig. 14, the industrial policy may be further sketched to evaluate the historical industrial policy, specifically, the most "added value" policy is determined by reflecting the return of the industrial policy through an input-output ratio, which is X1/Y1, where X1 is the average value of the tax payment sum of all enterprises related to the industrial policy in t years to t + k years under any one industrial policy, and Y1 is the average value of the held fund sum of all enterprises in t years to t + k years; reflecting the policy action through the power assistance index to determine the most' power giving policy

Wherein, X2 is the average value of the earning speed increase of all enterprises related to the industrial policy from t year to t + k year under any industrial policy, and Y2 is the average value of the employee speed increase of all enterprises from t year to t + k year; reflecting the coverage of the industry policy through a coverage index to determine the most 'popular' policy, wherein the coverage index is X3/Y3, X3 is the number of enterprises supported by the industry policy under any industry policy, and Y3 is the ratio of the number of all enterprises corresponding to the industry policy; in addition, the support times of each enterprise can be counted, and visual display is carried out according to the sequencing mode of the support times so as to determine the most favored enterprise; in addition, enterprises which are moved or cancelled in the supported enterprises can be counted and visually displayed to determine the most 'falling-to-empty' policy and the like.

It should be noted that the statistical analysis diagrams shown in fig. 11, 12, 13, and 14 are only exemplary diagrams, and are not limited to the statistical analysis of historical support data.

It can be seen that, in the embodiment of the present application, by analyzing and displaying the supporting situation of the supported enterprise, the use purpose of the support, the distribution information of the supporting fund, the execution rate of the supporting fund, and the like can be known in time; therefore, the support result corresponding to the historical support policy can be clarified from multiple dimensions, so that data reference is provided for the future establishment of the industrial support policy.

Fig. 15 is an evaluation apparatus 1500 for industry support policy according to an embodiment of the present disclosure, which includes:

the prediction unit 1510 is configured to predict a support effect of an enterprise to be supported by using a prediction model to obtain a prediction result, where the enterprise to be supported is screened from multiple enterprises according to a preset industry support policy;

the determining unit 1520 is configured to obtain an evaluation result of the industry support policy according to the prediction result.

In some possible embodiments, the evaluation apparatus 1500 further includes: a training unit 1530, before the prediction unit 1510 predicts the supporting effect of the enterprise to be supported by using the prediction model, the training unit 1530 is configured to construct the prediction model by using the historical supporting data of the M supported enterprises, wherein the prediction model comprises one or more of a first prediction model corresponding to an enterprise development dimension, a second prediction model corresponding to an enterprise growth dimension, and a third prediction model corresponding to a supporting benefit dimension,

in constructing the predictive model using historical support data for M supported businesses, the training unit 1530 is specifically configured to:

in determining the support result a of each supported enterprise in dimension a according to the historical support data of each of the M supported enterprises, the training unit 1530 is specifically configured to:

In some possible embodiments, in terms of obtaining the evaluation result of the industry support policy according to the prediction result, the determining unit 1520 is specifically configured to:

Fig. 16 is a processing device 160 for industry support results provided by an embodiment of the present application, which may include:

a determining unit 1610, configured to determine a historical support result between the tth year and the t + k year according to historical support data of each year from the tth year to the t + k year;

the display unit 1620 is configured to display the history support result on a visual interface.

in terms of determining the historical support result between the tth year and the t + k year according to the historical support data of each year from the tth year to the t + k year, the determining unit 1610 is specifically configured to:

in determining the historical support result of each supported enterprise in dimension a according to the enterprise data of each supported enterprise, the determining unit 1610 is specifically configured to:

In some possible embodiments, the historical support data includes support fund usage information, and in terms of determining the historical support result of each supported enterprise in dimension a according to the enterprise data of each supported enterprise, the determining unit 1610 is specifically configured to:

Fig. 17 is an apparatus 1700 for evaluating an industry support policy according to an embodiment of the present application, including:

a processor 1730, communication interface 1720, and memory 1710 coupled to each other; for example, processor 1730, communication interface 1720, and memory 1710 are coupled via bus 1740.

The Memory 1710 may include, but is not limited to, Random Access Memory (RAM), Erasable Programmable Read Only Memory (EPROM), Read-Only Memory (ROM), or portable Read-Only Memory (CD-ROM), among others, and the Memory 1710 may be used for related instructions and data.

The processor 1730 may be one or more Central Processing Units (CPUs), and in the case where the processor 1730 is one CPU, the CPU may be a single-core CPU or a multi-core CPU.

The processor 1730 is configured to read the program code stored in the memory 1710 and cooperate with the communication interface 1720 to perform some or all of the steps of the method performed by the apparatus 1700 for evaluating industry-supported policies according to the above-described embodiments of the present application.

The processor 1730 is configured to predict a supporting effect of an enterprise to be supported by the prediction model to obtain a prediction result, where the enterprise to be supported is screened from multiple enterprises according to a preset industry supporting policy;

the processor 1730 is further configured to obtain an evaluation result of the industry support policy according to the prediction result.

As can be seen, in the embodiment of the present application, the processor 1730 predicts the support result of the enterprise to be supported through the prediction model, to obtain the support result of each enterprise to be supported; and evaluating the advantages and disadvantages of the currently made industry support policy according to the support result so as to adjust the currently made industry support policy, thereby enabling the finally made industry support policy to achieve the optimal support effect.

In some possible embodiments, before processor 1730 predicts the support effect for the supported enterprise using the prediction model, processor 1730 is further configured to construct the prediction model using historical support data for the M supported enterprises, wherein the prediction model comprises one or more of a first prediction model corresponding to an enterprise development dimension, a second prediction model corresponding to an enterprise growth dimension, and a third prediction model corresponding to a support benefit dimension,

in constructing the predictive model using historical support data for the M supported enterprises, processor 1730 is specifically configured to:

in determining a support result a for each supported enterprise in dimension a from the historical support data for each of the M supported enterprises, processor 1730, is specifically configured to:

In some possible embodiments, in obtaining the evaluation result of the industry support policy according to the prediction result, the processor 1730 is specifically configured to:

Fig. 18 provides an industry support result processing apparatus 1800 for an embodiment of the present application, including:

a processor 1840, a communication interface 1830, a memory 1820, and a display 1810 coupled to each other; such as processor 1840, communication interface 1830, memory 1820, and display 1810, are coupled via bus 1850.

The Memory 1820 may include, but is not limited to, Random Access Memory (RAM), Erasable Programmable Read-Only Memory (EPROM), Read-Only Memory (ROM), or portable Read-Only Memory (CD-ROM), among others, and the Memory 1820 may be used for related instructions and data.

The processor 1840 may be one or more Central Processing Units (CPUs), which may be a single core CPU or a multi-core CPU in the case where the processor 1840 is one CPU.

The processor 1840 is configured to read program code stored in the memory 1820 and cooperate with the communication interface 1830 to perform some or all of the steps of the method performed by the industry supported result processing device 1800 in the embodiments described above.

For example, the processor 1840 is configured to determine a historical support result between the tth year and the t + k year according to the historical support data of each year from the tth year to the t + k year;

the processor 1840 is further configured to control the display 1810 to display the historical support result on a visual interface.

in determining historical support outcomes between the t year and the t + k year based on historical support data for each year from the t year to the t + k year, the processor 1840 is specifically configured to:

in determining the historical support result for each supported enterprise in dimension A based on the enterprise data for each supported enterprise, a processor 1840 is specifically configured to:

In some possible embodiments, the historical support data includes supported fund usage information, and in determining the historical support result for each supported enterprise in dimension a based on the enterprise data for each supported enterprise, the processor 1840 is specifically configured to:

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, digital subscriber line) or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., compact disk), or a semiconductor medium (e.g., solid state disk), among others. In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the foregoing embodiments, the descriptions of the embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is merely a logical division, and the actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted or not executed. In addition, the indirect coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, indirect coupling or communication connection of devices or units, and may be electrical or in other forms.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage media may include, for example: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

Claims

1. A method for evaluating industry-supported policies, comprising:

2. The method of claim 1, wherein prior to predicting the support effect of the enterprise to be supported using the predictive model, the method further comprises:

3. The method according to claim 1 or 2, wherein the historical support data comprises support funds, revenue acceleration, employee acceleration, revenue amount and tax amount in t year, and revenue acceleration, employee acceleration, revenue amount and tax amount in t + k year, wherein the t year is the year of obtaining support, and k is an integer greater than or equal to 1;

the determining a support result A of each supported enterprise in dimension A according to the historical support data of each of the M supported enterprises includes:

4. The method of claim 2 or 3, wherein the deriving the evaluation of the industry support policy based on the prediction comprises:

5. The method of claim 4,

when the first prediction result is greater than 0, the first support result belongs to a first support level, and the larger the first prediction result is, the better the support effect corresponding to the first support result is;

6. The method of claim 4,

when the second prediction result is greater than 0, the second support result belongs to a first support level, and the larger the second prediction result is, the better the support effect corresponding to the second support result is;

7. The method of claim 4,

when the third prediction result is greater than 0, the third support result belongs to a first support level, and the larger the third prediction result is, the better the support effect corresponding to the third support result is;

8. A method of processing an industry support result, comprising:

and displaying the historical support result on a visual interface.

9. The method of claim 8, wherein the support outcomes include a first support outcome corresponding to a business development dimension, a second support outcome corresponding to a business growth dimension, and a third support outcome corresponding to a support benefits dimension, the historical support data includes one or more of business data for each supported business, and determining the historical support outcomes between the t year and the t + k year from the historical support data for each year from the t year to the t + k year comprises:

10. The method of claim 9, wherein the business data includes supported funds, revenue acceleration, employee acceleration, revenue amount, and tax revenue amount obtained by each supported business, and wherein determining historical support results for each supported business in dimension a based on the business data for each supported business comprises:

11. The method of claim 8, wherein the historical support data includes supported fund usage information, and wherein determining the historical support outcome between the tth year and the t + k year from the historical support data for each of the tth year to the t + k year comprises:

12. An apparatus for evaluating industry-supported policies, comprising:

13. The apparatus of claim 12, wherein the evaluating means further comprises: a training unit, configured to construct a prediction model using historical support data of the M supported enterprises before the prediction unit predicts the support effect of the enterprise to be supported using the prediction model, wherein the prediction model includes one or more of a first prediction model corresponding to an enterprise development dimension, a second prediction model corresponding to an enterprise growth dimension, and a third prediction model corresponding to a support benefit dimension,

14. The apparatus according to claim 12 or 13, wherein the historical support data includes support funds, revenue acceleration, employee acceleration, revenue amount and tax amount for the t year, and revenue acceleration, employee acceleration, revenue amount and tax amount for the t + k year, the t year being the year in which support is obtained, k being an integer greater than or equal to 1;

in terms of determining a historical support result a of each supported enterprise in dimension a according to the historical support data of each of the M supported enterprises, the training unit is specifically configured to:

15. The apparatus of claim 13 or 14,

in terms of obtaining an evaluation result of the industry support policy according to the prediction result, the determining unit is specifically configured to:

16. The apparatus of claim 15,

17. The apparatus of claim 15,

18. The apparatus of claim 15,

19. An apparatus for processing results of industry support, comprising:

20. The apparatus of claim 19, wherein the support results comprise a first support result corresponding to a business development dimension, a second support result corresponding to a business growth dimension, and a third support result corresponding to a support benefit dimension, the historical support data comprises one or more of business data for each supported business,

21. The apparatus of claim 20, wherein the business data includes supported funds, revenue acceleration, employee acceleration, revenue amount, and tax amount obtained by each supported business,

22. The apparatus according to claim 19, wherein the historical support data includes supported fund usage information, and in determining the historical support result for each supported enterprise in dimension a based on the enterprise data for each supported enterprise, the determining unit is specifically configured to:

23. An apparatus for evaluating industry-supported policies, comprising:

24. An apparatus for processing results of industry support, comprising:

25. A computer-readable storage medium, characterized in that a computer program is stored, which is executed by hardware to implement the method of any one of claims 1 to 7 performed by an industry support result evaluation device or the method of any one of claims 8 to 11 performed by an industry support result processing device.