Index value determination method and device based on master-slave game theory, medium, equipment and computer program product

Abstract

The embodiment of the invention discloses an index value determination method and device based on a master-slave game theory, a medium, equipment and a computer program product. In a given guidance index value range set and a declaration index value range set, according to a total regional revenue function and a regional revenue function, the index value is determined according to the total regional revenue function and the regional revenue function; and respectively screening out an optimal static guidance index value set and an optimal static declaration index value set, and determining a dynamic guidance index value of the next time period in combination with the guidance index value set and the declaration index value set which are set in the current time period and the declaration index value of each region. And determining a dynamic declaration index value of each region in the next time period by combining a target declaration index value of the current time period, other declaration index values except the target declaration index value in the declaration index values of each region, a guide index value set of the current time period and the static declaration index value set. The method can improve the matching degree between the index issuing value and the actual condition of each city, and improves the economic stability.

Description

Technical Field

[0001] The present application relates to the financial field, and specifically relates to a method, device, medium, equipment and computer program product for determining index values based on the principal-agent game theory. Background Art

[0002] The existing economic operation early warning and regulation are mainly carried out through the method of "a table, a meeting, and a report", which mainly involves two parts: the issuance of annual plan indicators and the early warning and regulation of the completion of annual plan indicators. For the issuance of annual plan indicators, first, each prefecture-level city uniformly declares the index values. If the declared index values deviate from the actual situation, they will be sent back for re-declaration until the declared index values of all prefecture-level cities are within a reasonable range. Then, the provincial company uniformly issues the annual plan index values to each prefecture-level city based on the overall situation.

[0003] Principal-agent game depicts the asymmetric power structure in reality through a dynamic sequential decision-making mechanism. The existence and solution method of its equilibrium solution provide theoretical support for policy-making, market competition, etc. The core feature is that the participants are divided into leaders and followers. The leaders take the initiative by making prior decisions, while the followers adjust their own behaviors according to the strategies of the leaders. This model constructs a generalized principal-agent self-game model of one principal and multiple agents based on the realistic relationship structure of economic operation. One principal refers to the provincial bureau, which has the ability to set, allocate, guide and regulate the annual plan indicators of each prefecture-level city prior to the actions of each prefecture-level city. Multiple agents refer to each prefecture-level city, which has the ability to declare its own annual plan indicators within the scope of the guidance and regulation of the provincial bureau. Generalized means that each other's behaviors are within a certain range of constraints, and this range of constraints will also be affected by the behaviors of other parties. The game model emphasizes that both the provincial bureau and each prefecture-level city should take appropriate actions to make their own functional effects the best, and the behaviors of each other will also affect each other's functional effects. The self-game model is to spontaneously conduct the entire game by the provincial bureau in the capacity of a third party. Its purpose is to realize the organic integration of the planned economy and the market economy, give play to the advantages of both, avoid the reverse trends of both, and achieve steady progress through the mechanism design of this one principal and multiple agents generalized self-game model.

[0004] In the related art, due to the existence of a certain information asymmetry between the province and each prefecture-level city and the conflict between individual rationality and collective rationality, this may lead to a low matching degree between the issued values of the annual plan indicators and the actual situations of each prefecture-level city, resulting in each prefecture-level city being unable to complete the issued indicators and poor economic stability. Summary of the Invention

[0005] The embodiments of the present application provide a method, device, medium, equipment and computer program product for determining index values based on the principal-agent game theory, which can improve economic stability.

[0006] To solve the above technical problems, the embodiments of the present application provide the following technical solutions:

[0007] A method for determining index values based on the principal-agent game theory, comprising:

[0008] Obtain a set of guidance index value ranges and a set of declared index value ranges. The set of guidance index value ranges includes the guidance index value ranges for each region, and the set of declared index value ranges includes the declared index value ranges for each region;

[0009] Based on the total region revenue function and the region revenue function, screen out a set of static guidance index values from the set of guidance index value ranges, and screen out a set of static declared index values from the set of declared index value ranges. The set of static guidance index values includes the static guidance index values for each region, and the set of static declared index values includes the static declared index values for each region;

[0010] Obtain the set of guidance index values, the set of declared index values, and the declared index values for each region at the current time period;

[0011] Determine the dynamic guidance index values for the next time period according to the set of guidance index values, the set of declared index values, and the set of static guidance index values at the current time period;

[0012] For each region, determine the dynamic declared index values for the next time period according to the target declared index value at the corresponding current time period, the other declared index values except the target declared index value among the declared index values for each region, the set of guidance index values at the current time period, and the set of static declared index values, so as to conduct index value guidance for the next time period according to the dynamic guidance index values, and conduct index value declaration for the next time period according to the dynamic declared index values for each region.

[0013] An index value determination device, comprising:

[0014] A first acquisition unit for acquiring a set of guidance index value ranges and a set of declared index value ranges. The set of guidance index value ranges includes the guidance index value ranges for each region, and the set of declared index value ranges includes the declared index value ranges for each region;

[0015] A screening unit for screening out a set of static guidance index values from the set of guidance index value ranges and screening out a set of static declared index values from the set of declared index value ranges based on the total region revenue function and the region revenue function. The set of static guidance index values includes the static guidance index values for each region, and the set of static declared index values includes the static declared index values for each region;

[0016] A second acquisition unit for acquiring the set of guidance index values, the set of declared index values, and the declared index values for each region at the current time period;

[0017] A first determination unit, configured to determine a dynamic guidance index value for the next time period according to the set of guidance index values, the set of declared index values, and the set of static guidance index values in the current time period;

[0018] A second determination unit, for each region, according to the target declared index value in the corresponding current time period, other declared index values in the declared index values of each region except the target declared index value, the set of guidance index values in the current time period, and the set of static declared index values, determine the dynamic declared index value for each region in the next time period, so as to conduct index value guidance for the next time period according to the dynamic guidance index value, and conduct index value declaration for the next time period according to the dynamic declared index value of each region.

[0019] In some embodiments, the screening unit includes:

[0020] A first acquisition subunit, configured to acquire a set of historical guidance index values and acquire a set of historical declared index values for each region;

[0021] A first determination subunit, configured to determine an initial set of guidance index values from the set of guidance index value ranges and determine an initial declared index value for each region from the set of declared index value ranges;

[0022] A second determination subunit, configured to determine a set of guidance index value constraint ranges according to the set of historical guidance index values and the initial declared index value of each region;

[0023] A third determination subunit, configured to determine the total regional revenue value corresponding to each candidate set of guidance index values in the set of guidance index value constraint ranges through a total regional revenue function, and determine the target set of guidance index values corresponding to the maximum total regional revenue value;

[0024] A fourth determination subunit, for each region, according to the target set of guidance index values, the corresponding historical declared index values, and the initial declared index values of other regions, determine the declared index value constraint range;

[0025] A fifth determination subunit, configured to determine the regional revenue value corresponding to each candidate declared index value in the declared index value constraint range through a regional revenue function, and determine the target declared index value corresponding to the maximum regional revenue value;

[0026] The sixth determination subunit is configured to, when the sum of each guidance index value in the target guidance index value set is different from the sum of the target declaration index values corresponding to each region, determine the target declaration index value of each region as the corresponding initial declaration index value, determine the sum of each guidance index value in the target guidance index value set as the initial guidance index value, and return to execute the step of determining the guidance index value constraint range set according to the historical guidance index value set and the initial declaration index value of each region until the sum of each guidance index value in the target guidance index value set is the same as the sum of the target declaration index values corresponding to each region. Then, determine the finally obtained target guidance index value set as the static guidance index value set, and determine the finally obtained target declaration index value of each region as the static declaration index value, so as to obtain the static declaration index value set.

[0027] In some embodiments, the third determination subunit is configured to:

[0028] For each candidate guidance index value set in the guidance index value constraint range set, based on the candidate guidance index value set and the sum of each initial declaration index value, determine the total regional planned index value;

[0029] Through the index revenue sub-function in the total regional revenue function, determine the total regional index revenue value corresponding to the total regional planned index value;

[0030] From multiple total guidance index values whose distance values from the sum value of the candidate guidance index value set are within the first preset distance value, screen out the first minimum distance value from the sum value of the initial declaration index value;

[0031] Calculate the standard deviation between the candidate guidance index value set and the current period guidance index value set to obtain the growth rate standard deviation;

[0032] According to the total regional index revenue value, the first minimum distance value, and the growth rate standard deviation, determine the total regional revenue value, and obtain the total regional revenue value corresponding to each candidate guidance index value set.

[0033] In some embodiments, the fifth determination subunit is configured to:

[0034] For each candidate declaration index value, obtain the regional revenue sub-function of the corresponding region in the regional revenue function;

[0035] Based on the candidate guidance index value set and the sum of each initial declaration index value, determine the regional planned index value;

[0036] Through the regional revenue sub-function, determine the regional index revenue value corresponding to the regional planned index value;

[0037] From multiple declared index values whose distance values from the initial declared index value corresponding to the region are within the first preset distance value, screen out the second smallest distance value of the target guidance index value corresponding to the region in the target guidance index value set.

[0038] According to the regional index benefit value and the second smallest distance value, determine the regional benefit value, and obtain the regional benefit value corresponding to each candidate declared index value.

[0039] In some embodiments, the first determination unit includes:

[0040] A first calculation subunit, configured to calculate the total regional prediction value by using the total regional expectation function for the declared index value set and the static guidance index value set in the current period.

[0041] A first weighted summation subunit, configured to perform weighted summation on the guidance index value set and the total regional prediction value in the current period to obtain the dynamic guidance index value in the next period.

[0042] In some embodiments, the second determination unit includes:

[0043] A first acquisition subunit, configured to acquire the regional expectation function corresponding to each region for each region.

[0044] A second calculation subunit, configured to calculate the regional prediction value by using the regional expectation function for the guidance index value set, the static declared index value set, and other declared index values except the target declared index value in the declared index values of each region in the current period.

[0045] A second weighted summation subunit, configured to perform weighted summation on the target declared index value in the current period corresponding to the region and the regional prediction value to obtain the dynamic declared index value in the next period.

[0046] In some embodiments, the device further includes:

[0047] A third acquisition unit, configured to acquire the index feedback value of each index type in the feedback sub-period in the next period for each region, and determine the operation status evaluation value of each index type in the feedback sub-period in the next period for each region based on the index proportion mean value of the historical sub-periods of the feedback sub-period, the standard deviation of the index proportion of the historical sub-periods of the feedback sub-period, the cumulative index proportion mean value from the historical period to the feedback sub-period, and the cumulative index proportion standard deviation from the historical period to the feedback sub-period.

[0048] A comparison unit, configured to compare the operation status evaluation value of each index type with the corresponding regulation and control recommendation value.

[0049] A third determination unit, configured to determine, as a target index type, an index type in the target area whose operation status evaluation value is different from the corresponding regulation recommendation value;

[0050] A fourth acquisition unit, configured to acquire a plurality of warning intervals corresponding to the target index type in the target area;

[0051] A fourth determination unit, configured to determine a target warning interval in which the target operation status evaluation value of the target index type is located;

[0052] A fifth determination unit, configured to determine a target warning level corresponding to the target warning interval based on a preset mapping relationship between the warning interval and the warning level;

[0053] A generation unit, configured to generate a prompt message to prompt that the operation status evaluation value of the target index type in the target area is at the target warning level.

[0054] In some embodiments, the device further includes:

[0055] A fifth acquisition unit, configured to acquire a first regulation index value range set for the target index type in the target area, where the first regulation index value range set includes the regulation index value ranges of each sub-period from the feedback sub-period to the last sub-period in the next period;

[0056] A first simulation unit, configured to simulate corresponding total area index values according to different regulation index value sets combined by the regulation index value ranges of each sub-period;

[0057] A sixth determination unit, configured to determine, as a first candidate regulation index value set of the target index type in the target area from the feedback sub-period to the last sub-period, the regulation index value set corresponding to the maximum total area index value;

[0058] A sixth acquisition unit, configured to acquire the upper and lower limit mean values of the sub-period completion index ratios of each sub-period from the feedback sub-period to the last sub-period in the next period;

[0059] A first adjustment unit, configured to adjust the upper limit value or the lower limit value of the sub-period completion index ratio of the sub-period in which the regulation index value in the first candidate regulation index value set is different from the upper and lower limit mean values of the sub-period completion index ratio corresponding to the sub-period, to obtain the adjusted upper limit value and the adjusted lower limit value of the sub-period completion index ratio of each sub-period;

[0060] The first guiding unit is used to, when the upper limit value of the sub-period completion index ratio of a sub-period is less than the lower limit value of the sub-period completion index ratio of the corresponding sub-period, guide the index value of the target index type in the target area for the next period starting from the feedback sub-period according to the first candidate regulation index value set.

[0061] In some embodiments, the sixth obtaining unit includes:

[0062] The second obtaining subunit is used to obtain the upper limit value of the sub-period completion index ratio and the lower limit value of the sub-period completion index ratio for each sub-period from the feedback sub-period to the last sub-period in the next period.

[0063] The seventh determining subunit is used to determine the average value of the upper and lower limits of the completion index ratio for each sub-period based on the upper limit of the sub-period completion index ratio and the lower limit of the sub-period completion index ratio for each sub-period.

[0064] In some embodiments, the first adjustment unit includes:

[0065] The eighth determining subunit is used to, when there is a regulation index value of a first sub-period in the first candidate regulation index value set that is greater than the average value of the upper and lower limits of the completion index ratio of the target sub-period, determine a first adjustment value based on the regulation index value of the first sub-period and the average value of the upper and lower limits of the completion index ratio of the first sub-period.

[0066] The first adjustment subunit is used to adjust the lower limit value of the sub-period completion index ratio of the first sub-period according to the first adjustment value.

[0067] The ninth determining subunit is used to, when there is a regulation index value of a second sub-period in the first candidate regulation index value set that is less than the average value of the upper and lower limits of the completion index ratio of the target sub-period, determine a second adjustment value based on the regulation index value of the second sub-period and the average value of the upper and lower limits of the completion index ratio of the second sub-period.

[0068] The second adjustment subunit is used to adjust the upper limit value of the sub-period completion index ratio of the second sub-period according to the second adjustment value.

[0069] In some embodiments, the device further includes:

[0070] The seventh determining unit is used to, when there is an upper limit value of the sub-period completion index ratio of a third sub-period that is less than the lower limit value of the sub-period completion index ratio of the corresponding sub-period, determine the average value of the upper and lower limits of the adjusted upper limit value of the sub-period completion index ratio and the lower limit value of the sub-period completion index ratio for each sub-period from the feedback sub-period to the fourth sub-period before the third sub-period as the regulation index value of the corresponding sub-period.

[0071] An eighth determination unit, configured to determine an upper limit value or a lower limit value of a sub-period completion index ratio of the third sub-period as a regulation index value of the third sub-period;

[0072] A seventh acquisition unit, configured to acquire a second set of regulation index value ranges for the target index type in the target area, where the second set of regulation index value ranges includes regulation index value ranges for each sub-period from the fifth sub-period after the third sub-period to the last sub-period in the next period;

[0073] A second simulation unit, configured to simulate corresponding total area index values according to different sets of regulation index values combined from the regulation index value ranges for each sub-period from the fifth sub-period after the third sub-period to the last sub-period;

[0074] A ninth determination unit, configured to determine the set of regulation index values corresponding to the maximum total area index value as a second candidate set of regulation index values for the target index type in the target area from the fifth sub-period after the third sub-period;

[0075] An eighth acquisition unit, configured to acquire the average of the upper and lower limits of the sub-period completion index ratio for each sub-period from the fifth sub-period to the last sub-period in the next period;

[0076] A second adjustment unit, configured to adjust the upper limit value or the lower limit value of the sub-period completion index ratio of the sub-period in which the regulation index value in the second candidate set of regulation index values is different from the average of the upper and lower limits of the sub-period completion index ratio of the corresponding sub-period, to obtain the adjusted upper limit value and the adjusted lower limit value of the sub-period completion index ratio for each sub-period;

[0077] A second guidance unit, configured to, when there is no case where the upper limit value of the sub-period completion index ratio of a sub-period is less than the lower limit value of the sub-period completion index ratio of the corresponding sub-period, perform index value guidance for the target index type in the target area from the feedback sub-period in the next period according to the regulation index values for each sub-period from the third feedback sub-period to the fourth sub-period, the regulation index value of the third sub-period, and the second candidate set of regulation index values from the fifth sub-period after the third sub-period.

[0078] A computer-readable storage medium storing multiple instructions, where the instructions are suitable for being loaded by a processor to execute the above method for determining index values based on the master-slave game theory.

[0079] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above method for determining the index value based on the master-slave game theory is implemented.

[0080] A computer program product or a computer program includes computer instructions stored in a storage medium. The processor of the computer device reads the computer instructions from the storage medium, and the processor executes the computer instructions to implement the above method for determining the index value based on the master-slave game theory.

[0081] In the embodiment of the present application, by obtaining a set of guidance index value ranges and a set of declared index value ranges, the set of guidance index value ranges includes the guidance index value ranges of each region, and the set of declared index value ranges includes the declared index value ranges of each region; based on the total region revenue function and the region revenue function, a set of static guidance index values is screened out from the set of guidance index value ranges, and a set of static declared index values is screened out from the set of declared index value ranges. The set of static guidance index values includes the static guidance index values of each region, and the set of static declared index values includes the static declared index values of each region; obtain the set of guidance index values, the set of declared index values, and the declared index values of each region at the current time period; according to the set of guidance index values, the set of declared index values, and the set of static guidance index values at the current time period, determine the dynamic guidance index values for the next time period; for each region, according to the target declared index value at the corresponding current time period, the other declared index values in the declared index values of each region except the target declared index value, the set of guidance index values at the current time period, and the set of static declared index values, determine the dynamic declared index values for each region in the next time period, so as to conduct index value guidance for the next time period according to the dynamic guidance index values, and conduct index value declaration for the next time period according to the dynamic declared index values of each region.

[0082] Therefore, in the given sets of guiding index value ranges and declared index value ranges, according to the total regional revenue function and the regional revenue function, the optimal static guiding index value set and the optimal static declared index value set are respectively selected. Combining the guiding index value set, the declared index value set already set in the current period, and the declared index values of each region, the dynamic guiding index values for the next period are determined. And by combining the target declared index values in the current period, the other declared index values in the declared index values of each region except the target declared index values, the guiding index value set in the current period, and the static declared index value set, the dynamic declared index values for each region in the next period are determined. Compared with the related art where the guiding index values and declared index values can only be determined manually, the embodiments of the present application can improve the matching degree between the issued index values and the actual situations of each prefecture-level city, and enhance economic stability.

[0083] Other features and advantages of the present disclosure will be described in the following specification, and part of them will become obvious from the specification or be understood by implementing the present disclosure. The objectives and other advantages of the present disclosure can be achieved and obtained through the structures specifically pointed out in the specification, claims, and drawings. Brief Description of the Drawings

[0084] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0085] Figure 1 It is a schematic diagram of the scenario of the index value determination system provided by the embodiments of the present application.

[0086] Figure 2 It is a schematic flowchart of the method for determining index values based on the principal-agent game theory provided by the embodiments of the present application.

[0087] Figure 3 It is a schematic structural diagram of the index value determination device provided by the embodiments of the present application.

[0088] Figure 4 It is a schematic structural diagram of the terminal provided by the embodiments of the present application.

[0089] Figure 5 It is a schematic structural diagram of the server provided by the embodiments of the present application. Detailed Embodiments

[0090] To enable those skilled in the art to better understand the solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part rather than all of the embodiments of this application. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of this application.

[0091] It can be understood that in the specific implementation of this application, when it comes to relevant data such as index values, when the above embodiments of this application are applied to specific products or technologies, object permission or consent needs to be obtained, and the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards.

[0092] It should be noted that in some processes described in the specification, claims, and the above-mentioned drawings, there are multiple steps that appear in a specific order. However, it should be clearly understood that these steps may not be executed in the order in which they appear in this article or may be executed in parallel. The step numbers are only used to distinguish different steps, and the numbers themselves do not represent any execution order. In addition, descriptions such as "first", "second", or "target" in this article are used to distinguish similar objects and do not necessarily describe a specific order or sequence.

[0093] Currently, economic operation early warning and regulation are mainly carried out through the method of "a table, a meeting, and a report", which mainly involves two parts: the issuance of annual plan indicators and the early warning and regulation of the completion of annual plan indicators. For the issuance of annual plan indicators, first, each prefecture-level city uniformly declares the index value. If the declared index value is divorced from the actual situation, it will be sent back for re-declaration until the declared index values of all prefecture-level cities are within a reasonable range. Then, the provincial company uniformly issues the annual plan index values to each prefecture-level city based on the overall situation.

[0094] In the related art, due to the existence of a certain degree of information asymmetry between the province and each prefecture-level city and the conflict between individual rationality and collective rationality, this may lead to a low matching degree between the issued values of annual plan indicators and the actual situations of each prefecture-level city, resulting in the inability of each prefecture-level city to complete the issued indicators and poor economic stability.

[0095] In order to solve the above problems, the embodiments of the present application propose to screen out the optimal static guidance index value set and the optimal static declaration index value set according to the total regional revenue function and the regional revenue function in the given set of guidance index value ranges and the set of declared index value ranges, and combine the set of guidance index values, the set of declared index value ranges and the declared index values of each region that have been set in the current period to determine the dynamic guidance index values for the next period, and combine the target declared index values in the current period, the other declared index values in the declared index values of each region except the target declared index values, the set of guidance index values in the current period and the static declared index value set to determine the dynamic declared index values for each region in the next period. Compared with the related art where the determination of guidance index values and declared index values can only be carried out manually, the embodiments of the present application can improve the matching degree between the issued index values and the actual situations of each prefecture-level city, and enhance economic stability. For specific details, please continue to refer to the following specific embodiments.

[0096] Please refer to Figure 1 , Figure 1 which is a schematic diagram of the scenario of the index value determination system provided by the embodiments of the present application. It includes a terminal 140, the Internet 130, a gateway 120, a server 110, etc.

[0097] The terminal 140 includes, but is not limited to, mobile phones, personal computers, tablet computers, etc. In addition, it can be a single device or a set composed of multiple devices. The terminal 140 can communicate with the Internet 130 in a wired or wireless manner to exchange data.

[0098] The server 110 refers to a computer system that can provide certain services to the terminal 140. Compared with ordinary terminals 140, the server 110 has higher requirements in terms of stability, security, performance, etc. The server 110 can be a high-performance computer in a network platform, a cluster of multiple high-performance computers, a part (such as a virtual machine) allocated from a high-performance computer, a combination of parts (such as virtual machines) allocated from multiple high-performance computers, etc.

[0099] The gateway 120 is also called an inter-network connector and a protocol converter. The gateway realizes network interconnection at the transport layer and is a computer system or device that acts as a conversion function. Between two systems that use different communication protocols, data formats or languages, and even have completely different architectures, the gateway is a translator. At the same time, the gateway can also provide filtering and security functions. The messages sent by the terminal 140 to the server 110 need to be sent to the corresponding server 110 through the gateway 120. The messages sent by the server 110 to the terminal 140 also need to be sent to the corresponding terminal 140 through the gateway 120.

[0100] The method for determining index values based on the principal-agent game theory in the embodiments of the present disclosure can be implemented on the server 110.

[0101] When the method for determining index values based on the principal-agent game theory is implemented on the server 110, the server 110 obtains a set of guidance index value ranges and a set of declared index value ranges. The set of guidance index value ranges includes the guidance index value ranges for each region, and the set of declared index value ranges includes the declared index value ranges for each region. Based on the total region revenue function and the region revenue function, a set of static guidance index values is selected from the set of guidance index value ranges, and a set of static declared index values is selected from the set of declared index value ranges. The set of static guidance index values includes the static guidance index values for each region, and the set of static declared index values includes the static declared index values for each region. Obtain the set of guidance index values, the set of declared index values, and the declared index values for each region at the current time period. Determine the dynamic guidance index values for the next time period according to the set of guidance index values, the set of declared index values, and the set of static guidance index values at the current time period. For each region, determine the dynamic declared index values for the next time period according to the target declared index value at the corresponding current time period, the other declared index values in the declared index values for each region except the target declared index value, the set of guidance index values at the current time period, and the set of static declared index values, so as to conduct index value guidance for the next time period according to the dynamic guidance index values, and conduct index value declaration for the next time period according to the dynamic declared index values for each region.

[0102] It should be noted that Figure 1 The schematic diagram of the scenario of the index value determination system shown is only an example. The index value determination system and scenario described in the embodiments of the present application are for more clearly explaining the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those of ordinary skill in the art know that with the evolution of index value determination and the emergence of new business scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0103] In this embodiment, the description will be made from the perspective of the index value determination device. The index value determination device can be specifically integrated in a computer device with a storage unit and installed with a microprocessor and having computing capabilities. The computer device can be a server, and in this embodiment, the computer device is taken as a server for illustration.

[0104] Please refer to Figure 2 , Figure 2 which is a flowchart of the method for determining index values based on the principal-agent game theory provided by the embodiments of the present application. The method for determining index values based on the principal-agent game theory includes:

[0105] In step 201, obtain the set of guidance index value ranges and the set of declared index value ranges. The set of guidance index value ranges includes the guidance index value ranges for each region, and the set of declared index value ranges includes the declared index value ranges for each region.

[0106] Among them, the set of guidance index value ranges G(q l ,q z ) is a set containing multiple regional guidance index value ranges. The specific form is: Among them, the guidance index value range for each region is preset by the provincial company l of the overall planned area according to factors such as the overall plan, market conditions, and resource limitations, providing a general reference framework for setting the indicators for each region n. The set of guidance index value ranges G(q l ,q z ) is a reasonable range set determined by personnel based on the guidance index value q l of the overall area regulation period and the declared index values of each region to form the declared index value q z of the overall area.

[0107] For example, for each prefecture-level city z=(z1, z2,..., z n ), the prefecture-level city index set N={1, 2,..., n}. For different prefecture-level cities, the provincial company l determines the guidance index value range of a certain economic indicator (such as gross production value, sales volume, etc.) of the prefecture-level city according to factors such as its economic development level and industrial structure.

[0108] Specifically, the set of declared index value ranges H(q l ,q z ) covers the index value ranges self-declared by each region. Each prefecture-level city declares an index value range to the provincial company based on its actual situation, such as production capacity, market demand, resource reserves, etc., reflecting the index level they think they can achieve within a certain period. The declared index value of the overall area Among them, H(q l ,q z ) is the set of declared index value ranges, which is composed of the declared index value range H1(q l ,q z ) of region 1 to the declared index value range H n (q l ,q z ) of region n. That is ∈ the declared index value range H1(q l ,q z ) of region 1, ∈ the declared index value range H n (q l ,q z)。

[0109] Accordingly, the total region (provincial company l) determines the range of guiding index values for each region (prefecture-level city) respectively based on factors such as the macroeconomic situation, industry development trend, and its own strategic plan, etc., and aggregates these ranges to form a set of guiding index value ranges. And in combination with the actual situation of each region itself, after internal evaluation and analysis, it determines its own range of declared index values and forms a set of declared index value ranges.

[0110] In step 202, based on the total region revenue function and the regional revenue function, a set of static guiding index values is selected from the set of guiding index value ranges, and a set of static declared index values is selected from the set of declared index value ranges. The set of static guiding index values includes the static guiding index values of each region, and the set of static declared index values includes the static declared index values of each region.

[0111] Among them, the total region revenue function is used to measure the overall revenue that the entire region (such as the total region including each region) can obtain under different combinations of index values. This function comprehensively considers the impact of the economic activities of each region on the overall economy, as well as factors such as the utilization efficiency of various resources, and reflects the consideration of index values by the total region from the perspective of overall interests. The regional revenue function is a revenue function set for each region (prefecture-level city), which reflects the own revenue situation of the region under different index values. Each region will determine the relationship between its own revenue and index values according to factors such as its industrial structure, cost structure, and market share. The set of static guiding index values is a set of index values selected from the set of guiding index value ranges, and these index values are considered to be relatively stable at the current stage and can enable the total region and each region to achieve a better revenue balance. The set of static declared index values is a set of index values selected from the set of declared index value ranges, and it is a relatively reasonable declared index value for each prefecture-level city after considering the total region and its own interests.

[0112] Specifically, the total region revenue function and the regional revenue functions of each region are constructed. The total region revenue function can be the sum of the revenues of each region, and factors such as the synergy effect and resource allocation between regions are considered; the regional revenue function is set according to the specific situation of each prefecture-level city. For example, it can be a function of indicators such as gross domestic product and profit.

[0113] The provincial company uses optimization algorithms (such as linear programming, non-linear programming, etc.) to search within the set of guiding index value ranges and the set of declared index value ranges. By continuously trying different combinations of index values, calculating the values of the total region revenue function and the regional revenue function, and searching for the combination of index values that can make both functions reach a relatively optimal state. Finally, a set of static guiding index values is selected from the set of guiding index value ranges, and a set of static declared index values is selected from the set of declared index value ranges.

[0114] In some embodiments, screening out a static guidance index value set from the set of guidance index value ranges and screening out a static declaration index value set from the set of declared index value ranges based on the total regional revenue function and the regional revenue function includes:

[0115] (1) Obtaining a set of historical guidance index values and obtaining a set of historical declared index values for each region;

[0116] (2) Determining an initial guidance index value set from the set of guidance index value ranges and determining an initial declared index value for each region from the set of declared index value ranges;

[0117] (3) Determining a set of guidance index value constraint ranges according to the set of historical guidance index values and the initial declared index values for each region;

[0118] (4) Determining the total regional revenue value corresponding to each candidate guidance index value set in the set of guidance index value constraint ranges through the total regional revenue function, and determining the target guidance index value set corresponding to the maximum total regional revenue value;

[0119] (5) For each region, determining the declared index value constraint range according to the target guidance index value set, the corresponding historical declared index value, and the initial declared index values of other regions;

[0120] (6) Determining the regional revenue value corresponding to each candidate declared index value in the declared index value constraint range through the regional revenue function, and determining the target declared index value corresponding to the maximum regional revenue value;

[0121] (7) When the sum of each guidance index value in the target guidance index value set is different from the sum of the target declared index values corresponding to each region, determining the target declared index value of each region as the corresponding initial declared index value, determining the sum of each guidance index value in the target guidance index value set as the initial guidance index value, and returning to execute the step of determining the set of guidance index value constraint ranges according to the set of historical guidance index values and the initial declared index values of each region until the sum of each guidance index value in the target guidance index value set is the same as the sum of the target declared index values corresponding to each region. Determining the finally obtained target guidance index value set as the static guidance index value set, and determining the finally obtained target declared index value of each region as the static declared index value to obtain the static declared index value set.

[0122] Among them, the set of historical guidance index values It is a set composed of the guiding index values set by the provincial company for each region (prefectures and cities) in the past period (such as the previous year). These index values reflect the past decision-making situation of the provincial company, can be used as a reference for current decision-making, and reflect the impact of historical regulation strategies on current decision-making. The set of historical declared index values for each region The set of index values declared by each region (prefectures and cities) to the provincial company in the past period. Among them, i represents different regions, and these historical declared values reflect the past self-assessment and planning of the development capabilities of each prefecture and city, which helps to understand the development trends and declaration habits of each prefecture and city.

[0123] Specifically, extract the guiding index values set for each region in the past historical period, and summarize these values to form a set of historical guiding index values Similarly, collect the index values declared by each region in the same historical period, classify and organize them according to regions, and obtain the set of historical declared index values for each region

[0124] To solve the above problems, the embodiment of this application plans to be based on a one-master-multiple-slave generalized self-game model as the main framework. Through data-driven and game mechanism design, the total region (master) first gives the guiding values of the annual plan indicators and the feasible declared value range for each prefecture and city; each region (slave) then declares the annual plan indicators based on its own actual situation with reference to the feasible declared value range.

[0125] Specifically, in the first game process, a set of guiding index values selected from the set of guiding index value ranges G(q l ,q z ) is used as the starting point of the game, that is, the This set of values is initially set and will be adjusted according to the game results later. The declared index values determined for each region from the set of declared index value ranges, that is, the is used as the starting declared value for each region to participate in the game, and will also change as the game progresses. The set of guiding index value constraint ranges is the feasible constraint range of the guiding index values obtained by combining the set of historical guiding index values and the set of initial declared index values of each region currently to obtain the declared index values of the total region This set takes into account the coherence of historical decisions and the declaration situations of each region, and further restricts the range of guiding index values that the total region can choose in this game. The total region revenue function f l (q l ,q z ) is used to measure the entire region (such as the whole province) under different sets of guiding index value constraint ranges The function of the overall benefit that can be obtained under the combination. This function comprehensively considers factors such as economic activities, resource allocation, and synergy effects within the region, and reflects the evaluation of different combinations of index values by the overall region from the perspective of overall interests. The set of candidate guiding index values is all possible combinations of guiding index values within the set of guiding index value constraint ranges inside. The overall region benefit value is the benefit value obtained by inputting each set of candidate guiding index values into the overall region benefit function f l (q l ,q z ), which is used to evaluate the benefit impact of this set of candidate guiding index values on the entire region. The set of target guiding index values is the set of guiding index values that maximizes the overall region benefit function f l (q l ,q z ) among all sets of candidate guiding index values. This set of values is the set of guiding index values that the overall region believes is the most beneficial to the entire region after the first game.

[0126] After obtaining the set of target guiding index values in the first game, for each region i, according to the set of target guiding index values, the corresponding historical declared index values and the initial declared index values of other regions to determine the declared index value constraint range This declared index value constraint range is the feasible range of the declared index values for region i, which is determined by combining the set of target guiding index values, the historical declared index values of this region and the initial declared index values of other regions . This range limits the interval of index values that region i can declare in this game. The regional benefit function is a function to measure the self-benefit that each region (city or prefecture) can obtain under different combinations of declared index value constraint ranges . This function considers factors such as the regional industrial structure, cost, and market share, and reflects the goal of the region to maximize its own interests.

[0127] Substitute each candidate declared index value and the current set of target guiding index values into the regional benefit function, and calculate the corresponding regional benefit value. The target declared index value is to compare all the calculated regional benefit values, find the maximum value among them, and determine the candidate declared index value corresponding to this maximum value, and take it as the target declared index value of region i The target declared index values of all regions are combined together to form the set of target declared index values after the first game.

[0128] When the sum of each guiding index value in the target guiding index value set (i.e., the total regional guiding index value) is different from the sum of the target declaration index values corresponding to each region (i.e., the total regional declaration index value), it indicates that there is a difference between the total guiding index value issued by the total region and the total declaration index value declared by each region, and they cannot reach an agreement. Then, the master-slave game needs to be carried out again, and the target guiding index value set obtained from the first game needs to be The sum of each guiding value in it is determined as the initial guiding index value, and the target declaration index value of each region is determined as the corresponding initial declaration index value, and then return to carry out the cyclic game until the sum of each guiding index value in the target guiding index value set is the same as the sum of the target declaration index values corresponding to each region. For example, after k games, the target guiding index value set The sum of each guiding index value in is the same as the target declaration index value of each region The sum of is the same. Then, the finally obtained target guiding index value set is determined as the static guiding index value set, and the finally obtained target declaration index value of each region is determined as the static declaration index value, and the static declaration index value set is obtained.

[0129] In some embodiments, in the process of determining the total regional revenue value corresponding to each candidate guiding index value set in the guiding index value constraint range set through the total regional revenue function, it includes:

[0130] (1.1) For each candidate guiding index value set in the guiding index value constraint range set, based on the sum of the candidate guiding index value set and each initial declaration index value, determine the total regional planned index value;

[0131] (1.2) Through the index revenue sub-function in the total regional revenue function, determine the total regional index revenue value corresponding to the total regional planned index value;

[0132] (1.3) From multiple total guiding index values whose distance values from the sum value of the candidate guiding index value set are within the first preset distance value, screen out the first minimum distance value from the sum value of the initial declaration index value;

[0133] (1.4) Calculate the standard deviation of the candidate guiding index value set and the guiding index value set in the current period, and obtain the growth rate standard deviation;

[0134] (1.5) According to the total regional index revenue value, the first minimum distance value, and the growth rate standard deviation, determine the total regional revenue value, and obtain the total regional revenue value corresponding to each candidate guiding index value set.

[0135] Among them, the total regional revenue function f l (q l , q z ) can be referred to the following formula:

[0136]

[0137] Among them, for each candidate guiding index value set in the guiding index value constraint range set, based on the sum value of the candidate guiding index value set and each initial declared index value, determine the total regional planned index value Q(q l , q z ). M() is the index revenue sub-function in the total regional revenue function, used to determine the total regional index revenue value M(Q(q l , q z ) corresponding to Q(q l , q z ). O(q l , ∈) = {q: ||q - q l || < ∈} is the ∈-neighborhood of q l . ‖·‖ is the distance functional. This part can measure the regulatory index and the application index to measure the regulatory effect, specifically shown in the warning interval (warning value), that is, exceeding the warning interval will have a negative impact on the revenue. Therefore, from multiple total guiding index values whose distance values from the sum value of the candidate guiding index value set are within the first preset distance value ∈, screen out the first minimum distance value from the sum value of the initial declared index values std(Δq l ) is the standard deviation of the growth rate. This index can regulate the growth rate to a certain extent to avoid the impact of excessive growth rate fluctuations of indicators in each prefecture-level city on the stable and sustainable improvement of provincial indicators. μ, and λ are corresponding positive parameters. Finally, according to the total regional index revenue value M(Q(q l , q z ), the first minimum distance value and the standard deviation of the growth rate std(Δq l ) combined with the corresponding positive parameters, determine the total regional revenue value, and obtain the total regional revenue value corresponding to each candidate guiding index value set.

[0138] In some embodiments, in the process of determining the declared index value constraint range through the regional revenue function, the regional revenue value corresponding to each candidate declared index value includes:

[0139] (1.1) For each candidate declared index value, obtain the regional revenue sub-function of the corresponding region in the regional revenue function;

[0140] (1.2) Determine the regional planned index value based on the set of candidate guiding index values and the sum value of each of the initial declared index values;

[0141] (1.3) Determine the regional index revenue value corresponding to the regional planned index value through the regional revenue sub - function;

[0142] (1.4) From multiple declared index values whose distance values from the initial declared index value corresponding to the region are within the first preset distance value, screen out the second - smallest distance value from the target guiding index value corresponding to the region in the target guiding index value set;

[0143] (1.5) Determine the regional revenue value based on the regional index revenue value and the second - smallest distance value, and obtain the regional revenue value corresponding to each candidate declared index value.

[0144] Among them, the regional revenue function The specific content can refer to the following formula:

[0145]

[0146] Among them, for each candidate declared index value, obtain the regional revenue sub - function M i () of the corresponding region in the regional revenue function, and Q i (q l , q z ) is the regional planned index value determined based on the set of candidate guiding index values and the sum value of each initial declared index value. Determine the regional index revenue value M i () corresponding to the regional planned index value through the regional revenue sub - function M i (Q i (q l , q z )) is the ∈ - neighborhood of, which represents the deviation between the application index of region i and the total regional plan. That is, from multiple declared index values whose distance values from the initial declared index value corresponding to the region are within the first preset distance value ∈, screen out the second - smallest distance value from the target guiding index value corresponding to the region in the target guiding index value set α i and β i are corresponding positive parameters.

[0147] Finally, through the regional index revenue value M i (Q i (q l , q z )) and the second - smallest distance value Determine the regional revenue value to obtain the regional revenue value corresponding to each candidate declaration index value. Such a function design is to achieve precise and objective regulation of the enterprise's economic operation through the interaction of interests between the total region and each region. Each region improves efficiency and quality in mutual healthy competition. The ∈-neighborhood here is mainly the fault tolerance range for regulating and navigating deviations. It is considered that the regulation and navigation are excellent within a certain appropriate range. This neighborhood range can not only set different ∈ parameter values according to historical data, but also adjust the measurement method as appropriate.

[0148] In step 203, obtain the set of guiding index values, the set of declaration index values, and the declaration index value of each region at the current time period.

[0149] Among them, obtain the set of guiding index values q l (t) and the set of declaration index values q z (t) at the current time period t, as well as the declaration index value of each region

[0150] In step 204, determine the dynamic guiding index value for the next time period according to the set of guiding index values, the set of declaration index values, and the set of static guiding index values at the current time period.

[0151] Among them, since the set of static guiding index values finally determined by calculation according to the above formula is the optimal set of guiding index values, but it may not be possible to reach this set of static guiding index values due to regional factors in the actual process, it is necessary to determine the dynamic guiding index value for the next time period in combination with the actual situation.

[0152] In some embodiments, the determining the dynamic guiding index value for the next time period according to the set of guiding index values, the set of declaration index values, and the set of static guiding index values at the current time period includes:

[0153] (1) Calculate the total region prediction value by using the total region expectation function for the set of declaration index values and the set of static guiding index values at the current time period;

[0154] (2) Perform weighted summation on the set of guiding index values and the total region prediction value at the current time period to obtain the dynamic guiding index value for the next time period.

[0155] Among them, the dynamic game model is to dynamicize the strategies of the provincial company and local city and county bureaus. The corresponding indicators are added with the time t (year) variable. The corresponding dynamic equations can refer to the following formula:

[0156]

[0157] Among them, q l (t + 1) is the dynamic guiding index value for the next time period t + 1, and θl is the expected parameter, and in most cases, the expected parameter can be directly set to 95%. E l () is the total area expected function for the set of declared index values q for the current period z (t) and the set of static guidance index values are calculated to obtain the total area predicted value and combined with the expected parameter θ l to perform a weighted summation calculation with the set of guidance index values q l (t) to obtain the dynamic guidance index value q for the next period l (t + 1).

[0158] In step 205, for each region, based on the target declared index value for the corresponding current period, the other declared index values in the declared index values of each region except the target declared index value, the set of guidance index values for the current period, and the set of static declared index values, determine the dynamic declared index value for each region in the next period, so as to guide the index value in the next period according to the dynamic guidance index value, and declare the index value in the next period according to the dynamic declared index value of each region.

[0159] Among them, since the determined set of static declared index values is the optimal set of declared index values, but in actual situations, it may not be possible to reach this set of static declared index values due to regional factors, it is necessary to determine the dynamic declared index value for the next period in combination with the actual situation.

[0160] Specifically, after obtaining the dynamic guidance index value q l (t + 1) and the dynamic declared index value for each region in the next period , the dynamic guidance index value q for the next period can be displayed in the index formulation system of the total area l (t + 1) for reference by designated personnel to formulate the guidance index value; display the dynamic declared index value for this region in the next period in the index declaration system of each region for reference by declarants to formulate the declared index value.

[0161] In some embodiments, for each region, based on the target declared index value for the corresponding current period, the other declared index values in the declared index values of each region except the target declared index value, the set of guidance index values for the current period, and the set of static declared index values, determining the dynamic declared index value for each region in the next period includes:

[0162] (1) For each region, obtain the region - corresponding region expected function;

[0163] (2) Calculate the regional prediction value by using the regional expectation function for the set of guiding index values, the set of static declaration index values, and other declaration index values except the target declaration index value in the declaration index values of each region during the current period.

[0164] (3) Perform weighted summation on the target declaration index value of the region corresponding to the current period and the regional prediction value to obtain the dynamic declaration index value of the next period.

[0165] Among them, the dynamic declaration index value of each region in the next period is in the dynamic equation system: is the expected parameter, and in most cases, it can be directly set to 95%. is the regional expectation function of region i. Through the regional expectation function for the set of guiding index values during the current period the set of static declaration index values and other declaration index values except the target declaration index value in the declaration index values of each region perform calculations to obtain the regional prediction value Through the expected parameter for the target declaration index value during the current period and the regional prediction value perform weighted summation to obtain the dynamic declaration index value of the next period

[0166] In some embodiments, design the dynamic regulation intervals for each region and the total regional dynamic regulation interval.

[0167] For the dynamic regulation interval of each region, for any region i ∈ N in the next period, execute the index to perform interval constraint regulation.

[0168]

[0169] Among them, H i and are the upper and lower bound functions of the interval based on H i (such as designed according to the mean standard deviation of the historical period data of this index). Through this interval, timely guidance and regulation can be carried out on the real-time execution indicators of each region to prevent the execution chaos and instability phenomena caused by bounded rationality.

[0170] Total regional dynamic regulation interval: The regulation index should be set by comprehensively weighing and constraining the national plan index and the execution indexes of each prefecture-level city.

[0171]

[0172] Among them,G and G is based on the upper and lower limit functions of the G interval (designed according to the mean standard deviation of the historical period data of this indicator), and K is the planned indicator. This interval is to ensure the smooth completion of the indicator and the planned indicator allocation basically conforms to the actual situation of each region.

[0173] In the above model, stability theory analysis and simulation experiments are carried out for various different expected functions or the corresponding dynamic systems of multiple expectations integration. In this way, it is ensured to achieve equilibrium and efficiency stably and sustainably.

[0174] It should be noted that the design of the comprehensive income function is mainly to make the regulatory index equal to the execution index and consistent with the regulatory index at equilibrium. Equilibrium is a fixed-point stable state where, under the assumption of perfect rationality (participants maximize their income, individual rationality), no participant can improve their own income by adjusting their own strategy alone. Through appropriate income function design (incentive compatibility mechanism), the individual rational behavior can be made consistent with the macro overall goal direction, realizing the organic combination of the planned market and the free market, making it have the advantages of both, and having a certain self-repair ability. In the equilibrium state, the total regional "navigation" index, the application indicators of each region, and the planned indicators of each prefecture-level city bureau are completely consistent, and the income of each is maximized, and the economic operation state of the enterprise is of high quality and efficiency; that is, in the ideal situation, no regulation is required, achieving the highest goal of regulation - no regulation.

[0175] Let the set composed of all equilibrium states be NE(f). Then, under the design of an appropriate game mechanism, this set is an equilibrium region range. That is, when the regulatory value is within this equilibrium region range, it is the ideal situation of no regulation, that is, in the stable state, the regulatory role is invisible, just like there is no regulation.

[0176] Bounded rationality and dynamic regulation: Bounded rationality means that in the process of making decisions by game participants, due to information, decision-making ability, operation, and random factors, etc., the strategies they make often deviate from the optimal strategy. That is, a perfect equilibrium state is usually difficult to achieve. It is difficult for the total regional decision-making to always maintain perfect rationality, and it is easier for each region to have bounded rational behavior. Then, for the above model, corresponding stability analysis and dynamic regulation must be carried out to avoid significant differences in results.

[0177] First, the stability analysis is to ensure that under relatively small (or external shocks, etc.) fluctuations in decision-making, the resulting income results will not change too much; in the process of bounded rationality approaching perfect rationality, the corresponding effects are also constantly approaching the ideal effects.

[0178] For the concept of "satisfactory solution", the decision-maker's strategy only needs to be near the strategy near the maximum benefit. This can also be understood as the decision-maker having irrational behavior (mainly in terms of strategy and benefit) deviations during the decision-making process, but the relative deviation is relatively small.

[0179] (δ,ε)-equilibrium: There exists and the δ-neighborhood of for satisfying

[0180] (1)

[0181] (2) For any i ∈ N,

[0182]

[0183] The requirement for stable equilibrium is that when δ → 0 and ε → 0, the (δ,ε)-equilibrium tends to the original equilibrium.

[0184] Second, dynamic regulation is the continuous evolution and regulation during the economic operation of enterprises to prevent the situation from developing in the opposite direction of equilibrium and accelerate approaching equilibrium. The dynamic game model is a methodology that enables bounded-rational decision-makers to ultimately achieve a fully rational equilibrium through a learning mechanism in multiple repeated games; adding timely regulation during the process is an important means to accelerate the state's convergence to the equilibrium state and prevent divergence to an unstable state.

[0185] In some embodiments, after determining the dynamic declaration index value for each region in the next time period according to the target declaration index value corresponding to each region, other declaration index values in each region's declaration index values except the target declaration index value, the set of guiding index values for the current time period, and the set of static declaration index values, it further includes:

[0186] (1) Obtain the index feedback value of each index type in the feedback sub-time period in the next time period for each region, and determine the operation state evaluation value of each index type in the feedback sub-time period in the next time period for each region based on the historical sub-time period's completed index proportion mean, the historical sub-time period's completed index proportion standard deviation, the cumulative completed index proportion mean from the historical time period to the feedback sub-time period, and the cumulative completed index proportion standard deviation from the historical time period to the feedback sub-time period for each index type;

[0187] (2) Compare the operation state evaluation value of each index type with the corresponding regulation suggestion value;

[0188] (3) Determine the target index type as the index type in the target region where the operation state evaluation value is different from the corresponding regulation suggestion value;

[0189] (4) Obtain multiple warning intervals corresponding to the target indicator type in the target area;

[0190] (5) Determine the target warning interval in which the target operating status evaluation value of the target indicator type is located;

[0191] (6) Based on the preset mapping relationship between the warning interval and the warning level, determine the target warning level corresponding to the target warning interval;

[0192] (7) Generate a prompt message to prompt that the operating status evaluation value of the target indicator type in the target area is at the target warning level.

[0193] Among them, after the process of issuing the guiding indicator value in the total area and each area uploading the declared indicator value, it enters the indicator execution process of the next time period. During the execution process, each area will feedback the indicator completion situation of this sub-time period to the total area after the end of each sub-time period of the time period, that is, upload the indicator feedback value. After the total area obtains the indicator feedback value of each area, it needs to control it to determine whether early warning is required for the indicator completion situation.

[0194] Specifically, when determining whether early warning is required, it is first necessary to evaluate its economic operation status, that is, to determine the operating status evaluation value P i s (t) of each indicator type in each sub-time period of the next time period for each area. Its evaluation method needs to be determined according to the indicator feedback value of each indicator type in each sub-time period of the next time period for each area 0 represents the current time period (such as this year), and the average value of the historical sub-time period completion index ratio of each indicator type in the feedback sub-time period The standard deviation of the historical sub-time period completion index ratio of the feedback sub-time period The average value of the cumulative completion index ratio from the historical time period to the feedback sub-time period And the standard deviation of the cumulative completion index ratio from the historical time period to the feedback sub-time period to determine.

[0195] Specifically, the operating status evaluation value P i s (t) can be determined with reference to the following formula:

[0196]

[0197] Among them, represents the economic operation status, represents the economic operation progress, and γ, γ1, and γ2 are weight coefficients.

[0198] Specifically, let the determined total regional guidance index value q = ∑ i∈N q i where q i is the guidance index value for the next time period of region i, N is the set composed of all regions, where is the guidance index value for the next time period of the index type s of region i, S = {1, 2,..., y} is the index type set, and the index type set refers to the decomposition of the index in the business structure. For example, profit can be divided into the profit generated by business 1, the profit generated by business 2, the profit generated by business 3, the profit generated by business 4, etc. Thus, is the annual plan index of the total region type s. This is based on the division of two dimensions: region and index type.

[0199] To construct a discrete dynamic system, a division of the time dimension is added. where is the division of sub - time periods within a time period (e.g., for monthly, T = 12; for quarterly, T = 4; for weekly, T = 52); is the sub - time period t plan index of different decomposed sub - time periods of type s of the prefecture - level city bureau i; x refers to the unit value translated before and after the current year. 0 is the current year, x is x years in the future, and - x is x years in the past, and so on; this index can be directly calculated based on the current year's basic data and the index operation logic. By default, the future is for prediction, the past is known, and the present is in progress.

[0200] Let be the proportion of the completed plan index of sub - time period t of different decomposed sub - time periods of type s of region i. Then the average value of the proportion of the completed index in the historical sub - time periods of each index type in the feedback sub - time period can be determined with reference to the following formula:

[0201]

[0202] The standard deviation of the proportion of the completed index in the historical sub - time periods of the feedback sub - time period can be determined with reference to the following formula:

[0203]

[0204] where is the length of the historical time period. If uneven effects are to be applied to the data of previous years, a weight factor can be appropriately added.

[0205] Let be the cumulative proportion of the completed plan index of sub - time period t of different decomposed sub - time periods of type s of region i. Then the average value of the cumulative proportion of the completed index from the historical time period to the feedback sub - time period It can be determined with reference to the following formula:

[0206]

[0207] The standard deviation of the cumulative completion index ratio from the historical period to the feedback sub-period It can be determined with reference to the following formula:

[0208]

[0209] In this way, the operation status evaluation value of each index type in the feedback sub-period of each region in the next period is obtained.

[0210] When the data and subjective factors are considered sufficiently, the corresponding regulation recommendation value can directly use the average value of the upper and lower limits (mean value) Or

[0211] Compare the operation status evaluation value P i s (t) of each index type with the corresponding regulation recommendation value( Or ), and determine the index type with different operation status evaluation value and corresponding regulation recommendation value in the target region as the target index type.

[0212] Specifically, the embodiments of the present application set multiple warning intervals, each warning interval corresponding to a warning level, for the low warning level for the medium warning level and for the high warning level Determine the target warning interval where the target operation status evaluation value is located, and based on the preset mapping relationship between the warning interval and the warning level, determine the target warning level corresponding to the target warning interval. Generate a prompt message to prompt that the operation status evaluation value of the target index type in the target region is at the target warning level, so that personnel can control the index value.

[0213] In addition, it can also be based on and as reference values. Evaluation of the warning level setting rules: (1) Under the condition of ensuring the case, is low, is medium, is high. and The numerical values are set through comprehensive weighing of data and experience. (2) If the warning level is directly high. (When the economic operation status is less than the preset economic operation status threshold, determine the warning level according to the economic operation progress interval where the economic operation progress is located).

[0214] In some embodiments, after generating the prompt information, the following steps are further included:

[0215] (1) Obtain a first set of regulated index value ranges for the target index type in the target area, where the first set of regulated index value ranges includes the regulated index value ranges for each sub-period from the feedback sub-period to the last sub-period in the next period;

[0216] (2) Simulate the corresponding total area index values according to different sets of regulated index values combined from the regulated index value ranges of each sub-period;

[0217] (3) Determine the set of first candidate regulated index values for the target index type in the target area from the feedback sub-period to the last sub-period as the set of regulated index values corresponding to the maximum total area index value;

[0218] (4) Obtain the average of the upper and lower limits of the sub-period completion index ratio for each sub-period from the feedback sub-period to the last sub-period in the next period;

[0219] (5) Adjust the upper limit value or the lower limit value of the sub-period completion index ratio of the sub-periods in the first candidate regulated index value set where the regulated index value is different from the average of the upper and lower limits of the sub-period completion index ratio to obtain the adjusted upper limit value and the adjusted lower limit value of the sub-period completion index ratio for each sub-period;

[0220] (6) When there is no case where the upper limit value of the sub-period completion index ratio of a sub-period is less than the lower limit value of the sub-period completion index ratio of the corresponding sub-period, conduct index value guidance for the target index type in the target area from the feedback sub-period in the next period according to the first candidate regulated index value set.

[0221] Wherein, when the actual index has a deviation or an early warning, decompose all data dimensions of this node and below, find the dimension data that mainly deviates from the normal value, then fully explore all solutions for dealing with and coping with the abnormal situation of this dimension under the guidance of senior experts and front-line operators, and give a comprehensive evaluation score for the overall impact on the economic operation state according to this solution. The higher the score, the higher the ranking, and the higher the ranking, the better the recommendation; however, the actual solution selection is based on the front-line operators' comprehensive consideration of the actual situation in combination with this recommended decision-making set for re-decision-making.

[0222] The impact of the processing and response plan on the overall economic operation can be modeled through historical data, and an appropriate simulation evaluation function can be designed. This evaluation function combines the data-driven model of the entire enterprise's economic operation. After adding this external processing and response early warning plan, it is simulated and run, and then the evaluation function of the overall economic operation state of the enterprise after simulation is the simulation evaluation function, and the corresponding evaluation value is given. The specific model construction is as follows:

[0223] Taking the evaluation value P i s (t) as the evaluation value of the economic operation state of index type s in region i at time t, then the evaluation value of the overall economic operation state at time t is P(t) = ∑ i∈N ∑ s∈S P i s (t). Let P i s (t0, t; K) represent the evaluation value of the economic operation state of index type s in region i at time t after K decision regulations in the feedback sub-period t0. After quantization, K mainly refers to the controllable quantity of the economic operation index of index type s in region i from the feedback sub-period t0 to the last sub-period t1, that is Then the cumulative value of the economic operation state evaluation from the feedback sub-period t0 after K decision regulations to the sub-period t1 is:

[0224]

[0225] Based on this, obtain the first set of regulation index value ranges for the target index type in the target region It is the Cartesian product of the upper and lower limits of each component within the corresponding warning range (generally, the warning level here can be selected as medium warning, that is, the warning threshold is 0.8); then according to P(t0, T; K), the cumulative evaluation value of each decision in the feasible decision set of index type s in region i at the feedback sub-period t0 to the final time T can be calculated as the evaluation of the decision on the overall economic operation of the enterprise, and the highest total regional index value (regulation) is selected That is, according to the different regulation index value sets combined by the regulation index value ranges of each sub-period, simulate the corresponding total regional index values, and determine the regulation index value set corresponding to the largest total regional index value as the first candidate regulation index value set K of the target index type in the target region from the feedback sub-period to the last sub-period * * .

[0226] Taking the example of sorting the total regional index values, the lower the value, the better, and the higher the ranking, the first candidate regulation index value set can be determined according to the following formula:

[0227]

[0228] Among them, the above formula is to sort the total regional index values of P(t0, t1; K) for each K in, and determine the first candidate regulatory index value set K as the K with the smallest rank, that is, the highest total regional index value * .

[0229] Specifically, let and combine it with K * to dynamically adjust the upper and lower limits of the sub-period completion index ratio.

[0230] For the sub-period completion index ratio upper limit value * of the sub-period in the first candidate regulatory index value set K where the regulatory index value is different from the mean of the upper and lower limits of the sub-period completion index ratio corresponding to it or the sub-period completion index ratio lower limit value is adjusted (t * is the sub-period for which the upper limit or lower limit needs to be adjusted), and the adjusted sub-period completion index ratio upper limit value and sub-period completion index ratio lower limit value for each sub-period are obtained.

[0231] Among them, the upper limit value of the completion index ratio for different sub-periods of the index type s in region i based on the corresponding index (mean ± γ times standard deviation) obtained from historical data is:

[0232]

[0233] The lower limit value of the completion index ratio for different sub-periods is:

[0234]

[0235] In this way, the upper limit value and lower limit value of the sub-period completion index ratio for each sub-period from the feedback sub-period t0 to the last sub-period t1 are obtained. Among them, the parameter γ can be adjusted according to specific circumstances. For regional summary or type summary, only simple summation is required. Here, relative quantities such as index proportion and completion degree can also be considered instead of absolute quantities. For example, for indicators such as profit and sales volume, designing with the completion degree and cumulative completion degree based on the annual plan can, to a certain extent, eliminate the obvious growth trend of indicators each year and make the model results more in line with reality; while for indicators such as sales price, there is no completion degree or cumulative completion degree in terms of quantity, so there is no need to do so. For specific indicators, the model needs to be appropriately adjusted in combination with expert experience and data characteristics, and cannot be generalized. Taking the sales price as an example, to eliminate the influence of the growth trend of sales price over the years, it can be considered to let be the planned index of the time period t of different decomposition time periods of the index type s (sales price) in region i and its annual sales price Difference value, and only consider the index Do not consider the cumulative index Then obtain the upper and lower limits of the planned index volume warning in the same way and

[0236] When there is no special case where the upper limit value of the sub-period completion index ratio of a sub-period is less than the lower limit value of the sub-period completion index ratio of the corresponding sub-period, the index value of the target index type in the target area starting from the self-feedback sub-period t0 in the next period is guided according to the first candidate set of regulation index values.

[0237] In some embodiments, the obtaining of the upper and lower limit means of the sub-period completion index ratio for each sub-period from the self-feedback sub-period to the last sub-period in the next period includes:

[0238] (1.1) Obtain the upper limit value of the sub-period completion index ratio and the lower limit value of the sub-period completion index ratio for each sub-period from the self-feedback sub-period to the last sub-period in the next period;

[0239] (1.2) Based on the upper limit of the sub-period completion index ratio and the lower limit of the sub-period completion index ratio of each sub-period, determine the upper and lower limit means of the completion index ratio of each sub-period.

[0240] Among them, let the upper limit value of the sub-period completion index ratio of the warning sub-period be:

[0241]

[0242] Let the lower limit value of the sub-period completion index ratio of the warning sub-period be:

[0243]

[0244] Among them, each value in the set K of the upper and lower limit means of the sub-period completion index ratio E is the upper and lower limit mean of the sub-period completion index ratio for each sub-period in area i from the feedback sub-period t0 to the last sub-period t1. For example That is, the corresponding value of the feedback sub-period t0 in the set of upper limit values of the sub-period completion index ratio and the corresponding value in the set of lower limit values of the sub-period completion index ratio in The sum of the corresponding values is divided by 2. In this way, the upper and lower limit means of the sub-period completion index ratio for each sub-period from the feedback sub-period t0 to the last sub-period t1 in the next period are obtained.

[0245] In some embodiments, adjusting the upper limit value or the lower limit value of the sub-period completion index ratio of the sub-period in which the regulation index value in the first candidate regulation index value set is different from the average of the upper and lower limits of the completion index ratio of the corresponding sub-period to obtain the adjusted upper limit value and the adjusted lower limit value of the sub-period completion index ratio for each sub-period includes:

[0246] (1.1) When there is a regulation index value of a first sub-period in the first candidate regulation index value set that is greater than the average of the upper and lower limits of the completion index ratio of the target sub-period, determining a first adjustment value based on the regulation index value in the first sub-period and the average of the upper and lower limits of the completion index ratio of the first sub-period;

[0247] (1.2) Adjusting the lower limit value of the sub-period completion index ratio of the first sub-period according to the first adjustment value;

[0248] (1.3) When there is a regulation index value of a second sub-period in the first candidate regulation index value set that is less than the average of the upper and lower limits of the completion index ratio of the target sub-period, determining a second adjustment value based on the regulation index value in the second sub-period and the average of the upper and lower limits of the completion index ratio of the second sub-period;

[0249] (1.4) Adjusting the upper limit value of the sub-period completion index ratio of the second sub-period according to the second adjustment value.

[0250] Wherein, if K of a certain period * is greater than K E , then adjust the lower limit value of the completion index ratio; if K of a certain period * is less than K E , then adjust the upper limit value of the completion index ratio. The adjustment value is:

[0251] ΔK = 2|K * - K E |

[0252] Specifically, when there is a regulation index value of a first sub-period in the first candidate regulation index value set K * that is greater than the average of the upper and lower limits of the completion index ratio of the target sub-period in K E , determining a first adjustment value ΔK1 based on the regulation index value in the first sub-period and the average of the upper and lower limits of the completion index ratio of the first sub-period, and adjusting the lower limit value of the sub-period completion index ratio of the first sub-period according to the first adjustment value ΔK1; when there is a regulation index value of a second sub-period in the first candidate regulation index value set K * that is less than K EWhen determining the mean of the upper and lower limits of the completion index ratio for the target sub-period, based on the control index value in the second sub-period and the mean of the upper and lower limits of the completion index ratio in the second sub-period, determine the second adjustment value ΔK2, and adjust the upper limit value of the sub-period completion index ratio of the second sub-period according to the second adjustment value ΔK2.

[0253] In some embodiments, the method further includes:

[0254] (1) When the upper limit value of the sub-period completion index ratio of the third sub-period is less than the corresponding lower limit value of the sub-period completion index ratio, determine the mean of the upper and lower limits of the adjusted upper limit value and the lower limit value of the sub-period completion index ratio of each sub-period from the feedback sub-period to the fourth sub-period before the third sub-period as the control index value for the corresponding sub-period;

[0255] (2) Determine the upper limit value or the lower limit value of the sub-period completion index ratio of the third sub-period as the control index value of the third sub-period;

[0256] (3) Obtain a second set of control index value ranges for the target index type in the target area, where the second set of control index value ranges includes the control index value ranges for each sub-period from the fifth sub-period after the third sub-period to the last sub-period in the next period;

[0257] (4) Simulate the corresponding total area index value according to different sets of control index values combined from the control index value ranges for each sub-period from the fifth sub-period after the third sub-period to the last sub-period;

[0258] (5) Determine the set of control index values corresponding to the largest total area index value as the second candidate set of control index values for the target index type in the target area from the fifth sub-period after the third sub-period;

[0259] (6) Obtain the mean of the upper and lower limits of the sub-period completion index ratio for each sub-period from the fifth sub-period to the last sub-period in the next period;

[0260] (7) Adjust the upper limit value or the lower limit value of the sub-period completion index ratio of the sub-period where the control index value in the second candidate set of control index values is different from the corresponding mean of the upper and lower limits of the sub-period completion index ratio, to obtain the adjusted upper limit value and the lower limit value of the sub-period completion index ratio for each sub-period;

[0261] When the upper limit value of the sub-period completion index ratio of a sub-period is less than the lower limit value of the corresponding sub-period completion index ratio, the index value guidance of the target index type in the target area starting from the feedback sub-period in the next period is performed according to the regulation index values of each sub-period from the third feedback sub-period to the fourth sub-period, the regulation index value of the third sub-period, and the second candidate regulation index value set of the fifth sub-period after the third sub-period.

[0262] Among them, when there is a special case where the upper limit value of the sub-period completion index ratio of a sub-period is less than the lower limit value of the corresponding sub-period completion index ratio, the third sub-period t2 where this special case occurs is determined.

[0263] For the special case, if K * is greater than K E , let the lower limit value of the sub-period completion index ratio be equal to the upper limit value of the sub-period completion index ratio; if K * is less than K E , let the upper limit value of the sub-period completion index ratio be equal to the lower limit value of the sub-period completion index ratio. It should be noted that in this case, the early warning interval range is zero, and a minimum early warning interval can be set as appropriate. In this verification, the future guidance value is within the medium early warning (early warning threshold is 0.8) range, while the early warning interval uses the high early warning (early warning threshold is 1). Even in this special case, there is a basic adjustment interval range. In addition, since the adjustment amplitude of this component does not meet the standard in the special case, this unqualified part will be allocated to the subsequent future guidance values. The method idea is to fix the guidance value of this characteristic situation component and then repeat the previous method. Specifically as follows:

[0264] The regulation index values from the feedback sub-period t0 to the third sub-period t2 are:

[0265]

[0266] Or

[0267]

[0268] That is, the upper and lower limit mean values of the adjusted upper limit value and lower limit value of the sub-period completion index ratio of each sub-period from the feedback sub-period t0 to the fourth sub-period t2 - 1 before the third sub-period t2 are determined as the regulation index values of the corresponding sub-periods.

[0269] The upper limit value of the sub-period completion index ratio of the third sub-period t2 or the lower limit value of the sub-period completion index ratio is determined as the regulation index value of the third sub-period t2.

[0270] On this basis, from the fifth sub-period t2+1 after the third sub-period t2 to the last sub-period t1, the controllable quantity of the economic operation index of the index type s in region i is:

[0271]

[0272] Then, after making the K′ decision regulation in the fifth sub-period t2+1 until the last sub-period t1, the total regional index value is:

[0273]

[0274] Let the set of the second regulation index value ranges of the index type s in region i in the fifth sub-period t2+1 be Then, according to P(t2+1,T;K′), the set of the second regulation index value ranges of the index type s in region i in the fifth sub-period t2+1 can be calculated For each decision in it until the total regional index value of the last sub-period t2 is used as the evaluation of the decision on the overall enterprise economic operation, and this is used as the feasible decision ranking criterion. The lower the value, the better, and the higher the ranking. The optimal decision (regulation) is selected That is:

[0275]

[0276] Let the set of the upper and lower limit means of the sub-period completion index ratio from the fifth sub-period to the last sub-period in the next sub-period be ′

[0277] And in combination with K * dynamically adjust the upper limit value or the lower limit value of the sub-period completion index ratio. Let the upper limit value of the sub-period completion index ratio be:

[0278]

[0279] The lower limit value of the sub-period completion index ratio is:

[0280]

[0281] If K′ * is greater than K′ E , then the lower limit value of the sub-period completion index ratio; if K′ * is less than K′ E , then adjust the upper limit value of the sub-period completion index ratio. The adjustment value is:

[0282] ΔK′ = 2|K * ′ - K′ E |

[0283] Determine whether there is still such a special case from the fifth sub-period t2+1 to the last sub-period t1. If not, no further steps are required; if so, perform the above steps. This loop continues until such a special case no longer exists. Therefore, when the upper limit value of the sub-period completion index ratio of a sub-period is less than the lower limit value of the corresponding sub-period completion index ratio, according to the control index values of each sub-period from the third feedback sub-period to the fourth sub-period, the control index value of the third sub-period, and the set of second candidate control index values of the fifth sub-period after the third sub-period, conduct the index value guidance of the target index type in the target area of the next period starting from the feedback sub-period.

[0284] In some embodiments, a mid-period control model is also provided. Compared with the total-period declaration model, this model only replaces the declared index values of each region in the total-period declaration model with the execution strength of the actual relevant plan indexes estimated for each region based on the relevant plan index completion degree and the completion evaluation value obtained from the dynamic early warning model in the upper half of the period, and then weights them with the total-period guidance index value to obtain the corresponding mid-period value; where the weight of the execution strength is α. Let be the mid-period execution strength, then Q i (q l ,q m )=(1-α)q l +αq m is the mid-period value of address city i.

[0285] For the specific implementation of each of the above steps, reference can be made to the previous embodiments, which will not be elaborated here.

[0286] In an embodiment of the present application, by obtaining a set of guidance index value ranges and a set of declared index value ranges, the set of guidance index value ranges includes the guidance index value ranges for each region, and the set of declared index value ranges includes the declared index value ranges for each region; based on the total regional revenue function and the regional revenue function, a set of static guidance index values is selected from the set of guidance index value ranges, and a set of static declared index values is selected from the set of declared index value ranges, the set of static guidance index values includes the static guidance index values for each region, and the set of static declared index values includes the static declared index values for each region; obtain the set of guidance index values, the set of declared index values and the declared index values for each region at the current time period; according to the set of guidance index values, the set of declared index values and the set of static guidance index values at the current time period, determine the dynamic guidance index values for the next time period; for each region, according to the target declared index value at the corresponding current time period, the other declared index values in the declared index values for each region except the target declared index value, the set of guidance index values at the current time period and the set of static declared index values, determine the dynamic declared index values for each region in the next time period, so as to conduct index value guidance for the next time period according to the dynamic guidance index values, and conduct index value declaration for the next time period according to the dynamic declared index values for each region.

[0287] In this way, in the given set of guidance index value ranges and the set of declared index value ranges, according to the total regional revenue function and the regional revenue function, the optimal set of static guidance index values and the optimal set of static declared index values are respectively selected, and combined with the set of guidance index values, the set of declared index values and the declared index values for each region that have been set at the current time period, the dynamic guidance index values for the next time period are determined, and combined with the target declared index value at the current time period, the other declared index values in the declared index values for each region except the target declared index value, the set of guidance index values at the current time period and the set of static declared index values, the dynamic declared index values for each region in the next time period are determined. Compared with the related art where only manual determination of guidance index values and declared index values can be performed, the embodiment of the present application can improve the matching degree between the issued index values and the actual situations of each prefecture-level city, and enhance economic stability.

[0288] To facilitate better implementation of the index value determination method based on the principal-agent game theory provided by the embodiment of the present application, the embodiment of the present application further provides a device based on the above-mentioned index value determination method based on the principal-agent game theory. The meanings of the terms are the same as those in the above-mentioned index value determination method based on the principal-agent game theory, and the specific implementation details can refer to the description in the method embodiment.

[0289] Please refer to Figure 3 , Figure 3The figure is a schematic structural diagram of the index value determination device provided by an embodiment of this application. This index value determination device is applied to a computer device, and may include a first acquisition unit 401, a screening unit 402, a second acquisition unit 403, a first determination unit 404, a second determination unit 405, etc.

[0290] The first acquisition unit 401 is configured to acquire a set of guidance index value ranges and a set of declared index value ranges. The set of guidance index value ranges includes the guidance index value ranges of each region, and the set of declared index value ranges includes the declared index value ranges of each region.

[0291] The screening unit 402 is configured to screen out a set of static guidance index values from the set of guidance index value ranges and screen out a set of static declared index values from the set of declared index value ranges based on the total regional revenue function and the regional revenue function. The set of static guidance index values includes the static guidance index values of each region, and the set of static declared index values includes the static declared index values of each region.

[0292] The second acquisition unit 403 is configured to acquire a set of guidance index values, a set of declared index values at the current time period, and the declared index values of each region.

[0293] The first determination unit 404 is configured to determine the dynamic guidance index values for the next time period according to the set of guidance index values, the set of declared index values, and the set of static guidance index values at the current time period.

[0294] The second determination unit 405 is configured to, for each region, determine the dynamic declared index values for the next time period according to the target declared index value at the corresponding current time period, the other declared index values in the declared index values of each region except the target declared index value, the set of guidance index values at the current time period, and the set of static declared index values, so as to conduct index value guidance for the next time period according to the dynamic guidance index values and conduct index value declaration for the next time period according to the dynamic declared index values of each region.

[0295] In some embodiments, the screening unit includes:

[0296] The first acquisition subunit is configured to acquire a set of historical guidance index values and a set of historical declared index values of each region.

[0297] The first determination subunit is configured to determine an initial set of guidance index values from the set of guidance index value ranges and determine the initial declared index values of each region from the set of declared index value ranges.

[0298] A second determination subunit, configured to determine a set of guidance index value constraints according to the set of historical guidance index values and the initial declaration index value of each region;

[0299] A third determination subunit, configured to determine the total regional revenue value corresponding to each candidate guidance index value set in the set of guidance index value constraints through a total regional revenue function, and determine the target guidance index value set corresponding to the maximum total regional revenue value;

[0300] A fourth determination subunit, configured to, for each region, determine the range of declaration index value constraints according to the target guidance index value set, the corresponding historical declaration index value, and the initial declaration index values of other regions;

[0301] A fifth determination subunit, configured to determine the regional revenue value corresponding to each candidate declaration index value in the range of declaration index value constraints through a regional revenue function, and determine the target declaration index value corresponding to the maximum regional revenue value;

[0302] A sixth determination subunit, configured to, when the sum value of each guidance index value in the target guidance index value set is different from the sum value of the target declaration index value corresponding to each region, determine the target declaration index value of each region as the corresponding initial declaration index value, determine the sum value of each guidance index value in the target guidance index value set as the initial guidance index value, and return to execute the step of determining the set of guidance index value constraints according to the set of historical guidance index values and the initial declaration index value of each region until the sum value of each guidance index value in the target guidance index value set is the same as the sum value of the target declaration index value corresponding to each region. The finally obtained target guidance index value set is determined as the static guidance index value set, and the finally obtained target declaration index value of each region is determined as the static declaration index value, and a static declaration index value set is obtained.

[0303] In some embodiments, the third determination subunit is configured to:

[0304] For each candidate guidance index value set in the set of guidance index value constraints, based on the sum value of the candidate guidance index value set and each of the initial declaration index values, determine the total regional planned index value;

[0305] Determine the total regional index revenue value corresponding to the total regional planned index value through the index revenue sub-function in the total regional revenue function;

[0306] Select the first minimum distance value from the sum value of the candidate guidance index value set from multiple total guidance index values whose distance values are within the first preset distance value, and the sum value of the initial declaration index values;

[0307] Calculate the standard deviation of the set of candidate guidance index values and the set of guidance index values for the current period to obtain the growth rate standard deviation;

[0308] Determine the total regional revenue value based on the total regional indicator revenue value, the first minimum distance value, and the growth rate standard deviation, and obtain the total regional revenue value corresponding to each set of candidate guidance index values.

[0309] In some embodiments, the fifth determination subunit is configured to:

[0310] For each candidate declared index value, obtain the regional revenue sub-function of the corresponding region in the regional revenue function;

[0311] Determine the regional planned index value based on the set of candidate guidance index values and the sum value of each of the initial declared index values;

[0312] Determine the regional indicator revenue value corresponding to the regional planned index value through the regional revenue sub-function;

[0313] Select the second minimum distance value from a plurality of declared index values whose distance values from the initial declared index value corresponding to the region are within the first preset distance value and that are corresponding to the target guidance index value in the target guidance index value set;

[0314] Determine the regional revenue value based on the regional indicator revenue value and the second minimum distance value, and obtain the regional revenue value corresponding to each candidate declared index value.

[0315] In some embodiments, the first determination unit includes:

[0316] The first calculation subunit is configured to calculate the total regional prediction value by using the total regional expectation function for the set of declared index values and the set of static guidance index values for the current period;

[0317] The first weighted summation subunit is configured to perform weighted summation on the set of guidance index values and the total regional prediction value for the current period to obtain the dynamic guidance index value for the next period.

[0318] In some embodiments, the second determination unit includes:

[0319] The first acquisition subunit is configured to obtain the regional expectation function corresponding to each region;

[0320] The second calculation subunit is configured to calculate the regional prediction value by using the regional expectation function for the set of guidance index values, the set of static declared index values, and other declared index values except the target declared index value in the declared index values of each region for the current period;

[0321] A second weighted summation subunit, configured to perform weighted summation on the target declared index value of the current time period corresponding to the region and the region prediction value to obtain a dynamic declared index value for the next time period.

[0322] In some embodiments, the apparatus further includes:

[0323] A third acquisition unit, configured to acquire an index feedback value of each index type in each feedback sub-period in the next time period for each region, and determine an operation status evaluation value of each index type in each feedback sub-period in the next time period for each region based on the historical sub-periods of each index type in the feedback sub-period to complete the index proportion mean value, the historical sub-periods of the feedback sub-period to complete the index proportion standard deviation value, the cumulative completed index proportion mean value from the historical time period to the feedback sub-period, and the cumulative completed index proportion standard deviation value from the historical time period to the feedback sub-period;

[0324] A comparison unit, configured to compare the operation status evaluation value of each index type with the corresponding regulation recommendation value;

[0325] A third determination unit, configured to determine an index type in the target region where the operation status evaluation value is different from the corresponding regulation recommendation value as the target index type;

[0326] A fourth acquisition unit, configured to acquire a plurality of warning intervals corresponding to the target index type in the target region;

[0327] A fourth determination unit, configured to determine a target warning interval in which the target operation status evaluation value of the target index type is located;

[0328] A fifth determination unit, configured to determine a target warning level corresponding to the target warning interval based on a preset mapping relationship between the warning interval and the warning level;

[0329] A generation unit, configured to generate a prompt message to prompt that the operation status evaluation value of the target index type in the target region is at the target warning level.

[0330] In some embodiments, the apparatus further includes:

[0331] A fifth acquisition unit, configured to acquire a first set of regulation index value ranges for the target index type in the target region, where the first set of regulation index value ranges includes the regulation index value ranges for each sub-period from the feedback sub-period to the last sub-period in the next time period;

[0332] A first simulation unit, configured to simulate corresponding total region index values according to different sets of regulation index values combined from the regulation index value ranges of each sub-period;

[0333] The sixth determination unit is configured to determine, as the first candidate set of regulation index values of the target index type in the target area from the feedback sub-period to the last sub-period, the set of regulation index values corresponding to the maximum total area index value;

[0334] The sixth acquisition unit is configured to acquire the average upper and lower limits of the sub-period completion index ratio for each sub-period from the feedback sub-period to the last sub-period in the next period;

[0335] The first adjustment unit is configured to adjust the upper limit value or the lower limit value of the sub-period completion index ratio of the sub-period in which the regulation index value in the first candidate set of regulation index values is different from the average upper and lower limits of the sub-period completion index ratio corresponding thereto, to obtain the adjusted upper limit value and the adjusted lower limit value of the sub-period completion index ratio for each sub-period;

[0336] The first guidance unit is configured to, when there is no sub-period in which the upper limit value of the sub-period completion index ratio is less than the corresponding lower limit value of the sub-period completion index ratio, perform index value guidance of the target index type in the target area from the feedback sub-period in the next period according to the first candidate set of regulation index values.

[0337] In some embodiments, the sixth acquisition unit includes:

[0338] The second acquisition subunit is configured to acquire the upper limit value and the lower limit value of the sub-period completion index ratio for each sub-period from the feedback sub-period to the last sub-period in the next period;

[0339] The seventh determination subunit is configured to determine the average upper and lower limits of the completion index ratio for each sub-period based on the upper limit and the lower limit of the sub-period completion index ratio for each sub-period.

[0340] In some embodiments, the first adjustment unit includes:

[0341] The eighth determination subunit is configured to, when there is a regulation index value of a first sub-period in the first candidate set of regulation index values that is greater than the average upper and lower limits of the completion index ratio of the target sub-period, determine a first adjustment value based on the regulation index value in the first sub-period and the average upper and lower limits of the completion index ratio of the first sub-period;

[0342] The first adjustment subunit is configured to adjust the lower limit value of the sub-period completion index ratio of the first sub-period according to the first adjustment value;

[0343] A ninth determination subunit, configured to, when there is a control index value in the second sub-period in the first candidate control index value set that is less than the average of the upper and lower limits of the completion index ratio of the target sub-period, determine a second adjustment value based on the control index value in the second sub-period and the average of the upper and lower limits of the completion index ratio of the second sub-period;

[0344] A second adjustment subunit, configured to adjust the upper limit value of the sub-period completion index ratio of the second sub-period according to the second adjustment value.

[0345] In some embodiments, the apparatus further includes:

[0346] A seventh determination unit, configured to, when there is an upper limit value of the sub-period completion index ratio of a third sub-period that is less than the lower limit value of the corresponding sub-period completion index ratio, determine the average of the upper and lower limits of the adjusted upper limit value and the lower limit value of the sub-period completion index ratio of each sub-period from the feedback sub-period to the previous fourth sub-period of the third sub-period as the control index value of the corresponding sub-period;

[0347] An eighth determination unit, configured to determine the upper limit value or the lower limit value of the sub-period completion index ratio of the third sub-period as the control index value of the third sub-period;

[0348] A seventh acquisition unit, configured to acquire a second control index value range set for the target index type in the target area, where the second control index value range set includes the control index value range of each sub-period from the fifth sub-period after the third sub-period to the last sub-period in the next period;

[0349] A second simulation unit, configured to simulate the corresponding total area index value according to different control index value sets combined by the control index value ranges of each sub-period from the fifth sub-period after the third sub-period to the last sub-period;

[0350] A ninth determination unit, configured to determine the control index value set corresponding to the largest total area index value as the second candidate control index value set of the target index type in the target area from the fifth sub-period after the third sub-period;

[0351] An eighth acquisition unit, configured to acquire the average of the upper and lower limits of the sub-period completion index ratio of each sub-period from the fifth sub-period to the last sub-period in the next period;

[0352] A second adjustment unit, configured to adjust the upper limit value or the lower limit value of the sub-period completion index ratio of the sub-periods in the second candidate regulation index value set, where the regulation index value in the sub-period is different from the average of the upper and lower limits of the corresponding sub-period completion index ratio, so as to obtain the adjusted upper limit value of the sub-period completion index ratio and the adjusted lower limit value of the sub-period completion index ratio for each sub-period;

[0353] A second guidance unit, configured to, when there is no case where the upper limit value of the sub-period completion index ratio of a sub-period is less than the lower limit value of the corresponding sub-period completion index ratio, perform guidance on the index value of the target index type in the target area starting from the feedback sub-period in the next period according to the regulation index value of each sub-period from the third feedback sub-period to the fourth sub-period, the regulation index value of the third sub-period, and the second candidate regulation index value set of the fifth sub-period after the third sub-period.

[0354] For the specific implementation of each of the above units, reference may be made to the previous embodiments, which will not be elaborated here.

[0355] As can be seen from the above, in the embodiment of the present application, a first acquisition unit 401 acquires a set of guidance index value ranges and a set of declared index value ranges. The set of guidance index value ranges includes the guidance index value ranges of each region, and the set of declared index value ranges includes the declared index value ranges of each region. A screening unit 402 screens out a set of static guidance index values from the set of guidance index value ranges based on the total region revenue function and the region revenue function, and screens out a set of static declared index values from the set of declared index value ranges. The set of static guidance index values includes the static guidance index values of each region, and the set of static declared index values includes the static declared index values of each region. A second acquisition unit 403 acquires the set of guidance index values, the set of declared index values in the current period, and the declared index value of each region. A first determination unit 404 determines the dynamic guidance index value in the next period according to the set of guidance index values, the set of declared index values, and the set of static guidance index values in the current period. A second determination unit 405, for each region, determines the dynamic declared index value in the next period of each region according to the target declared index value in the corresponding current period, the other declared index values in the declared index values of each region except the target declared index value, the set of guidance index values in the current period, and the set of static declared index values, so as to perform index value guidance in the next period according to the dynamic guidance index value and perform index value declaration in the next period according to the dynamic declared index value of each region.

[0356] Therefore, in the given set of guiding index value ranges and the set of declared index value ranges, according to the total regional revenue function and the regional revenue function, the optimal static guiding index value set and the optimal static declared index value set are respectively selected. Combining the guiding index value set, the declared index value set already set in the current period, and the declared index values of each region, the dynamic guiding index value for the next period is determined. And by combining the target declared index value in the current period, the other declared index values in the declared index values of each region except the target declared index value, the guiding index value set in the current period, and the static declared index value set, the dynamic declared index value for each region in the next period is determined. Compared with the related art where only manual determination of guiding index values and declared index values is possible, the embodiments of the present application can improve the matching degree between the issued index values and the actual situations of each prefecture-level city, and enhance economic stability.

[0357] For the specific implementation of each of the above units, reference may be made to the previous embodiments, which will not be elaborated here.

[0358] To facilitate better implementation of the model training method provided by the embodiments of the present application, the embodiments of the present application also provide a device based on the above model training method. The meanings of the nouns are the same as those in the above model training method, and the specific implementation details can refer to the descriptions in the method embodiments.

[0359] Refer to Figure 4 , Figure 4 Shown is a partial structural block diagram of the terminal 140 for implementing the embodiments of the present disclosure. The terminal 140 includes components such as a radio frequency (RF) circuit 610, a memory 615, an input unit 630, a display unit 640, a sensor 660, an audio circuit 660, a wireless fidelity (WiFi) module 670, a processor 680, and a power supply 690. Those skilled in the art can understand that Figure 4 The shown structure of the terminal 140 does not constitute a limitation on a mobile phone or a computer, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0360] The RF circuit 610 can be used for receiving and transmitting signals during information reception or call processes. Specifically, after receiving the downlink information from the base station, it is given to the processor 680 for processing; in addition, the designed uplink data is sent to the base station.

[0361] The memory 615 can be used to store software programs and modules. The processor 680 executes various functional applications and index value determinations of the terminal by running the software programs and modules stored in the memory 615.

[0362] The input unit 630 can be used to receive input digital or character information and generate key signal inputs related to the settings and function control of the terminal. Specifically, the input unit 630 can include a touch panel 631 and other input devices 632.

[0363] The display unit 640 can be used to display the input information or provided information and various menus of the terminal. The display unit 640 can include a display panel 641.

[0364] The audio circuit 660, speaker 661, and microphone 662 can provide an audio interface.

[0365] In this embodiment, the processor 680 included in the terminal 140 can execute the method for determining the index value based on the master-slave game theory or the model training method in the previous embodiment.

[0366] The terminal 140 in the embodiments of the present disclosure includes, but is not limited to, mobile phones, computers, intelligent voice interaction devices, smart home appliances, vehicle terminals, aircraft, etc. The embodiments of the present invention can be applied to various scenarios, including but not limited to cloud technology, artificial intelligence, intelligent transportation, assisted driving, etc.

[0367] Figure 5 It is a block diagram of a part of the server 110 for implementing the embodiments of the present disclosure. The server 110 may vary greatly due to different configurations or performances, and may include one or more central processing units (CPUs) 722 (for example, one or more processors) and a memory 732, and one or more storage media 730 (for example, one or more mass storage devices) for storing application programs 742 or data 744. Among them, the memory 732 and the storage media 730 can be transient storage or persistent storage. The program stored in the storage media 730 can include one or more modules (not shown in the figure), and each module can include a series of instruction operations on the server 700. Further, the central processing unit 722 can be configured to communicate with the storage media 730 and execute a series of instruction operations in the storage media 730 on the server 700.

[0368] The server 110 may further include one or more power supplies 727, one or more wired or wireless network interfaces 750, one or more input / output interfaces 758, and / or one or more operating systems 741, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0369] The central processing unit 722 in server 110 can be used to execute the method for determining the index value based on the master-slave game theory according to the embodiments of the present disclosure, that is: obtaining a set of guidance index value ranges and a set of declared index value ranges, where the set of guidance index value ranges includes the guidance index value ranges for each region, and the set of declared index value ranges includes the declared index value ranges for each region; based on the total regional revenue function and the regional revenue function, screening out a set of static guidance index values from the set of guidance index value ranges, and screening out a set of static declared index values from the set of declared index value ranges, where the set of static guidance index values includes the static guidance index values for each region, and the set of static declared index values includes the static declared index values for each region; obtaining the set of guidance index values, the set of declared index values, and the declared index value for each region at the current time period; determining the dynamic guidance index value for the next time period according to the set of guidance index values, the set of declared index values, and the set of static guidance index values at the current time period; for each region, determining the dynamic declared index value for each region for the next time period according to the target declared index value at the corresponding current time period, the other declared index values in the declared index values for each region except the target declared index value, the set of guidance index values at the current time period, and the set of static declared index values, so as to conduct index value guidance for the next time period according to the dynamic guidance index value, and conduct index value declaration for the next time period according to the dynamic declared index value for each region.

[0370] An embodiment of the present disclosure also provides a computer-readable storage medium, which is used to store program codes for executing the method for determining the index value based on the principal-agent game theory in each of the foregoing embodiments, that is: obtaining a set of guidance index value ranges and a set of declared index value ranges, where the set of guidance index value ranges includes the guidance index value ranges of each region, and the set of declared index value ranges includes the declared index value ranges of each region; based on the total region revenue function and the region revenue function, screening out a set of static guidance index values from the set of guidance index value ranges, and screening out a set of static declared index values from the set of declared index value ranges, where the set of static guidance index values includes the static guidance index values of each region, and the set of static declared index values includes the static declared index values of each region; obtaining the set of guidance index values, the set of declared index values, and the declared index value of each region at the current time period; determining the dynamic guidance index value for the next time period according to the set of guidance index values, the set of declared index values, and the set of static guidance index values at the current time period; for each region, determining the dynamic declared index value for the next time period according to the target declared index value at the corresponding current time period, the other declared index values in the declared index values of each region except the target declared index value, the set of guidance index values at the current time period, and the set of static declared index values, so as to conduct index value guidance for the next time period according to the dynamic guidance index value, and conduct index value declaration for the next time period according to the dynamic declared index value of each region.

[0371] An embodiment of the present disclosure also provides a computer program product, which includes a computer program. The processor of the computer device reads and executes the computer program, so that the computer device executes and implements the foregoing method for determining the index value based on the principal-agent game theory or the model training method.

[0372] In addition, the terms "including" and "comprising" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0373] It should be understood that in the present disclosure, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may mean: only A exists, only B exists, and both A and B exist simultaneously. Here, A and B can be singular or plural. The character " / " generally indicates an "or" relationship between the associated objects before and after. "At least one (individual) of the following" or its similar expressions refer to any combination of these items, including any combination of single items (individuals) or plural items (individuals). For example, at least one (individual) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0374] It should be understood that in the description of the embodiments of the present disclosure, the meaning of "a plurality (or multiple items)" is more than two. Understandings such as greater than, less than, exceeding, etc. do not include the present number, and understandings such as above, below, within, etc. include the present number.

[0375] In several embodiments provided by the present disclosure, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0376] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0377] In addition, each functional unit in various embodiments of the present disclosure can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0378] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM for short), random access memories (RAM for short), magnetic disks, or optical discs.

[0379] It should also be understood that the various embodiments provided in the present disclosure can be combined arbitrarily to achieve different technical effects.

[0380] In the embodiments of the present application, the term "module" or "unit" refers to a computer program with a predetermined function or a part of a computer program, which works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of the overall module or unit that includes the function of this module or unit.

[0381] The above is a specific description of the embodiments of the present disclosure, but the present disclosure is not limited to the above embodiments. Those skilled in the art can also make various equivalent deformations or substitutions without departing from the spirit of the present disclosure, and these equivalent deformations or substitutions are all included within the scope defined by the claims of the present disclosure.

Claims

1. A method for determining an indicator value based on master-slave game theory, characterized in that: include: Obtaining a guidance indicator value range set and a declared indicator value range set, wherein the guidance indicator value range set includes the guidance indicator value range of each region, and the declared indicator value range set includes the declared indicator value range of each region; Based on the total regional benefit function and the regional benefit function, a static guiding indicator value set is screened out from the guiding indicator value range set, and a static declaration indicator value set is screened out from the declaration indicator value range set, wherein the static guiding indicator value set includes the static guiding indicator value of each region, and the static declaration indicator value set includes the static declaration indicator value of each region; Obtain the guidance indicator value set, the declared indicator value set and the declared indicator value of each area for the current period; Determine the dynamic guiding indicator value for the next period according to the guiding indicator value set, the declared indicator value set and the static guiding indicator value set for the current period; For each area, the dynamic declaration index value of each area for the next time period is determined based on the corresponding target declaration index value of the current time period, the declaration index values ​​of each area except the target declaration index value, the guidance index value set of the current time period and the static declaration index value set, so as to provide indicator value guidance for the next time period according to the dynamic guidance index value and declare the indicator value for the next time period according to the dynamic declaration index value of each area.

2. The method for determining an indicator value based on master-slave game theory according to claim 1, characterized in that: The step of selecting a static guiding indicator value set from the guiding indicator value range set based on the total regional benefit function and the regional benefit function, and selecting a static declaration indicator value set from the declaration indicator value range set, comprises: Obtain a set of historical guidance indicator values, and obtain a set of historical declared indicator values ​​for each region; Determining an initial guiding indicator value set from the guiding indicator value range set, and determining an initial declared indicator value for each region from the declared indicator value range set; Determine a set of constraint ranges of guiding indicator values ​​according to the set of historical guiding indicator values ​​and the initial declared indicator values ​​of each region; Determine the total regional benefit value corresponding to each candidate guiding indicator value set in the guiding indicator value constraint range set through the total regional benefit function, and determine the target guiding indicator value set corresponding to the maximum total regional benefit value; For each region, determine the declared index value constraint range according to the target guidance index value set, the corresponding historical declared index value and the initial declared index value of other regions; Determine the regional benefit value corresponding to each candidate declared index value within the declared index value constraint range through the regional benefit function, and determine the target declared index value corresponding to the maximum regional benefit value; When the sum of each guidance indicator value in the target guidance indicator value set is different from the sum of the target declared indicator values ​​corresponding to each region, the target declared indicator value of each region is determined as the corresponding initial declared indicator value, the sum of each guidance indicator value in the target guidance indicator value set is determined as the initial guidance indicator value, and the step of determining the guidance indicator value constraint range set based on the historical guidance indicator value set and the initial declared indicator value of each region is returned to execute until the sum of each guidance indicator value in the target guidance indicator value set is the same as the sum of the target declared indicator values ​​corresponding to each region, the final target guidance indicator value set is determined as the static guidance indicator value set, the final target declared indicator value of each region is determined as the static declared indicator value, and a static declared indicator value set is obtained.

3. The method for determining an indicator value based on master-slave game theory according to claim 2, characterized in that: The determining, by using the total regional benefit function, the total regional benefit value corresponding to each candidate guiding indicator value set in the guiding indicator value constraint range set includes: For each candidate guiding indicator value set in the guiding indicator value constraint range set, determine the total regional plan indicator value based on the candidate guiding indicator value set and the sum of each of the initial declared indicator values; Determine the total regional indicator benefit value corresponding to the total regional plan indicator value through the indicator benefit sub-function in the total regional benefit function; Filter out a first minimum distance value from the sum of the initial declared index values ​​from a plurality of total guiding index values ​​whose distance values ​​from the sum of the candidate guiding index value set are within a first preset distance value; Calculate the standard deviation of the candidate guiding indicator value set and the guiding indicator value set for the current period to obtain the growth rate standard deviation; The total regional benefit value is determined according to the total regional indicator benefit value, the first minimum distance value and the growth rate standard deviation, and the total regional benefit value corresponding to each candidate guidance indicator value set is obtained.

4. The method for determining an indicator value based on master-slave game theory according to claim 3, characterized in that: The regional benefit value corresponding to each candidate declared index value in the declared index value constraint range is determined by the regional benefit function, including: For each candidate declared index value, obtain the regional benefit sub-function of the corresponding region in the regional benefit function; Determine the regional planning indicator value based on the candidate guiding indicator value set and the sum of each of the initial declared indicator values; Determining the regional index benefit value corresponding to the regional plan index value through the regional benefit sub-function; Filtering out a second minimum distance value of the target guiding indicator value corresponding to the area in the target guiding indicator value set from a plurality of declared indicator values ​​whose distance values ​​to the initial declared indicator value corresponding to the area are within a first preset distance value; The regional benefit value is determined based on the regional index benefit value and the second minimum distance value, and the regional benefit value corresponding to each candidate declared index value is obtained.

5. The method for determining an indicator value based on master-slave game theory according to claim 1, characterized in that: The determining the dynamic guiding indicator value for the next period according to the guiding indicator value set, the declared indicator value set and the static guiding indicator value set for the current period includes: The total area prediction value is obtained by calculating the declared index value set and the static guidance index value set for the current period through the total area expectation function; The guidance indicator value set and the total regional prediction value of the current time period are weightedly summed to obtain the dynamic guidance indicator value of the next time period.

6. The method for determining an indicator value based on master-slave game theory according to claim 1, characterized in that: The method of determining the dynamic declaration index value of each region for the next period of time according to the corresponding target declaration index value of the current period, other declaration index values ​​of each region except the target declaration index value, the guidance index value set of the current period of time and the static declaration index value set for each region includes: For each region, obtain the regional expectation function corresponding to the region; By using the regional expectation function, the guiding indicator value set of the current period, the static declared indicator value set, and the declared indicator values ​​of each region other than the target declared indicator value are calculated to obtain the regional prediction value; The target declaration index value for the current period corresponding to the region and the predicted value of the region are weightedly summed to obtain the dynamic declaration index value for the next period.

7. The method for determining an indicator value based on master-slave game theory according to claim 1, characterized in that: After determining the dynamic declaration index value of each region for the next period according to the corresponding target declaration index value of the current period, other declaration index values ​​of each region except the target declaration index value, the guidance index value set of the current period and the static declaration index value set for each region, the method further includes: Obtain the indicator feedback value of each indicator type in the feedback sub-period of each region in the next period, and determine the operating status evaluation value of each indicator type in the feedback sub-period of each region in the next period based on the mean value of the indicator completion ratio of the historical sub-period of each indicator type in the feedback sub-period, the standard deviation of the indicator completion ratio of the historical sub-period of the feedback sub-period, the mean value of the cumulative indicator completion ratio from the historical period to the feedback sub-period, and the standard deviation of the cumulative indicator completion ratio from the historical period to the feedback sub-period; Compare the operating status assessment value of each indicator type with the corresponding control recommendation value; The indicator type having a different operating status evaluation value from a corresponding control recommendation value in the target area is determined as the target indicator type; Acquire multiple warning intervals corresponding to the target indicator type in the target area; Determine the target warning interval in which the target operating status evaluation value of the target indicator type lies; Determine the target warning level corresponding to the target warning interval based on the preset mapping relationship between the warning interval and the warning level; Prompt information is generated to prompt that the operating status evaluation value of the target indicator type in the target area is at a target warning level.

8. The method for determining an indicator value based on master-slave game theory according to claim 7, characterized in that: After the prompt information is generated, the method further includes: Acquire a first control indicator value range set for the target indicator type in the target area, wherein the first control indicator value range set includes a control indicator value range of each sub-period from the feedback sub-period to the last sub-period in the next period; Different sets of control index values ​​are combined according to the range of control index values ​​in each sub-period, and the corresponding total regional index values ​​are simulated; Determine a control index value set corresponding to the maximum total regional index value as a first candidate control index value set for the target index type in the target region from the feedback sub-period to the last sub-period; Obtain the average of the upper and lower limits of the sub-period completion indicator ratio of each sub-period from the feedback sub-period to the last sub-period in the next period; Adjust the upper limit value of the sub-period completion indicator ratio or the lower limit value of the sub-period completion indicator ratio of the sub-period whose control indicator value in the first candidate control indicator value set is different from the average of the upper and lower limits of the corresponding sub-period completion indicator ratio, to obtain the adjusted upper limit value of the sub-period completion indicator ratio and the lower limit value of the sub-period completion indicator ratio for each sub-period; When there is no sub-period in which the upper limit value of the sub-period completion index ratio is less than the corresponding sub-period completion index ratio lower limit value, the indicator value guidance of the target indicator type in the target area in the next period starting from the feedback sub-period is performed according to the first candidate control indicator value set.

9. The method for determining an indicator value based on master-slave game theory according to claim 8, characterized in that: The obtaining of the average of the upper and lower limits of the sub-period completion indicator ratio of each sub-period from the feedback sub-period to the last sub-period in the next period includes: Obtaining the upper limit value of the sub-period completion index ratio and the lower limit value of the sub-period completion index ratio of each sub-period from the feedback sub-period to the last sub-period in the next period; Based on the upper limit of the sub-period completion index ratio and the lower limit of the sub-period completion index ratio of each sub-period, the average of the upper and lower limits of the completion index ratio of each sub-period is determined.

10. The method for determining an indicator value based on master-slave game theory according to claim 8, characterized in that: The adjusting of the upper limit value of the sub-period completion index ratio or the lower limit value of the sub-period completion index ratio of the sub-period in which the control index value in the first candidate control index value set is different from the average of the upper and lower limits of the corresponding sub-period completion index ratio to obtain the adjusted upper limit value of the sub-period completion index ratio and the lower limit value of the sub-period completion index ratio of each sub-period, includes: When there is a control index value of the first sub-period in the first candidate control index value set that is greater than the average of the upper and lower limits of the completion index ratio of the target sub-period, a first adjustment value is determined based on the control index value in the first sub-period and the average of the upper and lower limits of the completion index ratio of the first sub-period; Adjust the lower limit of the sub-period completion index ratio of the first sub-period according to the first adjustment value; When there is a control index value of the second sub-period in the first candidate control index value set that is less than the average of the upper and lower limits of the completion index ratio of the target sub-period, a second adjustment value is determined based on the control index value in the second sub-period and the average of the upper and lower limits of the completion index ratio of the second sub-period; The upper limit value of the sub-period completion index ratio of the second sub-period is adjusted according to the second adjustment value.

11. The method for determining an indicator value based on master-slave game theory according to claim 8, characterized in that: The method further comprises: When there is a third sub-period in which the upper limit of the sub-period completion index ratio is less than the corresponding lower limit of the sub-period completion index ratio, the upper limit of the sub-period completion index ratio and the lower limit of the sub-period completion index ratio adjusted for each sub-period from the feedback sub-period to the fourth sub-period before the third sub-period are averaged as the control index value of the corresponding sub-period; Determine the upper limit value of the sub-period completion index ratio or the lower limit value of the sub-period completion index ratio of the third sub-period as the control index value of the third sub-period; Acquire a second control indicator value range set for the target indicator type in the target area, the second control indicator value range set comprising a control indicator value range of each sub-period from a fifth sub-period after the third sub-period to a last sub-period in the next time period; Simulate the corresponding total regional index value according to different sets of control index values ​​combined from the control index value range of each sub-period from the fifth sub-period after the third sub-period to the last sub-period; Determine the control index value set corresponding to the maximum total regional index value as the second candidate control index value set for the target index type in the target area in the fifth sub-period after the third sub-period; Obtain the average of the upper and lower limits of the sub-period completion indicator ratio of each sub-period from the fifth sub-period to the last sub-period in the next period; Adjust the upper limit value of the sub-period completion indicator ratio or the lower limit value of the sub-period completion indicator ratio of the sub-period whose control indicator value in the second candidate control indicator value set is different from the average of the upper and lower limits of the corresponding sub-period completion indicator ratio, to obtain the adjusted upper limit value of the sub-period completion indicator ratio and the lower limit value of the sub-period completion indicator ratio for each sub-period; When there is no sub-period in which the upper limit value of the sub-period completion index ratio is less than the corresponding lower limit value of the sub-period completion index ratio, the indicator value guidance of the target indicator type in the target area in the next period starting from the feedback sub-period is carried out according to the control index value of each sub-period from the third feedback sub-period to the fourth sub-period, the control index value of the third sub-period, and the second candidate control index value set of the fifth sub-period after the third sub-period.

12. An indicator value determination device, characterized in that: include: A first acquisition unit is used to acquire a guidance indicator value range set and a declaration indicator value range set, wherein the guidance indicator value range set includes the guidance indicator value range of each region, and the declaration indicator value range set includes the declaration indicator value range of each region; A screening unit, configured to screen out a static guiding indicator value set from the guiding indicator value range set based on the total regional benefit function and the regional benefit function, and screen out a static declaration indicator value set from the declaration indicator value range set, wherein the static guiding indicator value set includes a static guiding indicator value for each region, and the static declaration indicator value set includes a static declaration indicator value for each region; The second acquisition unit is used to acquire the guidance indicator value set, the declared indicator value set and the declared indicator value of each area in the current period; A first determining unit, configured to determine a dynamic guiding indicator value for a next period according to the guiding indicator value set, the declared indicator value set and the static guiding indicator value set for a current period; The second determination unit is used to determine the dynamic declaration index value of each area for the next time period according to the corresponding target declaration index value of the current time period, the other declaration index values ​​of each area except the target declaration index value, the guidance index value set of the current time period and the static declaration index value set, so as to provide indicator value guidance for the next time period according to the dynamic guidance index value and declare the indicator value for the next time period according to the dynamic declaration index value of each area.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the method for determining an indicator value based on the master-slave game theory as described in any one of claims 1 to 11.

14. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for determining an indicator value based on the master-slave game theory according to any one of claims 1 to 11 is implemented.

15. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the method for determining an indicator value based on master-slave game theory as described in any one of claims 1 to 11 is implemented.

Images