Commodity price online analysis method, device, equipment, medium and program

Abstract

The invention relates to the technical field of data analysis, and provides a commodity price online analysis method, device, equipment, medium and program, and the method comprises the steps: obtaining the price index data of a target commodity, and classifying the price index data into classification index data according to a preset commodity type; performing data screening on the classification index data to determine an influence factor value influencing the price of a target commodity of the preset commodity type in a preset time period; dividing the classification index data into a training set and a test set; establishing a prediction model, and performing model training on the prediction model by using the influence factor value and the training set to obtain a time sequence analysis model; obtaining an actual update price of a target commodity of the preset commodity type in a preset time period, and performing test analysis on the time sequence analysis model by using the test set and the actual update price to obtain an online analysis model; and using the online analysis model to analyze and predict the commodity price.

Description

Technical Field

[0001] The present disclosure relates to the field of data analysis technology, and in particular to a commodity price online analysis method, device, equipment, medium and program. Background Art

[0003] The traditional coal purchasing model mainly relies on manual experience, historical transaction data review and simple market research, and lacks a scientific and systematic price forecasting mechanism. This purchasing decision-making method is not only inefficient, but also difficult to accurately capture market dynamics, resulting in large fluctuations in purchasing costs, affecting the economic benefits and competitiveness of coal-fired power plants.

[0004] Due to the lack of effective price forecasting tools, coal-fired power plants can only respond passively when faced with frequent changes in coal market prices, and it is difficult for them to make reasonable procurement plans and inventory adjustments in advance. This not only increases the operational risks of the enterprises, but may also cause cost waste due to inappropriate procurement timing, and may even affect the stability and continuity of power production. Summary of the invention

[0005] In view of the above problems, embodiments of the present invention provide a method, device, equipment, medium and program for online analysis of commodity prices.

[0006] In a first aspect, an embodiment of the present invention provides a commodity price online analysis method, comprising:

[0007] Acquire price index data of a target commodity, and classify the price index data into classification index data according to preset commodity types;

[0008] Determine the impact factor value that affects the price of the target commodity of the preset commodity type in a preset time period by performing data screening on the classification index data;

[0009] Dividing the classification index data into a training set and a test set;

[0010] Establishing a prediction model, and performing model training on the prediction model using the impact factor value and the training set to obtain a time series analysis model;

[0011] Acquire the actual updated price of the target commodity of the preset commodity type in a preset time period, and test and analyze the time series analysis model using the test set and the actual updated price to obtain an online analysis model;

[0012] The online analysis model is used to analyze the price of the target commodity of the preset commodity type in a preset future time period.

[0013] According to an embodiment of the present invention, the classifying the price index data into classification index data according to preset commodity types includes:

[0014] Converting the price index data into a preset format to obtain unified format data;

[0015] Identify commodity attribute information of the unified format data to obtain commodity attribute data;

[0016] Marking the commodity attribute data;

[0017] Different types of data tags are assigned to different databases to obtain classification index data.

[0018] According to an embodiment of the present invention, the step of determining the impact factor value that affects the price of the target commodity of the preset commodity type in a preset time period by performing data screening on the classification index data includes:

[0019] Calculating the correlation coefficient between the classification index data and the preset influencing factors of the preset time period;

[0020] Determining whether the correlation coefficient is higher than a preset coefficient threshold;

[0021] If the correlation coefficient is lower than a preset coefficient threshold, deleting the influencing factor corresponding to the correlation coefficient;

[0022] If the correlation coefficient is higher than a preset coefficient threshold, the correlation coefficient is used as a compliance coefficient;

[0023] A multiple regression model is established with the classification index data as the dependent variable and the compliance coefficient as the independent variable;

[0024] Calculating the model fit goodness of each independent variable by changing the independent variables in the multiple regression model one by one;

[0025] Determining whether the model goodness of fit is higher than a preset goodness of fit threshold;

[0026] If the model goodness of fit is lower than the preset goodness of fit threshold, deleting the influencing factor corresponding to the model goodness of fit;

[0027] If the model goodness of fit is higher than the preset goodness of fit threshold, the conformity coefficient corresponding to the goodness of fit is used as the influencing factor value.

[0028] According to an embodiment of the present invention, the method of performing model training on the prediction model using the impact factor value and the training set to obtain a time series analysis model includes:

[0029] The prediction model is converted into a training time series model using the impact factor value and the training set as exogenous variables and the classification index data as endogenous variables;

[0030] Performing model training on the training set using the training time series model to obtain an analysis output value;

[0031] Calculating a loss value based on the analysis output value and the classification index data;

[0032] Determine whether the loss value is higher than a preset loss value threshold;

[0033] If the loss value is higher than the preset loss value threshold, calculating the model parameters according to the loss value;

[0034] Using the model parameters to update the parameters of the time series model, and using the training time series model after parameter update to perform model training on the training set;

[0035] If the loss value is lower than the preset loss value threshold, the model training is confirmed to be completed and a timing analysis model is obtained.

[0036] According to an embodiment of the present invention, the step of testing and analyzing the timing analysis model using the test set and the actual update price to obtain an online analysis model includes:

[0037] Performing model testing on the test set using the time series model to obtain a model analysis value;

[0038] Calculate an error value based on the model analysis value and the actual update price;

[0039] Determining whether the error value is higher than a preset error value threshold;

[0040] If the error value is higher than the preset error value threshold, the preset coefficient threshold and the preset loss value threshold are adjusted, and the model training is performed again;

[0041] If the error value is lower than the preset error value threshold, it is confirmed that the model test is completed and an online analysis model is obtained.

[0042] According to an embodiment of the present invention, the step of analyzing the price of the target commodity of the preset commodity type in a preset future time period by using the online analysis model includes:

[0043] Converting the actual updated price of the target commodity of the preset commodity type in a preset time period into a historical price;

[0044] Merging the historical price and the price index data of the target commodity into updated price index data;

[0045] Classifying the updated price index data into updated classification index data according to preset commodity types;

[0046] Performing data screening on the updated classification index data to determine an updated impact factor value that affects the price of a target commodity of the preset commodity type in a preset future time period;

[0047] The online analysis model is used to perform price analysis on the updated impact factor value and the historical price to obtain the price of the target commodity of the preset commodity type in a future time period.

[0048] In a second aspect, an embodiment of the present invention provides a commodity price online analysis device, comprising:

[0049] A data classification module, used to obtain price index data of a target commodity and classify the price index data into classification index data according to preset commodity types;

[0050] An influence determination module, configured to determine an influence factor value that affects the price of a target commodity of the preset commodity type in a preset time period by performing data screening on the classification index data;

[0051] A data partitioning module, used for partitioning the classification index data into a training set and a test set;

[0052] A model training module is used to establish a prediction model, and to perform model training on the prediction model using the impact factor value and the training set to obtain a time series analysis model;

[0053] A model testing module, used to obtain the actual updated price of the target commodity of the preset commodity type in a preset time period, and to test and analyze the time series analysis model using the test set and the actual updated price to obtain an online analysis model;

[0054] The price analysis module is used to analyze the price of the target commodity of the preset commodity type in a preset future time period by using the online analysis model.

[0055] In a third aspect, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the online commodity price analysis method described in the above aspect.

[0056] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the online commodity price analysis method described in the above aspects.

[0057] In a fifth aspect, an embodiment of the present invention provides a computer program product, including a computer program, which implements the steps of the online commodity price analysis method when executed by a processor.

[0058] Compared with the prior art, the above technical solution of the present invention has the following beneficial effects:

[0059] By classifying the price index data into classification index data according to preset commodity types, it can adapt to the diversified business needs of enterprises and assist enterprises in making scientific decisions in procurement, sales, market expansion, etc.; by screening out weakly correlated influencing factors, a more accurate and effective prediction model can be established to provide a reliable basis for enterprises in the decision-making process of procurement, sales, inventory management, etc., helping enterprises to better respond to market changes, reduce operational risks, and improve economic benefits and market competitiveness; by dividing the classification index data into training sets and test sets, the reliability of the model is ensured, so that the model can be used more confidently in actual decision-making; through data-driven and model iterative optimization, the model's ability to adapt to market changes is effectively improved. , ensuring the accuracy and reliability of model predictions; helping enterprises to keenly grasp price dynamics in a complex and changing market environment, rationally plan business strategies, reduce operational risks, and achieve sustainable development; through testing and optimization mechanisms, effectively evaluate model performance to ensure the reliability and accuracy of model predictions; through multi-link data integration and analysis, fully explore historical prices and real-time price information, accurately screen influencing factors, and use advanced model prediction capabilities to provide enterprises with reliable commodity price trend forecasts, helping enterprises to make scientific decisions in procurement, sales, inventory management, etc., effectively reduce market risks, improve economic benefits and market competitiveness, and ensure the stable operation and sustainable development of enterprises in a complex and changing market environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0061] Figure 1 A flowchart of a commodity price online analysis method according to a first embodiment of the present invention is shown;

[0062] Figure 2 An example diagram showing the visualization results of the coal price index prediction value of the commodity price online analysis method according to the first embodiment of the present invention;

[0063] Figure 3 The functional module diagram of the commodity price online analysis device according to the second embodiment of the present invention is shown;

[0064] Figure 4 A schematic diagram of the composition structure of an electronic device for implementing the commodity price online analysis method according to the fourth embodiment of the present invention is shown. DETAILED DESCRIPTION

[0065] The present disclosure is further described below in conjunction with the embodiments shown in the accompanying drawings.

[0066] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0067] The present invention realizes overall damage identification of the bridge structure in a shorter period, can complete all-round identification, and has a higher identification efficiency.

[0068] Embodiment 1

[0069] like Figure 1 As shown, an online commodity price analysis method provided by an embodiment of the present disclosure includes the following steps:

[0070] S1. Obtain price index data of a target commodity, and classify the price index data into classification index data according to preset commodity types.

[0071] In the embodiment of the present invention, the price index data of the target commodity is the basic data of the commodity price online analysis method. The principle is that it can comprehensively reflect the overall level and change trend of the market price of the target commodity. Its functions include serving as a classification basis, determining the influencing factor value, training and testing models, and predicting future prices, etc., which is of great significance to improving the scientificity, accuracy and competitiveness of procurement decisions; the preset commodity type plays a key role in the commodity price online analysis method. The principle is that it provides pertinence and guidance for the entire analysis process. Its functions cover multiple aspects such as data classification, influencing factor screening, model construction and optimization, and price prediction, which helps enterprises to conduct accurate price analysis and decision-making according to the characteristics of different commodities.

[0072] In the embodiment of the present invention, the classifying the price index data into classification index data according to the preset commodity type includes:

[0073] Converting the price index data into a preset format to obtain unified format data;

[0074] Identify commodity attribute information of the unified format data to obtain commodity attribute data;

[0075] Marking the commodity attribute data;

[0076] Different types of data tags are assigned to different databases to obtain classification index data.

[0077] In the embodiment of the present invention, the principle of the preset format is to establish a unified standard for price index data, so that data from different sources and in different forms can be consistent and comparable in subsequent processing; in the actual market environment, the price index data of the target commodity may come from multiple channels, such as industry associations, data monitoring agencies, internal enterprise statistics, etc., and the formats of these data may vary greatly, including data storage structure, field naming, encoding method, etc. By converting the price index data into the preset format, these differences can be eliminated, laying the foundation for accurate data processing and analysis.

[0078] In the embodiment of the present invention, the principle of commodity attribute information is that it reflects various intrinsic characteristics of the target commodity, which have a direct or indirect relationship with the formation and fluctuation of commodity prices. Different commodity attributes will lead to differences in the supply and demand relationship, cost structure, value assessment, etc. in the market, thus affecting the price. For example, the calorific value, origin and other attributes of coal. Coal with different calorific values ​​has different use values. The origin affects factors such as transportation costs, which in turn affect the price; the brand, configuration and other attributes of electronic products will also affect their market competitiveness and price positioning. These attribute information is the basis for understanding and analyzing commodity price changes.

[0079] In detail, first, the price index data is converted into a preset format to obtain unified format data; the commodity attribute information of the unified format data is identified to obtain commodity attribute data; the commodity attribute data is data-marked; different types of data tags are assigned to different databases to obtain classified index data; a basis is provided for accurate data analysis, which is helpful to deeply explore the law of commodity price changes; data management and retrieval are optimized to facilitate and quickly obtain required data.

[0080] In the embodiment of the present invention, this step can adapt to the diverse business needs of enterprises, assist enterprises in making scientific decisions in procurement, sales, market development, etc., and enhance the competitiveness of enterprises.

[0081] S2. Determine the impact factor value that affects the price of the target commodity of the preset commodity type in a preset time period by screening the classification index data.

[0082] In the embodiments of the present invention, data screening is based on an in-depth analysis of the correlation between various factors in the classification index data and the target commodity prices of the preset commodity types; in the actual market, the factors affecting commodity prices are numerous and complex, and these factors are intertwined and work together to form and fluctuate prices; for example, for coal commodities, coal origin, calorific value, market supply and demand, seasonal factors, policies and regulations, etc. may all have an impact on prices; its principle is to use scientific calculation and evaluation methods to accurately identify the key factors that have a significant impact on commodity prices from many related factors. Its functions include optimizing the selection of influencing factors, improving model accuracy, enhancing the reliability of price prediction, and assisting enterprises in making reasonable decisions, providing strong support for enterprises to grasp price dynamics in a complex market environment.

[0083] In the embodiment of the present invention, the step of determining the impact factor value that affects the price of the target commodity of the preset commodity type in the preset time period by screening the classification index data includes:

[0084] Calculating the correlation coefficient between the classification index data and the preset influencing factors of the preset time period;

[0085] Determining whether the correlation coefficient is higher than a preset coefficient threshold;

[0086] If the correlation coefficient is lower than a preset coefficient threshold, deleting the influencing factor corresponding to the correlation coefficient;

[0087] If the correlation coefficient is higher than a preset coefficient threshold, the correlation coefficient is used as a compliance coefficient;

[0088] A multiple regression model is established with the classification index data as the dependent variable and the compliance coefficient as the independent variable;

[0089] Calculating the model fit goodness of each independent variable by changing the independent variables in the multiple regression model one by one;

[0090] Determining whether the model goodness of fit is higher than a preset goodness of fit threshold;

[0091] If the model goodness of fit is lower than the preset goodness of fit threshold, deleting the influencing factor corresponding to the model goodness of fit;

[0092] If the model goodness of fit is higher than the preset goodness of fit threshold, the conformity coefficient corresponding to the goodness of fit is used as the influencing factor value.

[0093] In the embodiment of the present invention, the correlation coefficient is calculated by a specific mathematical formula to measure the closeness of the linear relationship between the classification index data and the preset influencing factors in the preset time period. It is based on statistical principles and conducts quantitative analysis on the coordinated changes of the two sets of data; its principle is to quantify the degree and direction of the linear association between the two variables. Its functions include preliminary screening of influencing factors, measuring the strength of the relationship between variables, assisting model construction decisions, and improving the accuracy of price forecasts, providing a key basis for subsequent precise analysis and decision-making.

[0094] In the embodiment of the present invention, the preset threshold is based on the definition of the significance of the data relationship. After calculating the correlation coefficient between the classification index data and the preset influencing factors, a clear boundary is needed to determine whether the relationship represented by these coefficients is significant enough, so as to determine whether the influencing factor should be included in the subsequent analysis; its principle is to provide a clear judgment standard for the screening of correlation coefficients, and its functions include controlling the screening accuracy, balancing the complexity and explanatory power of the model, adapting to different market environments, and ensuring the reliability of the analysis results, providing important guarantees for enterprises to accurately grasp the factors affecting commodity prices.

[0095] In detail, in an embodiment of the present invention, the correlation coefficient between the classification index data and the preset influencing factors of the preset time period is calculated; it is determined whether the correlation coefficient is higher than the preset coefficient threshold; if the correlation coefficient is lower than the preset coefficient threshold, the influencing factor corresponding to the correlation coefficient is deleted; if the correlation coefficient is higher than the preset coefficient threshold, the correlation coefficient is used as the compliance coefficient; a multivariate regression model is established with the classification index data as the dependent variable and the compliance coefficient as the independent variable; the model goodness of fit of each independent variable is calculated by changing the independent variables in the multivariate regression model one by one; it is determined whether the model goodness of fit is higher than the preset goodness of fit threshold; if the model goodness of fit is lower than the preset goodness of fit threshold, the influencing factor corresponding to the model goodness of fit is deleted; this step can screen out the key factors that have a significant impact on the target commodity price of the preset commodity type, and exclude the interference of irrelevant or weakly correlated factors.

[0096] In the embodiment of the present invention, by screening out weakly correlated influencing factors, a more accurate and effective prediction model is established, which provides a reliable basis for enterprises in decision-making processes such as procurement, sales, and inventory management, helping enterprises to better respond to market changes, reduce operational risks, and improve economic benefits and market competitiveness.

[0097] S3. Divide the classification index data into a training set and a test set.

[0098] In the embodiment of the present invention, the training set is mainly used for model construction and training, which contains rich historical data information. By allowing the model to learn the complex relationship between the target commodity price and related influencing factors in the training set, the parameters and structure of the model are continuously adjusted, so that the model can gradually fit the rules in the data; for example, in the coal price prediction model, the training set covers a variety of data such as coal price index, coal production, transportation costs, market supply and demand in different periods in the past. By learning these data, the model attempts to dig out the internal logic of price formation and fluctuation; and the test set is a data part independent of the training set, and its role is to objectively evaluate the performance of the model after the model training is completed. The data of the test set is not used in the model training process, so that it can truly reflect the model's prediction ability for unknown data.

[0099] In the embodiment of the present invention, by dividing the classification index data into a training set and a test set, the reliability of the model is ensured, so that the model can be used with more confidence in actual decision-making.

[0100] S4. Establish a prediction model, and use the impact factor value and the training set to perform model training on the prediction model to obtain a time series analysis model.

[0101] In the embodiment of the present invention, the core principle of model training is data-driven learning; based on the influencing factor values ​​and training set data, the prediction model begins to learn the complex relationship between the target commodity price and various influencing factors; by utilizing the influencing factor values ​​and training set data, the prediction model continuously adjusts its own parameters to learn the law of price changes. Its functions include building an accurate price prediction model, mining the intrinsic relationship of data, adapting to market dynamics, assisting corporate decision-making, and enhancing corporate market competitiveness, providing effective price analysis and decision-making support for enterprises in a complex market environment.

[0102] In the embodiment of the present invention, the prediction model is converted into a training time series model by using the impact factor value and the training set as exogenous variables and the classification index data as endogenous variables;

[0103] Performing model training on the training set using the training time series model to obtain an analysis output value;

[0104] Calculating a loss value based on the analysis output value and the classification index data;

[0105] Determine whether the loss value is higher than a preset loss value threshold;

[0106] If the loss value is higher than the preset loss value threshold, calculating the model parameters according to the loss value;

[0107] Using the model parameters to update the parameters of the time series model, and using the training time series model after parameter update to perform model training on the training set;

[0108] If the loss value is lower than the preset loss value threshold, the model training is confirmed to be completed and a timing analysis model is obtained.

[0109] In the embodiment of the present invention, the principle of exogenous variables and endogenous variables is based on the understanding of the relationship between variables in the economic system. In the online analysis model of commodity prices, endogenous variables refer to variables determined by the interaction of other variables within the model, and their values ​​are calculated through various economic relationships within the model system; for example, the price of a commodity itself is an endogenous variable, which is jointly affected by many factors such as market supply and demand, production costs, consumer preferences, etc. These factors interact in the model through specific economic logic and ultimately determine the value of the commodity price. Exogenous variables are variables given outside the model, and their changes are considered to be determined by factors outside the model. They are not affected by the variables inside the model, but will have an effect on endogenous variables.

[0110] In the embodiment of the present invention, the core principle of parameter updating is based on the error feedback between the model prediction results and the actual data; when the prediction model is trained using the training set, the model predicts the commodity price (endogenous variable) based on the input influencing factor value (exogenous variable), and then compares the predicted price with the actual price in the training set to calculate the error value. This error value reflects the current prediction accuracy of the model, and it becomes a key signal to drive parameter updates. For example, in the coal price prediction model, if the predicted price is higher than the actual price, it means that the model overestimates the price under the current parameter settings, and vice versa. The model adjusts the model parameters according to the direction and size of the error through a specific optimization algorithm, such as the gradient descent algorithm, so that the model can reduce the error in subsequent predictions and gradually approach the real price change law.

[0111] In detail, the prediction model is converted into a training time series model using the influencing factor value and the training set as exogenous variables and the classification index data as endogenous variables; the training time series model is used to perform model training on the training set to obtain an analysis output value; a loss value is calculated based on the analysis output value and the classification index data; it is determined whether the loss value is higher than a preset loss value threshold; if the loss value is higher than the preset loss value threshold, the model parameters are calculated based on the loss value; the time series model is updated using the model parameters, and the training set is trained using the training time series model after the parameter update; if the loss value is lower than the preset loss value threshold, it is confirmed that the model training is completed to obtain a time series analysis model.

[0112] In the embodiments of the present invention, through data-driven and model iterative optimization, the model's adaptability to market changes is effectively improved, ensuring the accuracy and reliability of model predictions, providing a solid and powerful scientific basis for enterprises in purchasing, sales, inventory management and other decision-making, and helping enterprises to keenly grasp price dynamics in a complex and changing market environment, reasonably plan business strategies, reduce operational risks, improve economic benefits and market competitiveness, and achieve sustainable development.

[0113] S5. Obtain the actual updated price of the target commodity of the preset commodity type in a preset time period, and use the test set and the actual updated price to test and analyze the time series analysis model to obtain an online analysis model.

[0114] In the embodiment of the present invention, the principle of the actual updated price is that it is a true reflection of the real-time market transaction situation and a dynamic record of the actual transaction price of the commodity in the market. In the commodity trading process, each new transaction price is formed by the combined effect of multiple factors such as the market supply and demand relationship, cost changes, policy impact, consumer preferences, etc. These real-time price data are collected and aggregated through various channels to form an actual updated price sequence; its principle is based on real-time market information feedback and data authenticity verification, and its functions include evaluating model accuracy, optimizing model parameters, ensuring prediction reliability, guiding enterprise real-time decision-making, and enhancing enterprise market resilience, providing key support for enterprises to achieve accurate decision-making and efficient operation in a dynamic market environment.

[0115] In the embodiment of the present invention, the test set and the actual update price are used to test and analyze the timing analysis model to obtain an online analysis model, including:

[0116] Performing model testing on the test set using the time series model to obtain a model analysis value;

[0117] Calculate an error value based on the model analysis value and the actual update price;

[0118] Determining whether the error value is higher than a preset error value threshold;

[0119] If the error value is higher than the preset error value threshold, the preset coefficient threshold and the preset loss value threshold are adjusted, and the model training is performed again;

[0120] If the error value is lower than the preset error value threshold, it is confirmed that the model test is completed and an online analysis model is obtained.

[0121] In the embodiment of the present invention, the core principle of model testing is comparative verification, that is, using the test set to verify the trained model. The test set is a data set independent of the training set, which contains commodity price-related data and influencing factor data similar to the training set, but does not participate in the model training process. The influencing factor data in the test set is input into the model, and the model generates a model analysis value based on the price change rules and influencing factor relationships learned during the training process, that is, the prediction result of the commodity price in the test set.

[0122] In detail, the time series model is used to perform model testing on the test set to obtain a model analysis value; an error value is calculated based on the model analysis value and the actual update price; it is determined whether the error value is higher than a preset error value threshold; if the error value is higher than the preset error value threshold, data adjustments are made to the preset coefficient threshold and the preset loss value threshold, and the model is trained again; if the error value is lower than the preset error value threshold, the model test is confirmed to be completed, and an online analysis model is obtained.

[0123] In the embodiments of the present invention, through the testing and optimization mechanism, the model performance is effectively evaluated, the reliability and accuracy of the model prediction are ensured, and an accurate price prediction basis is provided for enterprises in purchasing, sales, inventory management and other decision-making aspects, which helps enterprises to reasonably plan business strategies in a complex and changing market environment, reduce operational risks, improve economic benefits and market competitiveness, and achieve sustainable development.

[0124] S6. Analyze the price of the target commodity of the preset commodity type in a preset future time period by using the online analysis model.

[0125] In the embodiment of the present invention, the principle of presetting the future time period is based on the understanding of the market operation law, that is, it is believed that the market has a certain degree of trend continuity. Through the analysis of historical data and the construction of models, it is assumed that various factors affecting commodity prices will continue to affect price changes in a similar logic and pattern in the future.

[0126] In the embodiment of the present invention, the step of analyzing the price of the target commodity of the preset commodity type in a preset future time period by using the online analysis model includes:

[0127] Converting the actual updated price of the target commodity of the preset commodity type in a preset time period into a historical price;

[0128] Merging the historical price and the price index data of the target commodity into updated price index data;

[0129] Classifying the updated price index data into updated classification index data according to preset commodity types;

[0130] Performing data screening on the updated classification index data to determine an updated impact factor value that affects the price of a target commodity of the preset commodity type in a preset future time period;

[0131] The online analysis model is used to perform price analysis on the updated impact factor value and the historical price to obtain the price of the target commodity of the preset commodity type in a future time period.

[0132] In the embodiment of the present invention, the online analysis model constructs a complex mathematical relationship model through in-depth learning and training of a large amount of historical price data and the updated impact factor values ​​related thereto. These updated impact factor values ​​cover various key factors that affect commodity prices, such as market supply and demand conditions, changes in production costs, policy and regulatory adjustments, and fluctuations in the macroeconomic environment. After the model learns the inherent connection and change rules between these factors and historical prices, when a new updated impact factor value is input, it can predict and analyze future prices based on the established relationship model and the trend information in the historical price data; for example, for coal price prediction, the model learns the correlation between coal production, transportation costs, industrial electricity consumption, environmental protection policies and other factors and coal prices in different periods in the past. When the current new coal production data (updated impact factor value) is obtained, the model will comprehensively consider the impact of historical price trends and other related factors to calculate the predicted value of future coal prices.

[0133] Detailed, such as Figure 2 As shown, an example diagram of the visualization result of the coal price index prediction value of the commodity price online analysis method of the first embodiment of the present invention is shown; the actual updated price of the target commodity of the preset commodity type in the preset time period is converted into a historical price; the historical price and the price index data of the target commodity are merged into updated price index data; the updated price index data is classified into updated classification index data according to the preset commodity type; the updated classification index data is screened to determine the updated impact factor value that affects the price of the target commodity of the preset commodity type in the preset future time period; the online analysis model is used to perform price analysis on the updated impact factor value and the historical price to obtain the price of the target commodity of the preset commodity type in the future time period.

[0134] In the embodiments of the present invention, through multi-link data integration and analysis, historical price and real-time price information are fully mined, influencing factors are accurately screened, and with the help of advanced model prediction capabilities, reliable commodity price trend forecasts are provided to enterprises, helping enterprises to make scientific decisions in procurement, sales, inventory management, etc., effectively reducing market risks, improving economic benefits and market competitiveness, and ensuring the stable operation and sustainable development of enterprises in a complex and changing market environment.

[0135] Embodiment 2

[0136] like Figure 3 As shown, this embodiment also provides a functional module diagram of a commodity price online analysis device.

[0137] The commodity price online analysis device 100 described in this embodiment can be installed in an electronic device. According to the functions to be implemented, the commodity price online analysis device 100 may include a data classification module 101, an impact determination module 102, a data partitioning module 103, a model training module 104, a model testing module 105 and a price analysis module 106. The module described in the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0138] In this embodiment, the functions of each module / unit are as follows:

[0139] The data classification module 101 is used to obtain price index data of a target commodity and classify the price index data into classification index data according to preset commodity types;

[0140] The impact determination module 102 is used to determine the impact factor value that affects the price of the target commodity of the preset commodity type in a preset time period by performing data screening on the classification index data;

[0141] The data division module 103 is used to divide the classification index data into a training set and a test set;

[0142] The model training module 104 is used to establish a prediction model, and use the impact factor value and the training set to perform model training on the prediction model to obtain a time series analysis model;

[0143] The model testing module 105 is used to obtain the actual updated price of the target commodity of the preset commodity type in a preset time period, and use the test set and the actual updated price to test and analyze the time series analysis model to obtain an online analysis model;

[0144] The price analysis module 106 is used to analyze the price of the target commodity of the preset commodity type in a preset future time period by using the online analysis model.

[0145] In detail, each module described in the online commodity price analysis device 100 described in the embodiment of the present invention adopts the same technical means as the online commodity price analysis method described in the first embodiment when in use, and can produce the same technical effects, which will not be repeated here.

[0146] Embodiment 3

[0147] like Figure 4 As shown, this embodiment also provides a computer electronic device, which may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as an online commodity price analysis program.

[0148] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (for example, executing a commodity price online analysis program, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device and process data.

[0149] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 11 may also include both an internal storage unit of the electronic device and an external storage device. The memory 11 may not only be used to store application software and various types of data installed in the electronic device, such as the code of a commodity price online analysis program, but may also be used to temporarily store data that has been output or is to be output.

[0150] The communication bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0151] The communication interface 13 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0152] The figure only shows an electronic device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0153] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0154] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0155] The commodity price online analysis program stored in the memory 11 in the electronic device is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0156] Acquire price index data of a target commodity, and classify the price index data into classification index data according to preset commodity types;

[0157] Determine the impact factor value that affects the price of the target commodity of the preset commodity type in a preset time period by performing data screening on the classification index data;

[0158] Dividing the classification index data into a training set and a test set;

[0159] Establishing a prediction model, and performing model training on the prediction model using the impact factor value and the training set to obtain a time series analysis model;

[0160] Acquire the actual updated price of the target commodity of the preset commodity type in a preset time period, and test and analyze the time series analysis model using the test set and the actual updated price to obtain an online analysis model;

[0161] The online analysis model is used to analyze the price of the target commodity of the preset commodity type in a preset future time period.

[0162] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0163] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0164] Embodiment 4

[0165] This embodiment provides a storage medium storing a computer program. When the computer program is executed by a processor, the steps of the online commodity price analysis method described above are implemented.

[0166] These program codes can also be loaded onto a computer or other programmable data processing device so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions executed on the computer or other programmable device for implementing the process. Figure 1 The steps of a specified function in a process or multiple processes.

[0167] Storage media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, modules of programs or other data. Examples of storage media can include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0168] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0169] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple 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.

[0170] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0171] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0172] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is not limited only according to the above description, and it is intended that all changes within the meaning and scope of equivalent elements within the scope of protection are included in the present invention.

[0173] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0174] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0175] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A commodity price online analysis method, characterized in that: The method comprises: Acquire price index data of a target commodity, and classify the price index data into classification index data according to preset commodity types; Determine the impact factor value that affects the price of the target commodity of the preset commodity type in a preset time period by performing data screening on the classification index data; Dividing the classification index data into a training set and a test set; Establishing a prediction model, and performing model training on the prediction model using the impact factor value and the training set to obtain a time series analysis model; Acquire the actual updated price of the target commodity of the preset commodity type in a preset time period, and test and analyze the time series analysis model using the test set and the actual updated price to obtain an online analysis model; The online analysis model is used to analyze the price of the target commodity of the preset commodity type in a preset future time period.

2. The commodity price online analysis method according to claim 1, characterized in that: The classifying the price index data into classification index data according to preset commodity types includes: Converting the price index data into a preset format to obtain unified format data; Identify commodity attribute information of the unified format data to obtain commodity attribute data; Marking the commodity attribute data; Different types of data tags are assigned to different databases to obtain classification index data.

3. The commodity price online analysis method according to claim 1, characterized in that: The step of determining the impact factor value that affects the price of the target commodity of the preset commodity type in a preset time period by screening the classification index data includes: Calculating the correlation coefficient between the classification index data and the preset influencing factors of the preset time period; Determining whether the correlation coefficient is higher than a preset coefficient threshold; If the correlation coefficient is lower than a preset coefficient threshold, deleting the influencing factor corresponding to the correlation coefficient; If the correlation coefficient is higher than a preset coefficient threshold, the correlation coefficient is used as a compliance coefficient; A multiple regression model is established with the classification index data as the dependent variable and the compliance coefficient as the independent variable; Calculating the model fit goodness of each independent variable by changing the independent variables in the multiple regression model one by one; Determining whether the model goodness of fit is higher than a preset goodness of fit threshold; If the model goodness of fit is lower than the preset goodness of fit threshold, deleting the influencing factor corresponding to the model goodness of fit; If the model goodness of fit is higher than the preset goodness of fit threshold, the conformity coefficient corresponding to the goodness of fit is used as the influencing factor value.

4. The commodity price online analysis method according to claim 1, characterized in that: The method of performing model training on the prediction model using the impact factor value and the training set to obtain a time series analysis model includes: The prediction model is converted into a training time series model using the impact factor value and the training set as exogenous variables and the classification index data as endogenous variables; Performing model training on the training set using the training time series model to obtain an analysis output value; Calculating a loss value based on the analysis output value and the classification index data; Determine whether the loss value is higher than a preset loss value threshold; If the loss value is higher than the preset loss value threshold, calculating the model parameters according to the loss value; Using the model parameters to update the parameters of the time series model, and using the training time series model after parameter update to perform model training on the training set; If the loss value is lower than the preset loss value threshold, the model training is confirmed to be completed and a timing analysis model is obtained.

5. The commodity price online analysis method according to claim 1, characterized in that: The step of testing and analyzing the timing analysis model using the test set and the actual update price to obtain an online analysis model includes: Performing model testing on the test set using the time series model to obtain a model analysis value; Calculate an error value based on the model analysis value and the actual update price; Determining whether the error value is higher than a preset error value threshold; If the error value is higher than the preset error value threshold, the preset coefficient threshold and the preset loss value threshold are adjusted, and the model training is performed again; If the error value is lower than the preset error value threshold, it is confirmed that the model test is completed and an online analysis model is obtained.

6. The commodity price online analysis method according to claim 1, characterized in that: The using the online analysis model to analyze the price of the target commodity of the preset commodity type in a preset future time period includes: Converting the actual updated price of the target commodity of the preset commodity type in a preset time period into a historical price; Merging the historical price and the price index data of the target commodity into updated price index data; Classifying the updated price index data into updated classification index data according to preset commodity types; Performing data screening on the updated classification index data to determine an updated impact factor value that affects the price of a target commodity of the preset commodity type in a preset future time period; The online analysis model is used to perform price analysis on the updated impact factor value and the historical price to obtain the price of the target commodity of the preset commodity type in a future time period.

7. A commodity price online analysis device, characterized in that: The device comprises: A data classification module, used to obtain price index data of a target commodity and classify the price index data into classification index data according to preset commodity types; An influence determination module, configured to determine an influence factor value that affects the price of a target commodity of the preset commodity type in a preset time period by performing data screening on the classification index data; A data partitioning module, used for partitioning the classification index data into a training set and a test set; A model training module is used to establish a prediction model, and to perform model training on the prediction model using the impact factor value and the training set to obtain a time series analysis model; A model testing module, used to obtain the actual updated price of the target commodity of the preset commodity type in a preset time period, and to test and analyze the time series analysis model using the test set and the actual updated price to obtain an online analysis model; The price analysis module is used to analyze the price of the target commodity of the preset commodity type in a preset future time period by using the online analysis model.

8. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the commodity price online analysis method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the commodity price online analysis method described in any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the commodity price online analysis method described in any one of claims 1 to 6 are implemented.

Images