GDP prediction method and device based on energy production

Abstract

The invention provides a GDP prediction method and device based on energy production. The method comprises the steps of obtaining a GDP prediction instruction input by a user; according to the GDP prediction instruction, determining a GDP prediction model corresponding to the target region, and obtaining a generalized currency accumulated issuing amount and an energy production accumulated total amount corresponding to each time unit of the target region in a historical time period, and an energy production amount of the target region in a target time period; and obtaining a GDP predicted value of the target region in the target time period according to the information. According to the GDP prediction method provided by the embodiment of the invention, the used data is convenient to obtain, the required data volume is small, the processing process is simple, hardware processing resources are saved, the processing efficiency is improved, the GDP prediction value has certain precision, and the balance between the precision and the efficiency is achieved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular, to a GDP prediction method and device based on energy production. Background Art

[0002] Gross Domestic Product (GDP) is the final result of the production activities of all resident units in a country (or region) within a certain period. GDP is the core indicator of national economic accounting and an important indicator for measuring the economic situation and development level of a country or region. Therefore, the change in GDP can reflect the change in the economic situation of a country or region, which has important reference value for policymakers and researchers. Therefore, accurately, quickly, and timely predicting GDP plays an important role in the future development planning of a country or region.

[0003] Currently, there are also various methods for predicting GDP, such as the economic model method and the big data method. Among them, the economic model method uses the relationship between historical data and economic indicators to establish an economic model to predict the change in GDP in the future for a period of time. This method has strong timeliness, but it is necessary to continuously update the model parameters to adapt to the change of the economic environment. The big data method uses a large amount of economic data generated by the Internet and the Internet of Things, and through data mining and analysis, predicts GDP in real time or near real time.

[0004] However, the methods for predicting GDP currently require a large amount of data, a large amount of processing, a complex processing process, and occupy more hardware processing resources. Summary of the Invention

[0005] This application provides a GDP prediction method and device based on energy production to solve the technical problems mentioned in the background art.

[0006] In a first aspect, this application provides a GDP prediction method based on energy production, including:

[0007] Obtain a GDP prediction instruction input by a user, where the GDP prediction instruction includes: the target region, target time period, and historical time period for the user to predict GDP. Among them, when divided according to the time unit corresponding to the target time period, the historical time period includes at least one time unit;

[0008] According to the GDP prediction instruction, obtain the GDP prediction model corresponding to the target region pre-stored in the memory, and obtain from the memory the cumulative amount of broad money issued and the cumulative total amount of energy production corresponding to each time unit in the historical time period of the target region, as well as the energy production volume of the target region in the target time period. Wherein, the GDP prediction model is a linear model obtained by training with multiple sets of sample historical data corresponding to the target region, and each set of the sample historical data includes: historical cumulative amount of broad money issued, historical cumulative total amount of energy production, historical energy production volume, and historical GDP;

[0009] According to the GDP prediction model corresponding to the target region, the cumulative amount of broad money issued and the cumulative total amount of energy production corresponding to each time unit in the historical time period, and the energy production volume of the target region in the target time period, obtain and output to the user the GDP prediction value of the target region in the target time period.

[0010] Optionally, before determining the GDP prediction model corresponding to the target region according to the GDP prediction instruction, it further includes:

[0011] Obtain multiple sets of sample historical data of the target region;

[0012] Use the historical cumulative amount of broad money issued, the historical cumulative total amount of energy production, and the historical energy production volume in the sample historical data as the input of the initial GDP prediction model, and the historical GDP as the output of the initial GDP prediction model, and obtain and store the GDP prediction model in the memory.

[0013] Optionally, using the historical cumulative amount of broad money issued, the historical cumulative total amount of energy production, and the historical energy production volume in the sample historical data as the input of the initial GDP prediction model, and the historical GDP as the output of the initial GDP prediction model to obtain the GDP prediction model includes:

[0014] Use the historical cumulative amount of broad money issued, the historical cumulative total amount of energy production, and the historical energy production volume in the sample historical data as the input of the initial GDP prediction model, and the historical GDP as the output of the initial GDP prediction model to obtain the industrial structure coefficient in the GDP prediction model, and the industrial structure coefficient represents the industrial structure of the target region;

[0015] Obtain the GDP prediction model according to the industrial structure coefficient and the initial GDP prediction model.

[0016] Optionally, taking the cumulative historical broad money circulation volume, the cumulative total historical energy production volume, and the historical energy production volume in the sample historical data as the inputs of the initial GDP prediction model, and the historical GDP as the output of the initial GDP prediction model to obtain the industrial structure coefficient in the GDP prediction model, includes:

[0017] Taking the cumulative historical broad money circulation volume, the cumulative total historical energy production volume, and the historical energy production volume in each group of the sample historical data as the inputs of the initial GDP prediction model, and the GDP in each group of the sample historical data as the output of the initial GDP prediction model to obtain the industrial structure coefficient corresponding to each group of the sample historical data;

[0018] Obtaining the industrial structure coefficient in the GDP prediction model according to the industrial structure coefficient corresponding to each group of the sample historical data.

[0019] Optionally, the obtaining the industrial structure coefficient in the GDP prediction model according to the industrial structure coefficient corresponding to each group of the sample historical data includes:

[0020] Obtaining the distribution map of the industrial structure coefficient corresponding to each group of the sample historical data;

[0021] Determining the industrial structure coefficient according to the distribution density of the industrial structure coefficient corresponding to each group of the sample historical data in the distribution map.

[0022] Optionally, the obtaining the multiple groups of sample historical data of the target area includes:

[0023] Obtaining multiple groups of sample historical data of the target area divided by different time units.

[0024] Optionally, the GDP prediction model is:

[0025]

[0026] wherein, K represents the industrial structure coefficient, and the value range of K corresponds to the target area;

[0027] n is the number of the time units included in the historical time period;

[0028] M2 i is the cumulative broad money circulation volume corresponding to the i-th time unit in the historical time period;

[0029] W i is the cumulative total energy production volume corresponding to the i-th time unit in the historical time period;

[0030] where \(w\) is the energy production volume during the target time period.

[0031] In a second aspect, the present application provides a GDP prediction device based on energy production, including:

[0032] A first acquisition module, configured to acquire a GDP prediction instruction input by a user, where the GDP prediction instruction includes: a target region, a target time period, and a historical time period for which the user predicts GDP. When divided according to the time unit corresponding to the target time period, the historical time period includes at least one time unit;

[0033] A second acquisition module, configured to, according to the GDP prediction instruction, acquire a GDP prediction model corresponding to the target region pre-stored in a memory, the cumulative amount of broad money issuance and the cumulative total amount of energy production corresponding to each time unit within the historical time period in the memory for the target region, and the energy production volume of the target region during the target time period. The GDP prediction model is a linear model obtained by training with multiple sets of sample historical data corresponding to the target region. Each set of the sample historical data includes: historical cumulative broad money issuance, historical cumulative total energy production, historical energy production volume, and historical GDP;

[0034] A prediction module, configured to, according to the GDP prediction model corresponding to the target region, the cumulative amount of broad money issuance and the cumulative total amount of energy production corresponding to each time unit within the historical time period, and the energy production volume of the target region during the target time period, acquire and output to the user the GDP prediction value of the target region during the target time period.

[0035] Optionally, the device further includes: a training module;

[0036] Before the second acquisition module determines the GDP prediction model corresponding to the target region according to the GDP prediction instruction, the training module is configured to:

[0037] Acquire multiple sets of sample historical data of the target region;

[0038] Use the historical cumulative broad money issuance, historical cumulative total energy production, and historical energy production volume in the sample historical data as the input of an initial GDP prediction model, and the historical GDP as the output of the initial GDP prediction model, and acquire and store the GDP prediction model in the memory.

[0039] Optionally, when the training module uses the cumulative historical broad money issuance, cumulative total historical energy production, and historical energy production volume in the sample historical data as the inputs of the initial GDP prediction model, and the historical GDP as the output of the initial GDP prediction model to obtain the GDP prediction model, it is specifically used for:

[0040] Use the cumulative historical broad money issuance, cumulative total historical energy production, and historical energy production volume in the sample historical data as the inputs of the initial GDP prediction model, and the historical GDP as the output of the initial GDP prediction model to obtain the industrial structure coefficient in the GDP prediction model, where the industrial structure coefficient represents the industrial structure of the target region;

[0041] Obtain the GDP prediction model based on the industrial structure coefficient and the initial GDP prediction model.

[0042] Optionally, when the training module uses the cumulative historical broad money issuance, cumulative total historical energy production, and historical energy production volume in the sample historical data as the inputs of the initial GDP prediction model, and the historical GDP as the output of the initial GDP prediction model to obtain the industrial structure coefficient in the GDP prediction model, it is specifically used for:

[0043] Use the cumulative historical broad money issuance, cumulative total historical energy production, and historical energy production volume in each group of the sample historical data as the inputs of the initial GDP prediction model, and the GDP in each group of the sample historical data as the output of the initial GDP prediction model to obtain the industrial structure coefficient corresponding to each group of the sample historical data;

[0044] Obtain the industrial structure coefficient in the GDP prediction model based on the industrial structure coefficient corresponding to each group of the sample historical data.

[0045] Optionally, when the training module obtains the industrial structure coefficient in the GDP prediction model based on the industrial structure coefficient corresponding to each group of the sample historical data, it is specifically used for:

[0046] Obtain the distribution map of the industrial structure coefficient corresponding to each group of the sample historical data;

[0047] Determine the industrial structure coefficient according to the distribution density of the industrial structure coefficient corresponding to each group of the sample historical data in the distribution map.

[0048] Optionally, when the training module obtains multiple groups of sample historical data of the target region, it is specifically used for:

[0049] Obtain multiple groups of sample historical data of the target region divided by different time units.

[0050] Optionally, the GDP prediction model is as follows:

[0051]

[0052] where K represents the industrial structure coefficient, and the value range of K corresponds to the target region;

[0053] n is the number of time units included in the historical time period;

[0054] M2 i is the cumulative circulation volume of broad money corresponding to the i-th time unit in the historical time period;

[0055] W i is the cumulative total energy production corresponding to the i-th time unit in the historical time period;

[0056] w is the energy production in the target time period.

[0057] In a third aspect, the present application provides an electronic device, including: a processor and a memory;

[0058] The memory stores computer-executable instructions;

[0059] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the method according to any one of the first aspect.

[0060] In a fourth aspect, an embodiment of the present application provides a readable storage medium, including a program or instructions. When the program or instructions are run on a computer, the method according to any one of the above first aspects is executed.

[0061] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the method according to any one of the first aspect is implemented.

[0062] The GDP prediction method and device based on energy production provided by this application obtain a GDP prediction instruction input by a user. The GDP prediction instruction includes: the target region, target time period, and historical time period for which the user predicts GDP. When divided according to the time unit corresponding to the target time period, the historical time period includes at least one time unit. According to the GDP prediction instruction, a GDP prediction model corresponding to the target region is determined, and the cumulative broad money issuance and cumulative total energy production corresponding to each time unit within the historical time period of the target region, as well as the energy production volume of the target region during the target time period, are obtained. The GDP prediction model is a linear model trained using multiple sets of sample historical data corresponding to the target region. According to the GDP prediction model corresponding to the target region, the cumulative broad money issuance and cumulative total energy production corresponding to each time unit within the historical time period, and the energy production volume of the target region during the target time period, a GDP prediction value for the target region during the target time period is obtained. Compared with the existing GDP prediction methods, the data used in the GDP prediction method provided in this embodiment is easy to obtain, requires less data volume, has a simple processing process, saves hardware processing resources and improves processing efficiency, and the GDP prediction value has a certain accuracy, achieving a balance between accuracy and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] To more clearly illustrate the technical solutions in the embodiments of this application or in the prior art, the following briefly introduces the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0064] Figure 1 It is a flowchart of the GDP prediction method based on energy production provided by an embodiment of this application;

[0065] Figure 2 It is a flowchart of the training method of the GDP prediction model provided by an embodiment of this application;

[0066] Figure 3 It is a schematic structural diagram of the GDP prediction device based on energy production provided by an embodiment of this application;

[0067] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0068] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following provides a clear and complete description of the technical solutions in the embodiments of this application. Obviously, the described embodiments are some, but not all, of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts also belong to the scope of protection of this application.

[0069] In view of the technical problems that the current methods for predicting GDP require a large amount of data, involve a large processing volume, and have a complex processing process, this application proposes a GDP prediction method and device based on energy production. Since GDP is the core indicator of national economic accounting, changes in GDP can reflect changes in the economic conditions of a country or region. Economic activities mainly involve exchange behaviors, and currency participates in the entire exchange process as a medium. Moreover, the broad money M2 participates in the entire exchange process more comprehensively and completely than the cash in circulation M0 and the narrow money M1. Additionally, according to the role of currency in dividing the barter process and the principle of equal-energy exchange, there is a linear relationship between currency and energy. Therefore, the economic conditions of a region can be reflected through the broad money M2 and the energy production volume. Thus, this application predicts the GDP of a region through the broad money M2. Specifically, a GDP prediction model is obtained through the broad money M2 and the total energy production volume. Among them, the GDP prediction model is a linear model. Then, when predicting GDP through the GDP prediction model, only the corresponding broad money M2, the total energy production volume, and the energy production volume need to be obtained to predict the GDP. Therefore, the amount of data required is less compared with the prior art. Moreover, since the GDP prediction model is a linear model, the processing volume is small, the processing process is simple, and the hardware processing resources occupied are few.

[0070] Figure 1 This is a flowchart of the GDP prediction method based on energy production provided by an embodiment of this application. Among them, Figure 1 The execution subject of the shown method can be an electronic device (such as a computer, a server, a handheld terminal, etc.). As Figure 1 shown, the method includes:

[0071] S101. Obtain a GDP prediction instruction input by a user.

[0072] Among them, the GDP prediction instruction includes: the target region, the target time period, and the historical time period for which the user predicts the GDP.

[0073] Among them, when divided according to the time unit corresponding to the target time period, the historical time period includes at least one time unit.

[0074] In this step, the target area is divided by administrative units. It can be at the provincial level, such as Beijing City and Shaanxi Province. It can also be at the prefecture-level city level, such as Xi'an City. Or it can be at the administrative district level, or an area with a smaller administrative level.

[0075] The target time period is a time period that has passed but the official has not calculated the GDP in a timely manner. For example, the current time is April 2025. For March 2025, the official has not given the GDP of March 2025. In order to formulate the next economic work plan, it is necessary to know the GDP of March 2025. The GDP prediction method disclosed in this embodiment can be used to predict the GDP of March 2025.

[0076] The historical time period is the time period before the target time period. When predicting the GDP, the target time period is used as the time unit, and the historical time period should include at least one time unit. Generally, the historical time period contains 3 - 5 time units. For example, if the target time period is 2024, the time unit is year, and the historical time period is from 2021 to 2023; if the target time period is the first quarter of 2025, the time unit is quarter (which can also be said to be 3 months), and the historical time period is 2024.

[0077] This embodiment takes Xi'an City as the target area, the GDP of the first quarter of 2025 as the target time period, 2024 as the historical time period, and one quarter as the time unit to illustrate the GDP prediction:

[0078] This application displays input items or options for the target area, target time period, and historical time period to the user through the human - machine interaction interface. The user fills in or selects at the corresponding positions on the human - machine interaction interface that the target location is Xi'an City, the target time period is the first quarter of 2025, and the historical time period is 2024.

[0079] It should be noted that due to the different administrative levels of the target area, input items or options for provinces, cities, districts, and towns are respectively set on the human - machine interaction interface. The user selects according to their own needs from high to low according to the administrative level. For example, if the user predicts the GDP of the first quarter of 2025 for the whole province of Shaanxi, they can just select Shaanxi Province. If the user predicts the GDP of the first quarter of 2025 for Xi'an City, they can select Xi'an City, Shaanxi Province.

[0080] After the user operates on the human - machine interaction interface, the electronic device of this application obtains the user's operation, that is, obtains the GDP prediction instruction.

[0081] S102. According to the GDP prediction instruction, obtain the GDP prediction model corresponding to the target region pre-stored in the memory, and obtain from the memory the cumulative amount of broad money and the cumulative total amount of energy production corresponding to each time unit in the historical time period of the target region, as well as the energy production volume of the target region in the target time period.

[0082] Among them, the GDP prediction model is a linear model obtained by training with multiple groups of sample historical data corresponding to the target region. Each group of sample historical data includes: historical cumulative amount of broad money, historical cumulative total amount of energy production, historical energy production volume, and historical GDP.

[0083] It should be noted that the above cumulative amount refers to the cumulative amount starting from the historical preset time point.

[0084] In this step, the memory database pre-stores GDP prediction models corresponding to different regions. At the same time, it also pre-stores the cumulative amount of broad money and the cumulative total amount of energy production from the historical preset time point to the cut-off time point corresponding to different regions, as well as the energy production volume of different regions in the target time period.

[0085] Among them, the historical preset time point is the time point before the historical time period. In this application, the historical time period generally selects 1 - 60 months before the target time period. Therefore, in this application, the historical preset time point can be selected as January 1, 1990.

[0086] The cut-off time point is related to the last day of each time unit period in the historical time period. For example, if the historical time period is 2024 and the time unit is a quarter, then the corresponding cut-off time points are March 31, 2024, June 30, 2024, September 30, 2024, and December 31, 2024.

[0087] Among them, the energy production volume can generally be replaced by the energy consumption index. Therefore, in this embodiment, the energy production volume is replaced by the energy production volume, and the cumulative total amount of energy production is replaced by the cumulative total amount of energy production. The cumulative total amount of energy production is calculated from the energy production volume between the historical preset time point and the cut-off time point.

[0088] After obtaining the GDP prediction instruction, determine the GDP prediction model corresponding to the target region according to the target region. For example, the GDP prediction model corresponding to the target region is associated with the target region through an identification code, and for different regions, the identification codes are different. Through the identification code of the target region, find the GDP prediction model with the same identification code as the target region.

[0089] Since it is necessary to predict the GDP of the first quarter of 2025 in Xi'an, and the historical time period is 2024, so 2024 contains 4 quarterly time units, and the historical preset time point can be, for example, 1990. Therefore, the cumulative issue volume of broad money from the historical preset time point - the first quarter of 2024 (i.e., from January 1, 1990 to March 31, 2024), the cumulative issue volume of broad money at the historical preset time point - June 30, 2024, the cumulative issue volume of broad money at the historical preset time point - September 30, 2024, and the cumulative issue volume of broad money at the historical preset time point - December 31, 2024 are obtained separately from the database.

[0090] Similarly, the cumulative total energy production at the historical preset time point - March 31, 2024, the cumulative total energy production at the historical preset time point - June 30, 2024, the cumulative total energy production at the historical preset time point - September 30, 2024, and the cumulative total energy production at the historical preset time point - December 31, 2024 are obtained separately from the database.

[0091] Meanwhile, the energy production volume corresponding to the first quarter of 2025 in Xi'an is obtained from the database.

[0092] Among them, the official website of the People's Bank of China regularly publishes the new cumulative issue volume of broad money. As of April 1, 2025, the cumulative issue volume of broad money corresponding to February 2025 can be queried through the official website of the People's Bank of China, and the obtained broad money issue volume is stored in the database of the memory.

[0093] The official website of the statistics bureau regularly publishes the monthly energy production volume, and its unit is ten thousand tons of standard coal. Among them, when the time unit corresponding to the target time period is year, the annual energy production volume is obtained according to the energy production volumes of the 12 months corresponding to that year; when the time unit corresponding to the target time period is quarter, the quarterly energy production volume is obtained from the energy production volumes of the months included in that quarter.

[0094] Therefore, after the energy production volume of the first quarter of 2025 in Xi'an is announced on the official website of the Xi'an Statistics Bureau, it is pre-stored in the database of the memory, and the cumulative total energy production is obtained according to the energy production volume between the historical preset time point and the corresponding cut-off time point.

[0095] Among them, it should be noted that as time goes by, the official website will publish the latest broad money issue volume and energy production volume. Therefore, this application can obtain the latest relevant data according to the update time of each data and store it in the database of the memory to update the database.

[0096] Among them, the GDP prediction model is a linear model, which is obtained by training with a large amount of sample historical data of the target region, and its training process is described in detail in Figure 2 the embodiments and will not be elaborated here.

[0097] Optionally, the GDP prediction model is Formula 1:

[0098]

[0099] Among them, K represents the industrial structure coefficient, and the value of K corresponds to the target region;

[0100] n is the number of time units included in the historical time period;

[0101] M2 i is the cumulative issuance of broad money corresponding to the i-th time unit in the historical time period;

[0102] W i is the cumulative total energy production corresponding to the i-th time unit in the historical time period;

[0103] w is the energy production volume in the time unit to be predicted.

[0104] S103. According to the GDP prediction model corresponding to the target region, the cumulative issuance of broad money and the cumulative total energy production corresponding to each time unit in the historical time period, and the energy production volume of the target region in the target time period, obtain and output to the user the GDP prediction value of the target region in the target time period.

[0105] In this step, K in Formula 1 takes 8.15. Therefore, when predicting the GDP of Xi'an in the first quarter of 2025, the cumulative issuance of broad money and the cumulative total energy production corresponding to the four quarters of 2024, as well as the energy production volume in the first quarter of 2025, are input into Formula 1, that is:

[0106]

[0107] Among them, M21, M22, M23, and M24 are the cumulative issuance of broad money corresponding to the first quarter, second quarter, third quarter, and fourth quarter of Xi'an in 2024, respectively.

[0108] W21, W22, W23, and W24 are the cumulative total energy production corresponding to the first quarter, second quarter, third quarter, and fourth quarter of Xi'an in 2024, respectively.

[0109] w is the energy production volume corresponding to the first quarter of Xi'an in 2025.

[0110] The GDP prediction value corresponding to the first quarter of 2025 is specifically obtained through Formula 2.

[0111] After obtaining the GDP prediction value corresponding to the first quarter of 2025, the GDP prediction value can be displayed on the man-machine interaction interface, or the electronic device of the present application sends the GDP prediction value to the electronic device of the user bound to the electronic device. The electronic device is, for example, a mobile phone, so that the user can obtain the GDP prediction value.

[0112] Among them, the national GDP is predicted according to the GDP prediction method provided in this embodiment. The comparison between the predicted GDP values of previous years and the corresponding actual GDP values (officially announced GDP) is shown in Table 1:

[0113]

[0114]

[0115] Analyzing the data in the table, it can be seen that the largest error between the predicted GDP value and the actual GDP value is 5.44% in 2021, and the smallest error is 0.52% in 2018, with an average error of 2.16%.

[0116] Although there is an error between the predicted GDP value and the actual GDP value, when obtaining the predicted GDP value, only 3-5 groups of cumulative circulation volumes of broad money, cumulative total energy production, and energy production volume need to be obtained, and then the predicted GDP value can be obtained according to Formula 1. The data used in this process is easy to obtain, the amount of data required is small, it is easy to process, the processing process is simple, saving hardware processing resources and improving processing efficiency. Therefore, compared with the existing GDP prediction methods, the GDP prediction method provided in this embodiment can not only quickly obtain the predicted GDP value, but also the predicted GDP value has a certain accuracy, achieving a balance between accuracy and efficiency.

[0117] Figure 2 It is a flowchart of the training method of the GDP prediction model provided in an embodiment of the present application. As Figure 2 shown, the training method of the GDP prediction model of the above target area includes:

[0118] S201. Obtain multiple groups of sample historical data of the target area.

[0119] In this step, each group of sample historical data includes: historical cumulative circulation volume of broad money, historical cumulative total energy production, historical energy production volume, and historical GDP. Among them, the sample historical data are all real values.

[0120] Sample historical data can be obtained through the official websites corresponding to the above various data. Among them, the cumulative historical broad money supply and the cumulative total historical energy production are the total amounts corresponding to the time unit when obtaining the sample historical data, starting from a preset time point in history. The historical energy production is the energy production corresponding to the time unit when obtaining the sample historical data, and the historical GDP is the GDP corresponding to the time unit when obtaining the sample historical data. For example, when the time unit is years and the sample historical data is the data corresponding to 2024, the cumulative historical broad money supply is the cumulative broad money supply corresponding to the cumulative period from 1990 to 2024, the cumulative total historical energy production is the cumulative total energy production corresponding to the cumulative period from 1990 to 2024, the historical energy production is the energy production corresponding to 2024, and the historical GDP is the GDP corresponding to 2024.

[0121] It should be noted that in this application, the preset time point in history is illustrated by taking 1990 as an example. In fact, it can be any time point in history, as long as the preset time point in history corresponding to training the GDP prediction model is the same as the preset time point in history corresponding to using the GDP prediction model.

[0122] Among them, when training the GDP prediction model corresponding to the target area, it is necessary to select the sample historical data corresponding to the target area. In this way, the fit between the GDP prediction model and the target area can be improved, and the prediction accuracy can be enhanced.

[0123] Optionally, a specific implementation manner of S201 is as follows:

[0124] S2011. Obtain multiple groups of sample historical data of the target area divided by different time units.

[0125] Specifically, in order to improve the accuracy of the GDP prediction model for predicting GDP with different time units, when collecting sample historical data, the diversity and coverage rate of the sample historical data need to be considered. Therefore, sample historical data within different time units is obtained.

[0126] For example, for the prediction of the GDP of the first quarter of 2025 in Xi'an, although the corresponding time unit is a quarter, the time unit corresponding to the sample historical data can be years, months, quarters, etc.

[0127] The GDP prediction model obtained by training with these sample historical data can adapt to the prediction of GDP with different time units.

[0128] S202. Use the cumulative historical broad money issuance, cumulative total historical energy production, and historical energy production volume in the sample historical data as the inputs of the initial GDP prediction model, and the historical GDP as the output of the initial GDP prediction model, and obtain and store the GDP prediction model in the memory.

[0129] In this step, for different regions, the initial GDP prediction models are the same, which reflects the relationship between the cumulative historical broad money issuance, cumulative total historical energy production, energy production volume, and GDP.

[0130] During training, use the cumulative historical broad money issuance, cumulative total historical energy production, and historical energy production volume in each group of sample historical data as the inputs of the initial GDP prediction model, and the historical GDP as the output of the initial GDP prediction model to train the initial GDP prediction model.

[0131] After obtaining the GDP prediction model, store the GDP prediction model in the database of the memory.

[0132] Optionally, a specific implementation of S202 is as follows:

[0133] S2021. Use the cumulative historical broad money issuance, cumulative total historical energy production, and historical energy production volume in the sample historical data as the inputs of the initial GDP prediction model, and the historical GDP as the output of the initial GDP prediction model to obtain the industrial structure coefficient in the GDP prediction model.

[0134] Among them, the industrial structure coefficient represents the industrial structure of the target region.

[0135] Specifically, in the initial GDP prediction model, the industrial structure of the target region is reflected by setting the industrial structure coefficient at the input end of the model, thus also reflecting the influence degree of the cumulative historical broad money issuance, cumulative total historical energy production, and energy production volume in the target region on GDP. Among them, the industrial structure coefficient is related to the region, and different regions have different industrial structure coefficients.

[0136] Therefore, by using the cumulative historical broad money issuance, cumulative total historical energy production, and historical energy production volume in each group of sample historical data as the inputs of the initial GDP prediction model, and the GDP in each group of sample historical data as the output of the initial GDP prediction model, the industrial structure coefficient, that is, K in Formula 1, is obtained.

[0137] Optionally, a specific implementation of S2021 is as follows:

[0138] S211. Take the cumulative historical broad money issuance, cumulative total historical energy production, and historical energy production volume in each group of sample historical data as the inputs of the initial GDP prediction model, and take the GDP in each group of sample historical data as the output of the initial GDP prediction model to obtain the industrial structure coefficients corresponding to each group of sample historical data.

[0139] S212. Obtain the industrial structure coefficients in the GDP prediction model according to the industrial structure coefficients corresponding to each group of sample historical data.

[0140] Specifically, when each group of sample historical data is used to train the initial GDP prediction model, the corresponding industrial structure coefficients are obtained. Therefore, different sample historical data will result in different industrial structure coefficients. Therefore, when determining the industrial structure coefficients of the GDP prediction model, the mean value of the industrial structure coefficients corresponding to different sample historical data can be taken.

[0141] Or, as shown in S2121 and S2122:

[0142] S2121. Obtain the distribution map of the industrial structure coefficients corresponding to each group of sample historical data;

[0143] S2122. Determine the industrial structure coefficients according to the distribution density of the industrial structure coefficients corresponding to each group of sample historical data in the distribution map.

[0144] Specifically, according to the industrial structure coefficients corresponding to different sample historical data, obtain the corresponding distribution map, select the industrial structure coefficients corresponding to the area with relatively dense distribution of industrial structure coefficients in the distribution map, determine the value range of the industrial structure coefficients, so that when in use, select the value of K from the value range. For example, for Xi'an, the value range of K is 8 - 8.5. Among them, the value of K in Formula 2 is 8.15, which is selected from 8 - 8.5.

[0145] In this embodiment, by obtaining multiple groups of sample historical data, and then taking the cumulative historical broad money issuance, cumulative total historical energy production, and historical energy production volume in each group of sample historical data as the inputs of the initial GDP prediction model, and taking the historical GDP in each group of sample historical data as the output of the initial GDP prediction model, a GDP prediction model is obtained. Since the GDP prediction model is trained with a large number of real sample historical data, the accuracy and applicability of the GDP prediction model are ensured.

[0146] Figure 3 This is the structural schematic diagram of the GDP prediction device based on energy production provided by an embodiment of the present application. As Figure 3As shown in the figure, the GDP prediction device based on energy production includes: a first acquisition module 310, a second acquisition module 320, and a prediction module 330. Optionally, the GDP prediction device based on energy production further includes: a training module 340.

[0147] Among them, the first acquisition module 310 is configured to acquire a GDP prediction instruction input by a user, and the GDP prediction instruction includes: a target region, a target time period, and a historical time period for the user to predict GDP. When divided according to the time unit corresponding to the target time period, the historical time period includes at least one time unit;

[0148] The second acquisition module 320 is configured to, according to the GDP prediction instruction, acquire a GDP prediction model corresponding to the target region pre-stored in a memory, and acquire from the memory the cumulative amount of broad money issued and the cumulative total energy production corresponding to each time unit within the historical time period of the target region, and the energy production amount of the target region within the target time period. The GDP prediction model is a linear model obtained by training with multiple sets of sample historical data corresponding to the target region, and each set of the sample historical data includes: historical cumulative amount of broad money issued, historical cumulative total energy production, historical energy production amount, and historical GDP;

[0149] The prediction module 320 is configured to, according to the GDP prediction model corresponding to the target region, the cumulative amount of broad money issued and the cumulative total energy production corresponding to each time unit within the historical time period, and the energy production amount of the target region within the target time period, acquire and output to the user the GDP prediction value of the target region within the target time period.

[0150] Optionally, before the second acquisition module 320 determines the GDP prediction model corresponding to the target region according to the GDP prediction instruction, the training module 340 is configured to:

[0151] Acquire multiple sets of sample historical data of the target region;

[0152] Use the historical cumulative amount of broad money issued, the historical cumulative total energy production, and the historical energy production amount in the sample historical data as the input of an initial GDP prediction model, and the historical GDP as the output of the initial GDP prediction model to obtain the GDP prediction model.

[0153] Optionally, when the training module 340 uses the historical cumulative amount of broad money issued, the historical cumulative total energy production, and the historical energy production amount in the sample historical data as the input of an initial GDP prediction model, and the historical GDP as the output of the initial GDP prediction model to obtain the GDP prediction model, it is specifically configured to:

[0154] Using the cumulative historical broad money circulation volume, the cumulative total historical energy production volume, and the historical energy production volume in the sample historical data as the inputs of the initial GDP prediction model, and the historical GDP as the output of the initial GDP prediction model, the industrial structure coefficient in the GDP prediction model is obtained, and the industrial structure coefficient represents the industrial structure of the target area;

[0155] Based on the industrial structure coefficient and the initial GDP prediction model, the GDP prediction model is obtained.

[0156] Optionally, when the training module 340 uses the cumulative historical broad money circulation volume, the cumulative total historical energy production volume, and the historical energy production volume in the sample historical data as the inputs of the initial GDP prediction model, and the historical GDP as the output of the initial GDP prediction model to obtain the industrial structure coefficient in the GDP prediction model, it specifically is used for:

[0157] Using the cumulative historical broad money circulation volume, the cumulative total historical energy production volume, and the historical energy production volume in each group of the sample historical data as the inputs of the initial GDP prediction model, and the GDP in each group of the sample historical data as the output of the initial GDP prediction model, the industrial structure coefficient corresponding to each group of the sample historical data is obtained;

[0158] Based on the industrial structure coefficient corresponding to each group of the sample historical data, the industrial structure coefficient in the GDP prediction model is obtained.

[0159] Optionally, when the training module 340 obtains the industrial structure coefficient in the GDP prediction model based on the industrial structure coefficient corresponding to each group of the sample historical data, it specifically is used for:

[0160] Obtaining the distribution map of the industrial structure coefficient corresponding to each group of the sample historical data;

[0161] Based on the distribution density of the industrial structure coefficient corresponding to each group of the sample historical data in the distribution map, the industrial structure coefficient is determined.

[0162] Optionally, when the training module 340 obtains multiple groups of sample historical data of the target area, it specifically is used for:

[0163] Obtaining multiple groups of sample historical data of the target area divided by different time units.

[0164] Optionally, when the training module 340 obtains multiple groups of sample historical data of the target area, it specifically is used for:

[0165] Updating the multiple groups of sample historical data of the target area according to the target time period.

[0166] Optionally, the GDP prediction model is:

[0167]

[0168] where K represents the industrial structure coefficient, and the value range of K corresponds to the target area;

[0169] n is the number of time units included in the historical time period;

[0170] M2 i is the cumulative circulation of broad money corresponding to the i-th time unit in the historical time period;

[0171] W i is the cumulative total energy production corresponding to the i-th time unit in the historical time period;

[0172] w is the energy production in the target time period.

[0173] For the GDP prediction device based on energy production provided by the embodiments of the present application, the specific implementation process can be referred to the above method embodiments, and its implementation principle and technical effects are similar, which will not be elaborated here in this embodiment.

[0174] Figure 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Among them, the electronic device can be a computer, a server, a handheld terminal, etc. For example, a mobile phone is installed with a corresponding application software for predicting GDP according to the GDP prediction model. As Figure 4 shown, the electronic device includes: a processor 410 and a memory 420.

[0175] Among them, the memory 420 stores computer execution instructions.

[0176] The processor 410 executes the computer execution instructions stored in the memory 420, so that the processor 410 executes the method described in any of the above embodiments.

[0177] For the electronic device provided by the embodiments of the present application, the specific implementation process can be referred to the above method embodiments, and its implementation principle and technical effects are similar, which will not be elaborated here in this embodiment.

[0178] In the above Figure 4In the illustrated embodiments, it should be understood that the processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the invention may be directly embodied as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0179] The memory may include high-speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.

[0180] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the buses in the drawings of this application are not limited to only one bus or one type of bus.

[0181] The embodiments of the present application also provide a computer-readable storage medium, in which computer-executable instructions are stored. When the processor executes the computer-executable instructions, the method shown in the above method embodiments is implemented.

[0182] For the above computer-readable storage medium, the above-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc. The readable storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0183] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0184] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the foregoing storage medium includes: various media such as ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0185] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A GDP prediction method based on energy production, characterized in that, Including: Obtain a GDP prediction instruction input by a user, where the GDP prediction instruction includes: a target region, a target time period, and a historical time period for the user to predict GDP. When divided according to the time unit corresponding to the target time period, the historical time period includes at least one time unit; According to the GDP prediction instruction, obtain the GDP prediction model corresponding to the target region pre-stored in a memory, and obtain from the memory the cumulative amount of broad money issued and the cumulative total energy production corresponding to each time unit within the historical time period for the target region, as well as the energy production amount of the target region during the target time period. The GDP prediction model is a linear model obtained by training with multiple sets of sample historical data corresponding to the target region. Each set of the sample historical data includes: historical cumulative amount of broad money issued, historical cumulative total energy production, historical energy production amount, and historical GDP. According to the GDP prediction model corresponding to the target region, the cumulative amount of broad money issued and the cumulative total energy production corresponding to each time unit within the historical time period, and the energy production amount of the target region during the target time period, obtain and output to the user the GDP prediction value of the target region during the target time period.

2. The method according to claim 1, wherein Before determining the GDP prediction model corresponding to the target region according to the GDP prediction instruction, it further includes: Obtain multiple sets of sample historical data of the target region; Use the historical cumulative amount of broad money issued, historical cumulative total energy production, and historical energy production amount in the sample historical data as the input of an initial GDP prediction model, and use the historical GDP as the output of the initial GDP prediction model, and obtain and store the GDP prediction model in the memory.

3. The method according to claim 2, wherein The step of using the historical cumulative amount of broad money issued, historical cumulative total energy production, and historical energy production amount in the sample historical data as the input of an initial GDP prediction model, and using the historical GDP as the output of the initial GDP prediction model to obtain the GDP prediction model includes: Use the historical cumulative amount of broad money issued, historical cumulative total energy production, and historical energy production amount in the sample historical data as the input of an initial GDP prediction model, and use the historical GDP as the output of the initial GDP prediction model to obtain the industrial structure coefficient in the GDP prediction model, where the industrial structure coefficient represents the industrial structure of the target region; Obtain the GDP prediction model according to the industrial structure coefficient and the initial GDP prediction model.

4. The method according to claim 3, characterized in that The step of using the historical cumulative amount of broad money issued, historical cumulative total energy production, and historical energy production amount in the sample historical data as the input of an initial GDP prediction model, and using the historical GDP as the output of the initial GDP prediction model to obtain the industrial structure coefficient in the GDP prediction model includes: Taking the cumulative historical broad money issuance, cumulative total historical energy production, and historical energy production volume in each group of the sample historical data as the inputs of the initial GDP prediction model, and taking the GDP in each group of the sample historical data as the output of the initial GDP prediction model, to obtain the industrial structure coefficients corresponding to each group of the sample historical data; Based on the industrial structure coefficients corresponding to each group of the sample historical data, to obtain the industrial structure coefficients in the GDP prediction model.

5. The method according to claim 4, characterized in that The obtaining the industrial structure coefficients in the GDP prediction model based on the industrial structure coefficients corresponding to each group of the sample historical data includes: obtaining the distribution map of the industrial structure coefficients corresponding to each group of the sample historical data; Based on the distribution density of the industrial structure coefficients corresponding to each group of the sample historical data in the distribution map, to determine the industrial structure coefficients.

6. The method according to claim 2, wherein The obtaining the multiple groups of sample historical data of the target area includes: Obtaining multiple groups of sample historical data of the target area divided by different time units.

7. The method according to claim 3, characterized in that, The GDP prediction model is: Wherein, K represents the industrial structure coefficient, and the value range of K corresponds to the target area; n is the number of time units included in the historical time period; The M2 i is the cumulative circulation of broad money corresponding to the i-th time unit within the historical time period; The said W i is the cumulative total energy production corresponding to the i-th time unit within the said historical time period; w is the energy production volume in the target time period.

8. A GDP prediction device based on energy production, characterized in that, It includes: The first obtaining module is used to obtain the GDP prediction instruction input by the user. The GDP prediction instruction includes: the target area, target time period, and historical time period for which the user predicts GDP. Wherein, when divided by the time unit corresponding to the target time period, the historical time period includes at least one time unit; The second obtaining module is used to, according to the GDP prediction instruction, obtain the GDP prediction model corresponding to the target area pre-stored in the memory, and obtain from the memory the cumulative historical broad money issuance and cumulative total energy production corresponding to each time unit in the historical time period of the target area, and the energy production volume of the target area in the target time period. Wherein, the GDP prediction model is a linear model trained by multiple groups of sample historical data corresponding to the target area, and each group of the sample historical data includes: cumulative historical broad money issuance, cumulative total historical energy production, historical energy production volume, and historical GDP; The prediction module is used to, according to the GDP prediction model corresponding to the target area, the cumulative historical broad money issuance and cumulative total energy production corresponding to each time unit in the historical time period, and the energy production volume of the target area in the target time period, obtain and output to the user the GDP prediction value of the target area in the target time period.

9. An electronic device, characterized in that, It includes: A processor and a memory; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory, so that the processor executes the method according to any one of claims 1-7.

10. A readable storage medium, characterized in that, It includes: A program or instruction, when the program or instruction runs on a computer, the method according to any one of claims 1-7 above is executed.

Images