CN117540851A - Data prediction method and device, equipment and storage medium - Google Patents

Data prediction method and device, equipment and storage medium Download PDF

Info

Publication number
CN117540851A
CN117540851A CN202311469487.3A CN202311469487A CN117540851A CN 117540851 A CN117540851 A CN 117540851A CN 202311469487 A CN202311469487 A CN 202311469487A CN 117540851 A CN117540851 A CN 117540851A
Authority
CN
China
Prior art keywords
data
current
gdp
evaluation
preset
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311469487.3A
Other languages
Chinese (zh)
Inventor
张迎峰
罗慧瑜
马鑫磊
王菁
方辉敏
黎永昇
林令
刘斐
杨双
蔡家思
陈慧婷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Unicom Guangdong Industrial Internet Co Ltd
Original Assignee
China Unicom Guangdong Industrial Internet Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Unicom Guangdong Industrial Internet Co Ltd filed Critical China Unicom Guangdong Industrial Internet Co Ltd
Priority to CN202311469487.3A priority Critical patent/CN117540851A/en
Publication of CN117540851A publication Critical patent/CN117540851A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The embodiment of the application discloses a data prediction method, a device, equipment and a storage medium, comprising the following steps: obtaining current national production total value GDP data of an area to be predicted in a current time period, current environment data used for representing policy environment and current evaluation data used for representing environment data of a user, inputting the current GDP data into a preset prediction model to obtain initial prediction GDP data, determining influence factors corresponding to the current environment data and the current evaluation data, and determining target prediction GDP data according to the initial prediction GDP data and the influence factors. The initial predicted GDP data can be further adjusted based on the environmental data and the user evaluation data as influencing factors, thereby providing more accurate target predicted GDP data. The influence of the policy environment and the user evaluation on the GDP data is reflected more comprehensively, the accuracy of predicting the future GDP is improved, and a more reliable GDP predicting result is provided.

Description

Data prediction method and device, equipment and storage medium
Technical Field
Embodiments of the present application relate to data analysis technology, and relate to, but are not limited to, a data prediction method, a device, an apparatus, and a storage medium.
Background
In the process of national development, the specification of policies often requires corresponding data to support, and the GDP prediction can help a decision maker to know the trend of the GDP data, so as to formulate the corresponding policies. By accurately predicting the growth or decline trend of GDP, corresponding measures can be taken to promote GDP growth, stabilize employment, adjust expenditure, etc.
At present, in GDP prediction in China, a prediction model is a Nowcasting model, and the Nowcasting model predicts GDP in the current, very near future and the recent past, and although the on-demand Nowcasting model has been applied in GDP prediction in China for many years, the on-demand Nowcasting model is not comprehensive enough to factors which influence GDP when GDP prediction is carried out, and can cause the GDP prediction to be inaccurate.
Therefore, how to improve the accuracy of prediction of future GDPs, provide more reliable GDP prediction results, and better understand and evaluate GDP growth is a highly desirable problem.
Disclosure of Invention
In view of this, the data prediction method, device, equipment and storage medium provided in the embodiments of the present application can improve the accuracy of predicting the future GDP, provide a more reliable GDP prediction result, and better understand and evaluate the GDP growth. The data prediction method, the device, the equipment and the storage medium provided by the embodiment of the application are realized in the following way:
The data prediction method provided by the embodiment of the application comprises the following steps:
acquiring current national production total value GDP data of a region to be predicted in a current time period, current environment data used for representing a policy environment and current evaluation data used for representing the environment data of a user;
inputting the current GDP data into a preset prediction model to obtain initial predicted GDP data;
determining an influence factor corresponding to the current environmental data and the current evaluation data;
and determining target predicted GDP data according to the initial predicted GDP data and the influence factors.
In some embodiments, the impact factors include impact factors corresponding to current environmental impact factors and current rating impact factors, and the determining impact factors corresponding to the current environmental data and the current rating data includes:
determining a current environmental impact factor according to the current environmental data;
and determining a current evaluation influence factor according to the current evaluation data.
In some embodiments, the determining the current environmental impact factor from the current environmental data includes:
inputting the current environmental data into a preset environmental level judgment model to obtain a current environmental level, wherein the current environmental level is one of a plurality of preset environmental levels, and the preset environmental level judgment model is obtained by training according to historical environmental data and corresponding historical environmental levels;
And determining the current environment influence factor according to the preset mapping relation between the environment level and the environment influence factor and the current environment level.
In some embodiments, the determining a current rating impact factor from the current rating data comprises:
capturing a plurality of keywords used for representing the emotional state of the user from the current evaluation data;
determining a current evaluation level corresponding to the current evaluation data according to a first duty ratio of target sub-evaluation data comprising the keywords in the current evaluation data and a second duty ratio of target keywords corresponding to each emotional state in the plurality of keywords;
and determining the current evaluation influence factor according to the preset mapping relation between the evaluation level and the evaluation influence factor and the current evaluation level.
In some embodiments, the determining target predicted GDP data from the initial predicted GDP data and the impact factor comprises:
correcting the initial predicted GDP data according to a preset formula, the current environmental impact factor and the current evaluation impact factor to obtain the target predicted GDP data, wherein the preset formula is that
Wherein alpha is the current environmental impact factor, beta is the current evaluation impact factor,for initial prediction of GDP data, ρ and σ are equal to 0 or 1.
In some embodiments, before correcting the initial predicted GDP data according to a preset formula, the current environmental impact factor, and the current evaluation impact factor to obtain the target predicted GDP data, the method further includes:
determining the value of rho according to the magnitude relation between the current environmental impact factor and a first level threshold, wherein when the current environmental impact factor is greater than or equal to the first level threshold, the value of rho is 1, otherwise, the value of rho is 0, and the first level threshold is an environmental level positioned at a middle position among the plurality of preset environmental levels;
and determining the value of sigma according to the magnitude relation between the current evaluation influence factor and a second level threshold, wherein when the current evaluation influence factor is larger than or equal to the second level threshold, the value of sigma is 1, otherwise, the value of sigma is 0, and the second level threshold is an evaluation level positioned at the middle position among the plurality of preset evaluation levels.
In some embodiments, the inputting the current GDP data into a preset prediction model to obtain initial predicted GDP data includes:
Acquiring the preset prediction model parameters, wherein the preset prediction model parameters comprise implicit factor parameters and model parameters, the implicit factor parameters are used for representing trend of GDP data, and the model parameters are used for representing the relation between the current GDP data and the implicit factor parameters;
and obtaining initial predicted GDP data according to the preset prediction model and the current GDP data after the parameters are obtained.
In some embodiments, the obtaining initial predicted GDP data according to the preset prediction model and the current GDP data after obtaining the parameters, where the preset prediction model includes a measurement model and a transfer model includes:
acquiring estimated GDP data in a preset interval corresponding to the current GDP data according to the current GDP data and the measurement model;
and determining initial predicted GDP data according to the estimated GDP data and the transfer model in the preset interval.
The data prediction device provided in the embodiment of the application includes:
the system comprises an acquisition module, a prediction module and a prediction module, wherein the acquisition module is used for acquiring current national production total value GDP data of an area to be predicted in a current time period, current environment data used for representing a policy environment and current evaluation data used for representing a user on the environment data;
The input module is used for inputting the current GDP data into a preset prediction model to obtain initial prediction GDP data;
the determining module is used for determining an influence factor corresponding to the current environment data and the current evaluation data;
and the determining module is also used for determining target predicted GDP data according to the initial predicted GDP data and the influence factors.
The computer device provided by the embodiment of the application comprises a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the processor realizes the method described by the embodiment of the application when executing the program.
The computer readable storage medium provided in the embodiments of the present application stores a computer program thereon, which when executed by a processor implements the method provided in the embodiments of the present application.
According to the data prediction method, the device, the computer equipment and the computer readable storage medium, the current national production total value GDP data of the area to be predicted in the current time period, the current environment data used for representing the policy environment and the current evaluation data used for representing the environment data of the user are taken, the current GDP data are input into a preset prediction model to obtain initial prediction GDP data, influence factors corresponding to the current environment data and the current evaluation data are determined, and target prediction GDP data are determined according to the initial prediction GDP data and the influence factors. The initial predicted GDP data can be further adjusted based on the environmental data and the user evaluation data as influencing factors, thereby providing more accurate target predicted GDP data. The method can reflect the influence of the policy environment and the user evaluation on the GDP data more comprehensively, improve the accuracy of predicting the GDP in the future, provide a more reliable GDP predicting result and solve the technical problems in the background technology.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and, together with the description, serve to explain the technical aspects of the application.
Fig. 1 is an application scenario diagram of a data prediction method disclosed in an embodiment of the present application;
FIG. 2 is a flow chart of a data prediction method disclosed in an embodiment of the present application;
FIG. 3 is a general flow chart of a data prediction method disclosed in an embodiment of the present application;
FIG. 4 is a schematic diagram of a data prediction apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purposes, technical solutions and advantages of the embodiments of the present application to be more apparent, the specific technical solutions of the present application will be described in further detail below with reference to the accompanying drawings in the embodiments of the present application. The following examples are illustrative of the present application, but are not intended to limit the scope of the present application.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict.
It should be noted that the term "first/second/third" in reference to the embodiments of the present application is used to distinguish similar or different objects, and does not represent a specific ordering of the objects, it being understood that the "first/second/third" may be interchanged with a specific order or sequence, as permitted, to enable the embodiments of the present application described herein to be implemented in an order other than that illustrated or described herein.
In view of this, the embodiment of the application provides a data prediction method, which is applied to intelligent electronic equipment. Fig. 1 is an application scenario diagram of a data prediction method according to an embodiment. As shown in fig. 1, a user may carry, wear, or use an electronic device 10, which electronic device 10 may include, but is not limited to, a cell phone, a wearable device (e.g., a smart watch, a smart bracelet, smart glasses, etc.), a tablet computer, a notebook computer, a vehicle-mounted terminal, a PC (Personal Computer, a personal computer), etc. The functions performed by the method may be performed by a processor in an electronic device, which may of course be stored in a computer storage medium, as will be seen, comprising at least a processor and a storage medium.
Fig. 2 is a schematic implementation flow chart of a data prediction method provided in an embodiment of the present application. As shown in fig. 2, the method may include the following steps 201 to 204:
step 201, obtaining the total value GDP data of the current national production of the area to be predicted in the current time period, the current environment data used for representing the policy environment and the current evaluation data used for representing the environment data of the user.
In the embodiment of the application, the actual national production total value GDP data of the area to be predicted in the current time period is obtained, and optionally, the actual national production total value GDP data can be obtained from related statistical institutions, economic reports or other reliable sources. At the same time, current environmental data, such as policy documents, market indexes, etc., characterizing the policy environment are collected. There is also a need to obtain current ratings data characterizing users' environmental data, which may be obtained by way of questionnaires, social media analysis, and the like.
Step 202, inputting the current GDP data into a preset prediction model to obtain initial predicted GDP data.
In the embodiment of the application, a suitable prediction model is selected to predict the future GDP. Such as using time series analysis methods, ARIMA models, or exponential smoothing methods, to capture trends and seasonal variations in GDP data. Further, machine learning-based methods, such as regression analysis, support Vector Machines (SVMs), random forests, etc., may also be employed to predict with current GDP data and other relevant factors.
As an example, inputting current GDP data into a preset predictive model to obtain initial predicted GDP data, including:
correcting parameters of a preset prediction model, wherein the parameters of the preset prediction model comprise implicit factor parameters and model parameters, the implicit factor parameters are used for representing trend of GDP data, and the model parameters are used for representing the relation between the current GDP data and the implicit factor parameters. Optionally, historical GDP data is collected, and data preprocessing and cleaning are performed to ensure accuracy and integrity of the data.
And analyzing and mining the historical GDP data by using a statistical method or a machine learning algorithm, and extracting hidden factor parameters. Alternatively, principal component analysis (Principal Component Analysis, PCA) or other dimension reduction techniques may be used to extract the primary influencing factors from the historical data.
And correcting the extracted hidden factor parameters according to the GDP data of the current region to be predicted. The values of the implicit factor parameters can be adjusted by adopting methods such as linear regression, partial least square method and the like according to the relation between the current data and the historical data.
Further, according to the preset prediction model after the parameters are corrected and the current GDP data, initial prediction GDP data are obtained. Optionally, training a preset prediction model according to the historical data, and determining an initial value of a model parameter. A model suitable for the predictive task is selected, such as an ARIMA model, a neural network model, etc.
And correcting the model parameters according to the GDP data of the current region to be predicted. The values of the model parameters may be adjusted by minimizing prediction errors or maximizing posterior probabilities using optimization algorithms (e.g., gradient descent) or bayesian inference, among other methods. And inputting the corrected hidden factor parameters and model parameters into a corrected preset prediction model.
And inputting the GDP data of the current region to be predicted into the corrected model to obtain initial predicted GDP data. The specific calculation method may vary according to the selected prediction model, and the present application is not particularly limited.
As an example, initial predicted GDP data is obtained according to a preset prediction model and current GDP data after parameter correction, where the preset prediction model includes a measurement model and a transfer model, and includes: and acquiring estimated GDP data in a preset interval corresponding to the current GDP data according to the current GDP data and the measurement model. Alternatively, GDP data for the current time period and GDP data for a certain history time period are acquired as inputs. Such data may be obtained from published data sources such as statistical institutions, research reports, industry associations, and the like. Further, a measurement model is designed according to the historical data and the related characteristics, and the current GDP data is mapped to estimated GDP data in a preset interval. The measurement model can be modeled and trained based on linear regression, ARIMA time series models, neural networks, and the like. According to the chosen method, the appropriate features need to be extracted and model parameters estimated and optimized.
And predicting the current GDP data by using the measurement model to obtain estimated GDP data in a preset interval range. The confidence interval or prediction interval of the model may be used to represent the estimated range, which may take into account uncertainty factors.
Further, initial predicted GDP data is determined based on the estimated GDP data and the transition model within the predetermined interval. Optionally, a transition model is designed based on the estimated GDP data within the preset interval, and the initial predicted GDP data is determined by analyzing the change condition of the estimated GDP data. The transfer model can be modeled and trained by adopting a time sequence model, a statistical regression model and the like. Depending on the method chosen, appropriate features and variables need to be selected and model parameters estimated and optimized.
And predicting the estimated GDP data in a preset interval by using the transfer model to obtain initial predicted GDP data. The initial prediction horizon may be represented by using the prediction results of the model or confidence intervals thereof.
In step 203, an impact factor corresponding to the current environmental data and the current evaluation data is determined.
In the embodiment of the application, the relation between the current environmental data and the evaluation data and the GDP prediction result is determined according to the current environmental data and the evaluation data, and the influence factors are calculated. The weights of the influencing factors may be determined by correlation analysis, regression coefficient estimation or knowledge judgment of domain experts. For example, reform files in policy environment data may have a large impact on the GDP, while user's assessment data may reflect the impact of market confidence on the GDP.
As one example, the impact factors include an impact factor corresponding to the current environmental impact factor and the current evaluation impact factor, determining the impact factor corresponding to the current environmental data and the current evaluation data, comprising: and determining the current environment influence factor according to the current environment data. Alternatively, current environmental data, such as related documents, GDP indicators, market reports, etc., may be obtained from reliable sources such as related departments, research institutions, financial markets, etc.
According to the collected current environmental data, an index or variable related to GDP prediction is selected as an environmental index. For example, monetary supply, financial policies, industry structures, etc. may reflect indicators of environmental changes. And (3) carrying out normalization processing on the selected environment index, and converting the environment index into a unified numerical range so as to carry out subsequent weight calculation. According to the importance and the relativity of the environmental indexes, the weights of the environmental indexes are calculated by using a statistical analysis method (such as principal component analysis and regression coefficient estimation) or knowledge of domain experts, so as to obtain the current environmental impact factors.
Further, a current evaluation influence factor is determined according to the current evaluation data. Optionally, the evaluation opinion of the current user on the environmental data is collected through a user questionnaire, social media analysis, public opinion monitoring and other modes. And selecting an evaluation index related to GDP prediction according to the collected current evaluation data. For example, market confidence index, consumer satisfaction survey results, public opinion analysis, etc. may reflect user ratings for the environment.
And carrying out normalization processing on the selected evaluation index, and converting the selected evaluation index into a uniform numerical range. According to the importance and the relativity of the evaluation indexes, the weight of each evaluation index is calculated by using a statistical analysis method or the knowledge of domain experts, and the current evaluation influence factor is obtained.
As one example, determining the current environmental impact factor from the current environmental data includes:
the method comprises the steps of inputting current environment data into a preset environment level judgment model to obtain a current environment level, wherein the current environment level is one of a plurality of preset environment levels, and the preset environment level judgment model is obtained by training according to historical environment data and corresponding historical environment levels. Optionally, historical environmental data and corresponding historical environmental levels are collected. The historical environmental data may include various types of policy indicators, GDP indicators, environmental indicators, and the like. Further, based on the collected data, an appropriate machine learning algorithm (e.g., decision tree, support vector machine, neural network, etc.) is selected for training and modeling.
Dividing the data set into a training set and a testing set, training and verifying the model, and adjusting model parameters to improve prediction accuracy.
And evaluating the performance of the model, and evaluating the performance of the model on a test set by using proper evaluation indexes (such as accuracy, recall rate, F1 value and the like), so as to ensure the robustness and accuracy of the model.
Further, according to the preset mapping relation between the environment level and the environment influence factor and the current environment level, the current environment influence factor is determined. Optionally, a range or rule of values of the environmental impact factors corresponding to different environmental levels is determined based on domain knowledge or expert experience. May be a linear mapping, a non-linear mapping, or other form of mapping function. And carrying out statistical analysis or modeling according to the historical data and the determined environmental level, and finding out the relevance between the environmental level and the environmental impact factor. An appropriate mapping function or rule is determined to convert the current environmental level to a specific value of the current environmental impact factor.
As one example, determining the current rating impact factor from the current rating data includes: a plurality of keywords characterizing the emotional state of the user are captured from the current ratings data. Alternatively, the text is split into multiple words or phrases using text processing techniques, such as chinese word segmentation tools, to process and segment the current rating data.
Keywords associated with the emotional state of the user are selected based on domain knowledge or expert experience. These keywords may include words that represent positive emotions, negative emotions, neutral emotions, or a particular level of evaluation (e.g., good, bad, general, etc.).
Further, a current rating level corresponding to the current rating data is determined based on a first ratio of target sub-rating data including keywords in the current rating data and a second ratio of target keywords corresponding to respective emotional states in the plurality of keywords. Optionally, statistical analysis is performed on the target sub-evaluation data, and the occurrence frequency or the duty ratio of the target sub-evaluation data in the current evaluation data is calculated. A calculation formula such as (target sub-evaluation data amount)/(current evaluation data total amount) may be used.
And carrying out statistical calculation on the duty ratio of the target keywords corresponding to each emotion state or evaluation level in the plurality of keywords. A calculation formula such as (target keyword number)/(total number of keywords) may be used.
And comprehensively considering and determining the evaluation level corresponding to the current evaluation data according to the duty ratio of the target sub-evaluation data and the duty ratio of the target keywords. The determination and calculation may be performed by setting a threshold value or using a weighted average or the like.
Further, according to the preset mapping relation between the evaluation level and the evaluation influence factor and the current evaluation level, the current evaluation influence factor is determined. And setting a mapping relation table or function of the preset evaluation level and the evaluation influence factor. For example, the rating level corresponding to positive emotion may be mapped to a high impact factor, and the rating level corresponding to negative emotion may be mapped to a low impact factor.
And searching corresponding evaluation influence factors in a mapping relation table or a function according to the current evaluation level.
As one example, determining target predicted GDP data from the initial predicted GDP data and the impact factor, includes: correcting the initial predicted GDP data according to a preset formula, a current environmental impact factor and a current evaluation impact factor to obtain target predicted GDP data, wherein the preset formula is as follows:
wherein alpha is the current environmental impact factor, beta is the current evaluation impact factor,for initial prediction of GDP data, ρ and σ are equal to 0 or 1. Optionally, according to a preset prediction model, inputting the GDP data of the total national production value in the current time period into the prediction model to obtain initial predicted GDP data +.>And taking the current environmental data as input, and delivering the current environmental data to a preset environmental level judgment model. The environment level judgment model is trained according to the historical environment data and the corresponding historical environment levels to obtain a plurality of preset environment levels. And determining the current environment level corresponding to the current environment data. And determining the current environmental impact factor alpha according to the preset mapping relation between the environmental level and the environmental impact factor. A plurality of keywords characterizing the emotional state of the user are captured from the current ratings data. A first duty ratio of the target sub-rating data in the current rating data and a second duty ratio of the target keywords corresponding to the respective emotional states in the plurality of keywords are calculated. And determining a current evaluation influence factor beta according to the preset mapping relation between the evaluation level and the evaluation influence factor and the current evaluation level.
And correcting and calculating the initial predicted GDP data according to a preset formula by using the determined current environmental impact factor alpha and the determined current evaluation impact factor beta to obtain target predicted GDP data.
Specifically, the correction calculation formula is:
target prediction
As an example, before correcting the initial predicted GDP data according to the preset formula, the current environmental impact factor and the current evaluation impact factor to obtain the target predicted GDP data, the method further includes: and determining the value of rho according to the magnitude relation between the current environmental impact factor and the first level threshold, wherein when the current environmental impact factor is greater than or equal to the first level threshold, the value of rho is 1, otherwise, the value of rho is 0, and the first level threshold is an environmental level in the middle position among a plurality of preset environmental levels. Optionally, training is performed according to the historical data and the corresponding historical environmental level, and a preset environmental level judgment model is constructed. In this model, a plurality of preset environmental levels, and a threshold value corresponding to each level, need to be determined. The threshold setting may be based on statistical analysis or expert experience.
And inputting the current environmental data into a preset environmental level judgment model to obtain the current environmental level. According to the mapping relation between the current environment level and the preset environment level and the environment influence factor, the current environment influence factor can be determined. The mapping relation needs to be set when training the model, and analysis depending on actual data is required.
Further, determining the value of sigma according to the magnitude relation between the current evaluation influence factor and the second level threshold, wherein when the current evaluation influence factor is larger than or equal to the second level threshold, the value of sigma is 1, otherwise, the value of sigma is 0, and the second level threshold is an evaluation level positioned at the middle position among a plurality of preset evaluation levels. Optionally, a plurality of keywords characterizing the emotional state of the user are captured from the current rating data. May be implemented using natural language processing techniques such as word segmentation, keyword extraction, and the like.
And determining the current evaluation level corresponding to the current evaluation data according to the first duty ratio of the target sub-evaluation data in the current evaluation data and the second duty ratio of the target keywords corresponding to each emotion state in the plurality of keywords. Defining a plurality of preset evaluation levels and target sub-evaluation data corresponding to each level. Then, it is necessary to determine to which emotional state each target keyword corresponds to, and the ratio of the target sub-rating data in the current rating data, using statistical analysis or machine learning, or the like. And finally, determining the current evaluation influence factor according to each duty ratio and the mapping relation between the preset evaluation level and the evaluation influence factor.
Specifically, embodiments of the present application use a dynamic factor model that includes the measurement equation (Measurement Equation): the observable and implicit variables and transfer equations are connected (Transition Equation): the dynamic process of implicit factors is described, in particular, the measurement equation:
let y t ＝[y 1,t ，y 2,t ，…，y n,t ] T Represents n normalized observable variables, where any y i,t Is 0 and the variance is 1. Assuming that the number of implicit factors is r, y t The following relation is satisfied with the implicit factor:
y t ＝Cf t +∈ t , ∈ t ～i.i.d.N(0,R)
wherein f t Is an implicit factor vector with dimension r x 1; c is a factor load matrix with dimension of n x r, which connects an implicit factor and an observable variable; e-shaped article t ＝[∈ 1,t ，∈ 2,t ，…，∈ n,t ] T Is an error vector that cannot be interpreted by an implicit factor, which obeys the covariance matrix as an R normal distribution.
Transfer equation:
further assume that each implicit factor obeys an autoregressive process as follows:
f t ＝Af t-1 +μ t , μ t ～i.i.d.N(0,Q)
wherein A is an autoregressive coefficient matrix of dimension r x r; mu (mu) t The error vector obeys a normal distribution with a mean of 0 and a variance of Q.
The above formula defines a standard dynamic factor model.
Further, assume that the error term vector e t Also obeys the autoregressive process and canIs decomposed into sections independent of each other And xi i,t ：
ξ i,t ～i.i.d.N(0,κ)
Wherein xi i,t Obeying the variance to be a normal distribution of k, which is an extremely small constant;obeying a first order AR procedure, alpha i Is its autoregressive coefficient. e, e i,t Is the error term, subject to variance +.>Is a normal distribution of (c).
By expanding the factor vector, the model can be written in the form of a state space model as follows:
wherein the method comprises the steps ofThe expanded implicit factor vector is obtained; />Is an error vector; />Is a factor load matrix; />An autocorrelation coefficient matrix which is a factor;covariance matrix of error vector of transfer equation; />Is the covariance matrix of the error vector of the measurement equation, which is a diagonal matrix, and the diagonal elements are all constants k.
Assume error term vector e t Is also subject to the autoregressive process and can be decomposed into sections that are uncorrelated with each otherAnd xi i,t ：
ξ i,t ～i.i.d.N(0,κ)
Wherein xi i,t Obeying the variance as a normal distribution of κ, which is a very small constant;obeying a first order AR procedure, alpha i Is its autoregressive coefficient. e, e i,t Is the error term, subject to variance +.>Is a normal distribution of (c).
By expanding the factor vector, the model can be written in the form of a state space model as follows:
wherein the method comprises the steps ofThe expanded implicit factor vector is obtained; />Is an error vector; />Is a factor load matrix; />An autocorrelation coefficient matrix which is a factor; Covariance matrix of error vector of transfer equation; />Is the covariance matrix of the error vector of the measurement equation, which is a diagonal matrix, and the diagonal elements are all constants k.
In the embodiment of the application, variables to be estimated in the dynamic factor model include each implicit factor and model parameters, and the flow is as follows:
and performing principal component analysis on the input data by using a PCA method to obtain a feature vector corresponding to the maximum feature value of the covariance matrix. Projecting the data onto the feature vector direction to obtain a principal component sequenceInitial value as implicit factor:
subtracting the obtained principal component sequence from the original data to obtain residual data;
continuously repeating the process, and analyzing the main component by using the residual data to obtain initial values of other implicit factors;
autoregressive using implicit factor sequences to obtain transfer matrix A and residual μ t 。
Autoregressive using residual sequence to obtain autoregressive coefficient alpha 1 ,…,α n And residual e t 。
According to the residual error mu t And e t Sequence calculation covariance matrix
Setting diagonal arraysWherein the diagonal element is a constant k.
Obtaining initial values of all model parameters; e-step: based on the model parameters and the observable data set obtained by the previous iteration, obtaining an implicit factor sequence and a likelihood value of the current model by using Kalman filtering, and filling the missing value.
M-step: based on the obtained implicit factor sequences and the observable data set, new model parameters are obtained using a maximum likelihood method.
E-step and M-step are repeated until the stop condition is satisfied.
Through the steps, the PCA+EM algorithm can robustly estimate the hidden factors and model parameters of the dynamic factor model. In each iteration, the estimates of the implicit factors are updated by E-step, and then the estimates of the model parameters are updated by M-step. And repeating the iteration until the stopping condition is met, so that a robust estimation result is obtained.
Step 204, determining target predicted GDP data according to the initial predicted GDP data and the impact factors.
In the embodiment of the application, the initial predicted GDP data and the corresponding influencing factors thereof are comprehensively considered, and the final target predicted GDP data is calculated. Alternatively, a weighted average method may be adopted, where the initial predicted GDP is multiplied by a corresponding influence factor and added to obtain a weighted prediction result. The initial predicted outcome may also be modified using the impact factors to obtain a more accurate target predicted GDP.
According to the embodiment of the application, after the GDP speed-increasing predicted value of each quarter is obtained through calculation of the dynamic factor model, the predicted value is optimized according to the influence factors constructed by the policy and public opinion data. The calculation formula is as follows:
Wherein y' t Represents the optimized GDP speed-up predicted value,and the GDP speed-increasing predicted value obtained by fitting the dynamic factor model is represented. Alpha and beta represent factor coefficients of policy and public opinion data, respectively, and ρ and σ are equal to 0 or 1, respectively, representing positive or negative effects of policy and public opinion factors on GDP.
According to the method and the device, factors such as policy environment and user evaluation are considered, input information of a prediction model is increased, and therefore future GDP data can be predicted more accurately. The traditional prediction model usually only considers single factors such as historical trend, and the application considers multidimensional factors such as current policy environment and user evaluation, so that the method and the device are more suitable for actual situations. By determining the influence factors and deriving target predicted GDP data in combination with the prediction model, the change trend of the GDP data can be better explained. The method and the device can improve prediction accuracy, consider multidimensional factors and enhance prediction interpretation.
An exemplary application of the embodiments of the present application in a practical application scenario will be described below.
Fig. 3 is an overall flow chart of a data prediction method provided in an embodiment of the present application. As shown in fig. 3, the method includes the following steps 301 to 307:
step 301, obtaining the total value GDP data of the current national production of the area to be predicted in the current time period;
Step 302, obtaining current environment data for characterizing a policy environment;
step 303, obtaining current evaluation data for representing environmental data of a user;
step 304, obtaining initial forecast GDP data according to the total GDP data produced by the former national citizen;
step 305, generating an environmental impact factor according to current environmental data for characterizing the policy environment;
step 306, generating an evaluation influence factor according to current evaluation data for representing the environmental data of the user;
step 307, correcting the initial predicted GDP data according to the environmental impact factor and the evaluation impact factor to obtain target predicted GDP data.
It should be understood that, although the steps in the flowcharts described above are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described above may include a plurality of sub-steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of execution of the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternately with at least a part of the sub-steps or stages of other steps or other steps.
Based on the foregoing embodiments, the embodiments of the present application provide a data prediction apparatus, where the apparatus includes each module included, and each unit included in each module may be implemented by a processor; of course, the method can also be realized by a specific logic circuit; in an implementation, the processor may be a Central Processing Unit (CPU), a Microprocessor (MPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), or the like.
Fig. 4 is a schematic structural diagram of a data prediction apparatus provided in the embodiment of the present application, as shown in fig. 4, the apparatus 400 includes an obtaining module 401, an input module 402, and a determining module 403, where:
an obtaining module 401, configured to obtain current national production total value GDP data of an area to be predicted in a current time period, current environment data for characterizing a policy environment, and current evaluation data for characterizing environment data of a user;
an input module 402, configured to input current GDP data into a preset prediction model, to obtain initial predicted GDP data;
a determining module 403, configured to determine an impact factor corresponding to the current environmental data and the current evaluation data;
the determining module 403 is further configured to determine target predicted GDP data according to the initial predicted GDP data and the impact factor.
In some embodiments, the determining module 403 is further configured to determine a current environmental impact factor according to the current environmental data;
further, the determining module 403 is further configured to determine a current evaluation influence factor according to the current evaluation data.
In some embodiments, the input module 402 is further configured to input the current environmental data into a preset environmental level judgment model to obtain a current environmental level, where the current environmental level is one of a plurality of preset environmental levels, and the preset environmental level judgment model is obtained by training according to the historical environmental data and the corresponding historical environmental level;
the determining module 403 is further configured to determine a current environmental impact factor according to a preset mapping relationship between the environmental level and the environmental impact factor, and the current environmental level.
In some embodiments, the obtaining module 401 is further configured to capture, from the current evaluation data, a plurality of keywords for characterizing an emotional state of the user;
the determining module 403 is further configured to determine a current evaluation level corresponding to the current evaluation data according to a first duty ratio of target sub-evaluation data including keywords in the current evaluation data and a second duty ratio of target keywords corresponding to respective emotional states in the plurality of keywords;
Further, the determining module 403 is further configured to determine a current evaluation impact factor according to a preset mapping relationship between the evaluation level and the evaluation impact factor and the current evaluation level.
In some embodiments, the determining module 403 is further configured to correct the initial predicted GDP data according to a preset formula, a current environmental impact factor, and a current evaluation impact factor to obtain target predicted GDP data, where the preset formula is:
wherein alpha is the current environmental impact factor, beta is the current evaluation impact factor,for initial prediction of GDP data, ρ and σ are equal to 0 or 1.
In some embodiments, the determining module 403 is further configured to determine the value of ρ according to the magnitude relation between the current environmental impact factor and the first level threshold, where when the current environmental impact factor is greater than or equal to the first level threshold, the value of ρ is 1, otherwise, the value of ρ is 0, and the first level threshold is an environmental level located in a middle position among the plurality of preset environmental levels;
further, the determining module 403 is further configured to determine a value of σ according to a magnitude relation between the current evaluation influence factor and a second level threshold, where when the current evaluation influence factor is greater than or equal to the second level threshold, the value of σ is 1, and otherwise, the value of σ is 0, and the second level threshold is an evaluation level located in a middle position among the multiple preset evaluation levels.
In some embodiments, the determining module 403 is further configured to modify parameters of a preset prediction model, where the parameters of the preset prediction model include implicit factor parameters and model parameters, the implicit factor parameters are used to characterize trend of GDP data, and the model parameters are used to characterize a relationship between current GDP data and the implicit factor parameters;
further, the determining module 403 is further configured to obtain initial predicted GDP data according to the preset prediction model and the current GDP data after the parameters are corrected.
In some embodiments, the obtaining module 401 is further configured to obtain estimated GDP data in a preset interval corresponding to the current GDP data according to the current GDP data and the measurement model;
the determining module 403 is further configured to determine initial predicted GDP data according to the estimated GDP data and the transition model within the preset interval.
The description of the apparatus embodiments above is similar to that of the method embodiments above, with similar advantageous effects as the method embodiments. For technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.
It should be noted that, in the embodiment of the present application, the division of the modules by the data prediction apparatus shown in fig. 4 is schematic, which is merely a logic function division, and there may be another division manner in actual implementation. In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units. Or in a combination of software and hardware.
It should be noted that, in the embodiment of the present application, if the method is implemented in the form of a software functional module, and sold or used as a separate product, the method may also be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially or part contributing to the related art, and the computer software product may be stored in a storage medium, including several instructions for causing an electronic device to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read Only Memory (ROM), a magnetic disk, an optical disk, or other various media capable of storing program codes. Thus, embodiments of the present application are not limited to any specific combination of hardware and software.
The embodiment of the application provides a computer device, which may be a server, and an internal structure diagram thereof may be shown in fig. 5. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing data. The network interface of the computer device is used for communicating with an external terminal through a network connection. Which computer program, when being executed by a processor, carries out the above-mentioned method.
The present embodiment provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the method provided in the above embodiment.
The present application provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the steps of the method provided by the method embodiments described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 5 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a data prediction apparatus provided herein may be implemented in the form of a computer program that is executable on a computer device as shown in fig. 5. The memory of the computer device may store the various program modules that make up the apparatus. The computer program of each program module causes a processor to perform the steps in the methods of each embodiment of the present application described in the present specification.
It should be noted here that: the description of the storage medium and apparatus embodiments above is similar to that of the method embodiments described above, with similar benefits as the method embodiments. For technical details not disclosed in the storage medium, storage medium and device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" or "some embodiments" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" or "in some embodiments" in various places throughout this specification are not necessarily referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application. The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments. The foregoing description of various embodiments is intended to highlight differences between the various embodiments, which may be the same or similar to each other by reference, and is not repeated herein for the sake of brevity.
The term "and/or" is herein merely an association relation describing associated objects, meaning that there may be three relations, e.g. object a and/or object B, may represent: there are three cases where object a alone exists, object a and object B together, and object B alone exists.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments are merely illustrative, and the division of the modules is merely a logical function division, and other divisions may be implemented in practice, such as: multiple modules or components may be combined, or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or modules, whether electrically, mechanically, or otherwise.
The modules described above as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules; can be located in one place or distributed to a plurality of network units; some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in each embodiment of the present application may be integrated in one processing unit, or each module may be separately used as one unit, or two or more modules may be integrated in one unit; the integrated modules may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read Only Memory (ROM), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the integrated units described above may be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially or part contributing to the related art, and the computer software product may be stored in a storage medium, including several instructions for causing an electronic device to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a removable storage device, a ROM, a magnetic disk, or an optical disk.
The methods disclosed in the several method embodiments provided in the present application may be arbitrarily combined without collision to obtain a new method embodiment.
The features disclosed in the several product embodiments provided in the present application may be combined arbitrarily without conflict to obtain new product embodiments.
The features disclosed in the several method or apparatus embodiments provided in the present application may be arbitrarily combined without conflict to obtain new method embodiments or apparatus embodiments.
The foregoing is merely an embodiment of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (11)

1. A method of data prediction, the method comprising:
acquiring current national production total value GDP data of a region to be predicted in a current time period, current environment data used for representing a policy environment and current evaluation data used for representing the environment data of a user;
inputting the current GDP data into a preset prediction model to obtain initial predicted GDP data;
determining an influence factor corresponding to the current environmental data and the current evaluation data;
and determining target predicted GDP data according to the initial predicted GDP data and the influence factors.
2. The method of claim 1, wherein the impact factors include impact factors corresponding to current environmental impact factors and current rating impact factors, the determining impact factors corresponding to the current environmental data and the current rating data comprising:
Determining a current environmental impact factor according to the current environmental data;
and determining a current evaluation influence factor according to the current evaluation data.
3. The method of claim 2, wherein said determining a current environmental impact factor from said current environmental data comprises:
inputting the current environmental data into a preset environmental level judgment model to obtain a current environmental level, wherein the current environmental level is one of a plurality of preset environmental levels, and the preset environmental level judgment model is obtained by training according to historical environmental data and corresponding historical environmental levels;
and determining the current environment influence factor according to the preset mapping relation between the environment level and the environment influence factor and the current environment level.
4. The method of claim 2, wherein said determining a current rating impact factor from said current rating data comprises:
capturing a plurality of keywords used for representing the emotional state of the user from the current evaluation data;
determining a current evaluation level corresponding to the current evaluation data according to a first duty ratio of target sub-evaluation data comprising the keywords in the current evaluation data and a second duty ratio of target keywords corresponding to each emotional state in the plurality of keywords;
And determining the current evaluation influence factor according to the preset mapping relation between the evaluation level and the evaluation influence factor and the current evaluation level.
5. The method of any of claims 2-4, wherein the determining target predicted GDP data from the initial predicted GDP data and the impact factor comprises:
correcting the initial predicted GDP data according to a preset formula, the current environmental impact factor and the current evaluation impact factor to obtain the target predicted GDP data, wherein the preset formula is as follows:
wherein alpha is the current environmental impact factor, beta is the current evaluation impact factor,for initial prediction of GDP data, ρ and σ are equal to 0 or 1.
6. The method of claim 5, wherein the modifying the initial predicted GDP data according to the preset formula, the current environmental impact factor, and the current evaluation impact factor, before obtaining the target predicted GDP data, further comprises:
determining the value of rho according to the magnitude relation between the current environmental impact factor and a first level threshold, wherein when the current environmental impact factor is greater than or equal to the first level threshold, the value of rho is 1, otherwise, the value of rho is 0, and the first level threshold is an environmental level positioned at a middle position among the plurality of preset environmental levels;
And determining the value of sigma according to the magnitude relation between the current evaluation influence factor and a second level threshold, wherein when the current evaluation influence factor is larger than or equal to the second level threshold, the value of sigma is 1, otherwise, the value of sigma is 0, and the second level threshold is an evaluation level positioned at the middle position among the plurality of preset evaluation levels.
7. The method of claim 1, wherein the inputting the current GDP data into a pre-set prediction model to obtain initial predicted GDP data comprises:
correcting parameters of the preset prediction model, wherein the parameters of the preset prediction model comprise implicit factor parameters and model parameters, the implicit factor parameters are used for representing trend of GDP data, and the model parameters are used for representing relationship between the current GDP data and the implicit factor parameters;
and obtaining initial predicted GDP data according to the preset prediction model after the parameters are corrected and the current GDP data.
8. The method of claim 7, wherein the obtaining initial predicted GDP data from the modified parameter of the preset predictive model and the current GDP data, the preset predictive model including a measurement model and a transfer model, comprises:
Acquiring estimated GDP data in a preset interval corresponding to the current GDP data according to the current GDP data and the measurement model;
and determining initial predicted GDP data according to the estimated GDP data and the transfer model in the preset interval.
9. A data prediction apparatus, comprising:
the system comprises an acquisition module, a prediction module and a prediction module, wherein the acquisition module is used for acquiring current national production total value GDP data of an area to be predicted in a current time period, current environment data used for representing a policy environment and current evaluation data used for representing a user on the environment data;
the input module is used for inputting the current GDP data into a preset prediction model to obtain initial prediction GDP data;
the determining module is used for determining an influence factor corresponding to the current environment data and the current evaluation data;
and the determining module is also used for determining target predicted GDP data according to the initial predicted GDP data and the influence factors.
10. A computer device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that the processor implements the steps of the method of any of claims 1 to 8 when the program is executed.
11. A computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the method according to any one of claims 1 to 8.
CN202311469487.3A 2023-11-06 2023-11-06 Data prediction method and device, equipment and storage medium Pending CN117540851A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311469487.3A CN117540851A (en) 2023-11-06 2023-11-06 Data prediction method and device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311469487.3A CN117540851A (en) 2023-11-06 2023-11-06 Data prediction method and device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117540851A true CN117540851A (en) 2024-02-09

Family

ID=89783304

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311469487.3A Pending CN117540851A (en) 2023-11-06 2023-11-06 Data prediction method and device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117540851A (en)

Similar Documents

Publication Publication Date Title
Ribeiro et al. Transfer learning with seasonal and trend adjustment for cross-building energy forecasting
Meiri et al. Using simulated annealing to optimize the feature selection problem in marketing applications
Shang Forecasting intraday S&P 500 index returns: A functional time series approach
CN107506868A (en) A kind of method and device of temporary electricity load prediction
US11995667B2 (en) Systems and methods for business analytics model scoring and selection
US20230105547A1 (en) Machine learning model fairness and explainability
Talagala et al. Meta‐learning how to forecast time series
CN116091118A (en) Electricity price prediction method, device, equipment, medium and product
Widodo et al. Model selection using dimensionality reduction of time series characteristics
CN111309994A (en) User matching method and device, electronic equipment and readable storage medium
CN117235608B (en) Risk detection method, risk detection device, electronic equipment and storage medium
Stødle et al. Data‐driven predictive modeling in risk assessment: Challenges and directions for proper uncertainty representation
CN114118570A (en) Service data prediction method and device, electronic equipment and storage medium
US11847389B2 (en) Device and method for optimizing an input parameter in a processing of a semiconductor
CN117540336A (en) Time sequence prediction method and device and electronic equipment
CN117217812A (en) User behavior prediction method and device, computer equipment and storage medium
CN117540851A (en) Data prediction method and device, equipment and storage medium
WO2022222230A1 (en) Indicator prediction method and apparatus based on machine learning, and device and storage medium
CN111177657B (en) Demand determining method, system, electronic device and storage medium
EP3989129A1 (en) A computer-implemented method for deriving a data processing and inference pipeline
CA3160715A1 (en) Systems and methods for business analytics model scoring and selection
Mares et al. An Architecture to Improve Energy-Related Time-Series Model Validity Based on the Novel rMAPE Performance Metric
US20230419195A1 (en) System and Method for Hierarchical Factor-based Forecasting
Tang et al. Considerations in Using XGBoost Models with SHAP Credit Assignment to Calculate Student Growth Percentiles
Widodo et al. Feature enhancement for model selection in time series forecasting

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination