A global industry trend forecasting analysis method and system

Abstract

The application discloses a kind of global industry trend prediction analysis method and system, it includes: obtaining and analyzing the cross-sectional data of each industry in different periods, determine the index data characteristics of each preset index in different periods;Based on index data characteristics, the index characteristic value of each preset index in different periods is calculated, and data set is respectively constructed;Extract the data variation characteristics of each data set, and based on it and preset prediction model, the data prediction model of each preset index is constructed to predict and obtain index characteristic prediction value;Based on the index characteristic prediction value of each preset index, the future competition prediction value of each industry is determined, and based on the index characteristic value of each preset index, the competition development coefficient of each industry history is determined;Based on the competition prediction value and competition development coefficient of each industry, development trend analysis value is determined.The application realizes the change from static description to dynamic prediction, from isolated research to systematic analysis, provides accurate quantitative analysis basis for industrial strategic layout.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, and in particular to a method and system for predicting and analyzing global industry trends. Background Technology

[0002] Against the backdrop of deepening globalization and accelerating technological revolution, the industrial landscape is undergoing unprecedented and profound changes. Traditional industry analysis often relies on trend extrapolation from single time series or static cross-sectional comparisons, making it difficult to systematically capture the dynamics, interconnectedness, and complexity of the industrial ecosystem, especially lacking a collaborative perspective when conducting comparative analysis of multiple industries globally. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention provides a global industry trend forecasting and analysis method and system, comprising:

[0004] Obtain cross-sectional data of various industries around the world at different times, analyze the cross-sectional data, and determine the characteristics of the indicator data corresponding to each preset indicator at different times; The characteristic values ​​of each preset indicator in different periods are calculated based on the characteristics of the indicator data, and datasets are constructed based on the characteristic values ​​of each preset indicator in different periods. Extract the data change characteristics of each dataset, and construct a data prediction model for each preset indicator based on the data change characteristics and the preset prediction model to make predictions and obtain the predicted values ​​of the indicator characteristics; The future competitive forecast value of each industry is determined based on the indicator characteristic prediction value of each preset indicator, and the historical competitive development coefficient of each industry is determined based on the indicator characteristic value of each preset indicator. A comprehensive analysis of the competitive forecast values ​​and competitive development coefficients of each industry is conducted to determine the development trend analysis values ​​of each industry.

[0005] Furthermore, the acquisition of cross-sectional data of various industries worldwide at different times, and the analysis of this cross-sectional data to determine the characteristics of each preset indicator at different times, includes: Obtain cross-sectional data of various industries around the world at different times, and determine pre-set indicators, including industry growth indicators, market share indicators, investment scale indicators, and innovation index indicators. Data analysis of cross-sectional data is conducted to determine the industry growth rate corresponding to the industry growth index, the industry economic share corresponding to the market share index, the total investment corresponding to the investment scale index, and the R&D investment share corresponding to the innovation index index for each industry in different periods. These are identified as the data characteristics of each preset index in different periods.

[0006] Furthermore, the step of calculating the indicator feature values ​​of each preset indicator at different times based on indicator data characteristics, and constructing datasets based on the indicator feature values ​​of each preset indicator at different times, includes: Determine the average and median of the corresponding indicator data characteristics for each preset indicator in the same period, and calculate the difference between the corresponding indicator data characteristics and the average and median for each preset indicator in the same period to obtain the difference in the mean and the difference in the median of each preset indicator in the same period. The mean difference and median difference of each preset indicator in the same period are evaluated and valued respectively to obtain the mean difference evaluation value and median difference evaluation value of each preset indicator in the same period, and the preset weights corresponding to the mean difference evaluation value and median difference evaluation value are determined. The characteristic values ​​of each preset indicator in the same period are obtained by weighted summation of the mean difference assessment value and median difference assessment value of each preset indicator in the same period, along with their corresponding preset weights. The characteristic values ​​of each preset indicator at different times are sorted and set in chronological order to construct the dataset corresponding to each preset indicator.

[0007] Furthermore, the step of extracting data change characteristics from each dataset and constructing data prediction models for each preset indicator based on these data change characteristics and a preset prediction model to obtain predicted values ​​for the indicator features includes: Extract the data change characteristics of each dataset, and input the dataset and data change characteristics into the corresponding preset time series prediction models to construct the initial data prediction models for each preset indicator; The dataset is divided into training and test sets according to a preset ratio, and the training and test sets are respectively input into the initial data prediction model for each preset indicator; The initial data prediction model is trained and tested until it meets the preset convergence conditions, thus obtaining the data prediction model for each preset indicator. Based on the data prediction model of each preset indicator, the predicted value of the indicator characteristics of each preset indicator is obtained.

[0008] Furthermore, the determination of future competitive forecasts for each industry based on the predicted values ​​of the indicator characteristics of each preset indicator includes: Determine the preset weights corresponding to each preset indicator, and then calculate the weighted sum of the predicted value of the indicator characteristics of each preset indicator with the corresponding preset weight to obtain the predicted value of future competition for each industry.

[0009] Furthermore, the determination of the historical competitive development coefficient of each industry based on the characteristic values ​​of each preset indicator includes: Based on the characteristic values ​​of each preset indicator, a time progress change curve is constructed, and the peak and trough points of each change curve are determined. The variation curve is divided into multiple curve segments based on the peak and valley points, and the slope of each curve segment is determined. Calculate the average slope of all curve segments to obtain the average slope of the changing curve, and determine the standard deviation of the changing curve; The development coefficients of each preset indicator are determined based on the average slope and standard deviation of the change curves, and the development coefficients of each preset indicator are added together to obtain the historical competitive development coefficients of each industry.

[0010] Furthermore, the determination of the development coefficients for each preset index based on the average slope and standard deviation of the change curve includes: The average slope and standard deviation of the change curve are evaluated and normalized to obtain the slope coefficient and standard deviation coefficient. The weights corresponding to the slope coefficient and standard deviation coefficient are determined respectively, and the slope coefficient and standard deviation coefficient are weighted and added to the corresponding weights to obtain the development coefficient of each preset indicator.

[0011] Furthermore, the comprehensive analysis of the competitive forecast values ​​and competitive development coefficients of each industry to determine the development trend analysis values ​​of each industry includes: Based on the competitive development coefficient of each industry, a correction coefficient is determined, and the correction coefficient is multiplied by the competitive forecast value to obtain the development trend analysis value of each industry.

[0012] Furthermore, the determination of correction coefficients based on the competitive development coefficients of each industry includes: A pre-defined correspondence between the preset correction coefficient and the competitive development coefficient interval is established. For each competitive development coefficient interval, a corresponding preset correction coefficient is associated with it. Determine the competitive development coefficient of each industry, and based on the mapping relationship between the competitive development coefficient interval to which the competitive development coefficient belongs and the corresponding relationship between the preset correction coefficient and the competitive development coefficient interval, select the preset correction coefficient corresponding to the competitive development coefficient interval as the correction coefficient of each industry.

[0013] This invention also provides a global industry trend forecasting and analysis system, comprising: The acquisition module is used to acquire cross-sectional data of various industries around the world at different times, and to analyze the cross-sectional data to determine the characteristics of the indicator data corresponding to each preset indicator at different times. The calculation module is used to calculate the indicator feature values ​​of each preset indicator in different periods based on the indicator data characteristics, and to construct datasets based on the indicator feature values ​​of each preset indicator in different periods. The prediction module is used to extract the data change characteristics of each dataset, and to construct a data prediction model for each preset indicator based on the data change characteristics and the preset prediction model to make predictions and obtain the predicted values ​​of the indicator characteristics. The determination module is used to determine the future competitive forecast value of each industry based on the indicator characteristic prediction value of each preset indicator, and to determine the historical competitive development coefficient of each industry based on the indicator characteristic value of each preset indicator. The analysis module is used to comprehensively analyze the competitive forecast values ​​and competitive development coefficients of various industries, and determine the development trend analysis values ​​of each industry.

[0014] Compared with existing technologies, the global industry trend forecasting and analysis method and system of this invention have the following advantages: This invention extracts the era-specific values ​​of industry indicators by analyzing cross-sectional data from various periods, transforming static indicators into a dynamic reference system that evolves over time. This solves the problem of rigid benchmarks in traditional analysis and independently constructs time-series prediction models for each core indicator, accurately predicting changes in the future industrial environment. This invention calculates the competitive forecast value of an industry based on future indicator forecast values ​​to measure its matching degree with the future benchmark environment. On the other hand, it calculates the competitive development coefficient based on historical performance to quantify its development momentum and path inertia, thus achieving a balance between forward-looking and continuous considerations. This invention generates development trend analysis values ​​for each industry that combine quantitative accuracy with qualitative insights by integrating competitive forecast values ​​and development coefficients. It can not only identify current leading industries, but also discover potential industries with continuous evolution capabilities. It provides full-chain decision support for strategic investment, policy making, and resource allocation, from macro-ecological insights to micro-industry positioning, and significantly improves the systematicness, dynamism, and operability of industry trend judgment. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the process structure of the global industry trend prediction and analysis method in an embodiment of the present invention; Figure 2 This is a schematic diagram of the composition of the global industry trend prediction and analysis system in an embodiment of the present invention. Detailed Implementation

[0016] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0017] like Figure 1As shown in the embodiments of this application, a global industry trend prediction and analysis method is provided, including: S100: acquiring cross-sectional data of various industries around the world at different periods, analyzing the cross-sectional data, and determining the indicator data characteristics corresponding to each preset indicator at different periods; S200: calculating the indicator characteristic values ​​of each preset indicator at different periods based on the indicator data characteristics, and constructing datasets based on the indicator characteristic values ​​of each preset indicator at different periods; S300: extracting the data change characteristics of each dataset, and constructing a data prediction model for each preset indicator based on the data change characteristics and a preset prediction model to make predictions and obtain the indicator characteristic prediction values; S400: determining the future competitive prediction values ​​of each industry based on the indicator characteristic prediction values ​​of each preset indicator, and determining the historical competitive development coefficient of each industry based on the indicator characteristic values ​​of each preset indicator; S500: comprehensively analyzing the competitive prediction values ​​and competitive development coefficients of each industry to determine the development trend analysis values ​​of each industry.

[0018] Furthermore, this invention extracts the era-specific values ​​of industry indicators by analyzing cross-sectional data from various periods, transforming static indicators into dynamic reference systems that evolve over time. This solves the problem of rigid benchmarks in traditional analysis. It also independently constructs time-series prediction models for each core indicator, accurately predicting future changes in the industry environment. On one hand, this invention calculates the competitive prediction value of an industry based on future indicator predictions, measuring its matching degree with the future benchmark environment. On the other hand, it calculates the competitive development coefficient based on historical performance, quantifying its development momentum and path inertia, achieving a balance between forward-looking and continuous considerations. Through the comprehensive analysis of competitive prediction values ​​and development coefficients, this invention generates development trend analysis values ​​for each industry that combine quantitative accuracy with qualitative insights. It can not only identify current leading industries but also discover potential industries with continuous evolutionary capabilities, providing full-chain decision support for strategic investment, policy formulation, and resource allocation, from macro-ecological insights to micro-industry positioning. This significantly improves the systematicness, dynamism, and operability of industry trend judgment.

[0019] In the embodiments of this application, a global industry trend prediction and analysis method is provided. The step of acquiring cross-sectional data of various industries around the world at different periods and analyzing the cross-sectional data to determine the indicator data characteristics corresponding to each preset indicator at different periods includes: acquiring cross-sectional data of various industries around the world at different periods and determining preset indicators, including industry growth indicators, market share indicators, investment scale indicators and innovation index indicators; performing data analysis on the cross-sectional data, and determining the industry growth rate corresponding to the industry growth indicator, the industry economic share corresponding to the market share indicator, the total investment corresponding to the investment scale indicator, and the R&D investment share corresponding to the innovation index indicator as the indicator data characteristics corresponding to each preset indicator at different periods.

[0020] Specifically, this approach involves acquiring cross-sectional data from various global industries at multiple historical points in time, focusing on four pre-defined core indicators: industry growth, market share, investment scale, and innovation index. Through data analysis, the growth rate, economic share, total investment, and R&D expenditure share of each industry in different periods are clearly quantified into corresponding indicator data characteristics. This step not only clearly presents the relative position and distribution structure of each industry in terms of growth momentum, market position, capital intensity, and innovation strength at the same time cross-section, but also extracts the dynamic evolution sequence of each indicator over time. This elevates discrete industry data into a systematic spatiotemporal characteristic matrix of industries, laying a precise, consistent, and computable data foundation for subsequent in-depth analysis of indicator evolution patterns and prediction of future industry environment benchmarks.

[0021] In the embodiments of this application, a global industry trend prediction and analysis method is provided. The method involves calculating the indicator feature values ​​of each preset indicator at different times based on indicator data characteristics, and constructing datasets based on the indicator feature values ​​of each preset indicator at different times. This includes: determining the average and median of the indicator data characteristics corresponding to each preset indicator at the same time, and calculating the difference between the indicator data characteristics of each preset indicator at the same time and the average and median, to obtain the indicator mean difference value and indicator median difference value of each preset indicator at the same time; evaluating the indicator mean difference value and indicator median difference value of each preset indicator at the same time, to obtain the indicator mean difference evaluation value and median difference evaluation value of each preset indicator at the same time, and determining the preset weights corresponding to the indicator mean difference evaluation value and median difference evaluation value; performing a weighted summation calculation based on the indicator mean difference evaluation value and median difference evaluation value of each preset indicator at the same time and the corresponding preset weights to obtain the indicator feature value of each preset indicator at the same time; and sorting and aggregating the indicator feature values ​​of each preset indicator at different times according to the chronological order to construct the dataset corresponding to each preset indicator.

[0022] Specifically, for each preset indicator, the average and median of all industry data are calculated for each specific period, serving as the benchmark for the industry ecosystem during that period. The difference between the actual data of each industry and these two central benchmarks is calculated to obtain the mean difference value and the median difference value, thereby quantifying the dispersion and distribution skewness of each industry relative to the overall level. These difference values ​​are standardized or graded for evaluation, transformed into a unified evaluation value, and assigned preset weights that reflect the focus of the analysis. The evaluation information from the two dimensions of mean and median is integrated through weighted calculation to synthesize a comprehensive indicator feature value, which robustly represents the overall industry ecosystem level and concentration state of the indicator in the corresponding period. These feature values ​​are then aggregated in chronological order to construct a time-series dataset reflecting the evolution of each indicator over time. This step, by fusing the mean (sensitive to outliers) and the median (more robust to the distribution center) and weighting them together, enables the resulting indicator feature values ​​to more reliably characterize the overall center of gravity of the industrial ecosystem, reducing the interference of extreme data. It achieves effective compression and extraction of distribution information, condensing massive, discrete cross-sectional industrial data into a feature value with clear economic meaning for each period and capable of time series analysis, greatly reducing data complexity. It lays a high-quality foundation for subsequent dynamic analysis. The constructed dataset is essentially the evolutionary history of the core dimension baseline of the industrial ecosystem, providing a clear, continuous, and meaningful input sequence for predicting future changes and assessing the relative position of individual industries. It is a key quantitative link in the entire prediction method chain.

[0023] In the embodiments of this application, a global industry trend prediction and analysis method is provided. The method involves extracting data change characteristics from each dataset and constructing data prediction models for each preset indicator based on the data change characteristics and preset prediction models to obtain predicted values ​​of indicator features. The method includes: extracting data change characteristics from each dataset and inputting the dataset and data change characteristics into corresponding preset time series prediction models to construct initial data prediction models for each preset indicator; dividing the dataset into training and testing sets according to a preset ratio and inputting the training and testing sets into the initial data prediction models for each preset indicator; training and testing the initial data prediction models until they meet preset convergence conditions to obtain data prediction models for each preset indicator; and making predictions based on the data prediction models for each preset indicator to obtain predicted values ​​of indicator features for each preset indicator.

[0024] Specifically, deep feature mining is performed on the time-series datasets of each preset indicator to extract core change patterns such as trends, seasonality, periodicity, and volatility. The datasets and these features are then input into a preset prediction model to complete the initial model construction. The datasets for each indicator are scientifically divided into training and testing sets according to a preset ratio, used for parameter learning and performance validation of the model, respectively. Through iterative training and testing, and by optimizing and validating the model according to preset convergence conditions, reliable data prediction models for each indicator are finally obtained after sufficient training and validation. Based on these models, the indicator feature values ​​at future points in time are predicted, and the predicted values ​​for each indicator are output. This step uses data variation characteristics as prior knowledge input into the model, guiding it to more accurately capture the inherent patterns of the sequence, thus improving the relevance and efficiency of model construction. Rigorous training-test splitting and convergence condition control ensure that the model not only fits historical data but also possesses good generalization ability and predictive robustness, effectively avoiding overfitting or underfitting. It generates independently optimized and reliable predictive models for each key indicator, and the predicted values ​​of the indicator features output by these models provide accurate and reliable quantitative input for the next step of assessing the competitive position of various industries in the future dynamic benchmark environment. This is the key computing engine that connects the preceding and following steps in the entire prediction chain.

[0025] In the embodiments of this application, a global industry trend prediction and analysis method is provided. The step of determining the future competitive prediction value of each industry based on the indicator feature prediction value of each preset indicator includes: determining the preset weight corresponding to each preset indicator, and weighting and adding the indicator feature prediction value of each preset indicator with the corresponding preset weight to obtain the future competitive prediction value of each industry.

[0026] Specifically, based on domain knowledge or data-driven methods, appropriate pre-defined weights are assigned to each preset indicator. These weights reflect the relative importance of different indicators in determining the future competitive position of an industry. The predicted values ​​of each indicator obtained in the previous step are weighted and summed with their corresponding weights to generate a single, comprehensive competitive prediction value, representing the overall competitive potential of the industry in the target future period. This step achieves effective fusion and dimensionality reduction of multi-dimensional predictive information, aggregating the scattered predicted values ​​of multiple indicators into a comprehensive score with clear comparative significance, solving the problems of information redundancy and decision-making difficulties in multi-indicator evaluation; enhancing the customizability and targeting of the evaluation, by adjusting the preset weights, it can flexibly reflect the value orientation under different decision-making scenarios, ensuring that the evaluation results are consistent with specific strategic goals; providing intuitive and actionable decision-making basis, the generated competitive prediction value can be directly used to prioritize, classify potential, or allocate resources for various industries globally, transforming complex predictive data into clear and actionable insights, significantly improving the conversion efficiency and decision reliability from trend prediction to strategic planning.

[0027] In an embodiment of this application, a global industry trend prediction and analysis method is provided. The method for determining the historical competitive development coefficient of each industry based on the characteristic values ​​of each preset indicator includes: constructing a time progress change curve based on the characteristic values ​​of each preset indicator, and determining the peak point and trough point of each change curve; dividing the change curve into multiple curve segments based on the peak point and trough point, and determining the slope of each curve segment; calculating the average slope of all curve segments to obtain the average slope of the change curve, and determining the standard deviation of the change curve; determining the development coefficient of each preset indicator based on the average slope and standard deviation of the change curve, and adding the development coefficients of each preset indicator to obtain the historical competitive development coefficient of each industry.

[0028] Specifically, based on the characteristic values ​​of each preset indicator at different times, a change curve over time is constructed, and key historical turning points are identified by detecting the peak and trough points of the curve. Based on these extreme points, each curve is divided into multiple continuous segments, and the slope of each segment is calculated to accurately quantify the rate of change of the indicator at different stages. The average slope of all curve segments is calculated as a measure of the overall trend strength, and its standard deviation is calculated to assess the degree of volatility. By combining the average slope (reflecting the trend direction and strength) and the standard deviation (reflecting stability), the development coefficient of each preset indicator is determined. Finally, the development coefficients of all indicators are added together to obtain the historical competitive development coefficient of each industry. This step transforms discrete historical data into an analyzable trend trajectory, and achieves precise quantification of the development pace and turning points through extreme value segmentation and slope calculation. By integrating trend strength and volatility, the development coefficient captures both the aggressiveness and robustness of industry growth, avoiding the bias of single-dimensional assessment. By summing the development coefficients of multiple indicators, a comprehensive indicator that fully reflects the historical competitive evolution of the industry is constructed, providing a reliable and in-depth historical benchmark for subsequent comparison of industry potential and diagnosis of development quality.

[0029] In the embodiments of this application, a global industry trend prediction and analysis method is provided. The method for determining the development coefficient of each preset indicator based on the average slope and standard deviation of the change curve includes: evaluating the average slope and standard deviation of the change curve and normalizing the evaluation results to obtain the slope coefficient and standard deviation coefficient; determining the weights corresponding to the slope coefficient and standard deviation coefficient respectively, and weighting and adding the slope coefficient and standard deviation coefficient with the corresponding weights to obtain the development coefficient of each preset indicator.

[0030] Specifically, the average slope (representing trend strength and direction) and standard deviation (representing volatility and stability) of the curves reflecting historical trends are standardized and normalized, transforming them into comparable slope coefficients and standard deviation coefficients between 0 and 1. Through summation, the comprehensive development coefficient for each preset indicator is finally obtained. This step achieves the integration and balance of multi-dimensional historical characteristics. By incorporating the slope (representing aggressiveness) and standard deviation (representing robustness) into a unified framework, it avoids the assessment bias of focusing solely on growth intensity while ignoring volatility risk. This allows the development coefficient to simultaneously characterize the industry's growth strength and development quality, providing a robust quantitative summary of the industry's historical momentum. The resulting development coefficient is a composite indicator integrating trend strength and stability, which can more comprehensively and fairly measure the industry's overall competitive evolution performance in past cycles, providing a solid and comparable historical dimension input for comprehensive analysis of subsequent and future competitive forecasts.

[0031] In the embodiments of this application, a global industry trend forecasting and analysis method is provided. The method involves comprehensively analyzing the competitive forecast values ​​and competitive development coefficients of each industry to determine the development trend analysis values ​​of each industry. This includes determining a correction coefficient based on the competitive development coefficient of each industry, and multiplying the correction coefficient by the competitive forecast value to obtain the development trend analysis values ​​of each industry.

[0032] Specifically, a correction coefficient is determined based on the historical competitive development coefficient of each industry. This coefficient is typically positively correlated with the development coefficient. This correction coefficient is then multiplied by the industry's independent future competitive forecast to obtain the final development trend analysis value. This step reflects the principle of development continuity. By incorporating the industry's historical path dependence into the final assessment through the correction coefficient, it avoids unreasonable judgments of weak historical performance but inflated future forecasts, making the analysis results more consistent with the laws of industrial development. The correction coefficient is essentially a confidence level. For industries with robust historical development (high competitive development coefficient), their future forecast values ​​will be amplified or strengthened; while for industries with large historical fluctuations or weak trends, their future forecast values ​​will be appropriately lowered. This reduces over-reliance on a single future forecast model and enhances the robustness of the assessment. A composite index that can be directly used for prioritization is output. The final development trend analysis value not only includes future prospects but also incorporates an assessment of historical foundations, becoming a comprehensive score that combines foresight and reality. This provides a highly condensed and logically sound decision-making basis for resource allocation, strategic focus, or risk warning.

[0033] In the embodiments of this application, a global industry trend prediction and analysis method is provided. The step of determining the correction coefficient based on the competitive development coefficient of each industry includes: pre-setting a preset correction coefficient-competitive development coefficient interval correspondence relationship, wherein the preset correction coefficient-competitive development coefficient interval correspondence relationship is associated with a corresponding preset correction coefficient for each competitive development coefficient interval; determining the competitive development coefficient of each industry, and selecting the preset correction coefficient corresponding to the competitive development coefficient interval as the correction coefficient of each industry based on the mapping relationship of the competitive development coefficient interval to which the competitive development coefficient belongs within the preset correction coefficient-competitive development coefficient interval correspondence relationship.

[0034] Specifically, by establishing a pre-defined correspondence between correction coefficients and competitive development coefficient intervals, the continuous values ​​of historical competitive development coefficients for industries are mapped to discrete correction coefficients. The historical competitive development coefficients for each industry are determined, and then, based on the specific intervals into which these coefficients fall, the corresponding pre-defined correction coefficients are automatically selected as multipliers to adjust future competitive forecasts. This step, through pre-defined interval mapping rules, completely eliminates the subjective arbitrariness of manually setting correction coefficients, ensuring consistency in evaluation standards across different industries and periods, and making the analysis results highly comparable and repeatable. Interval processing allows the system to move beyond simple linear proportional relationships, designing differentiated incentive or conservative correction strategies for industries at different development stages, such as those with weak foundations, steady development, and strong leadership. This makes the final development trend analysis values ​​more reflective of management wisdom and strategic orientation. Decision-makers or the analysis system do not need to make complex secondary judgments for each industry; they can automatically complete the correction based on clear and transparent interval rules, quantitatively and efficiently transforming historical momentum into calibration instructions for future predictions. This makes the comprehensive trend analysis process both rigorous and efficient, providing a reliable and automated solution for large-scale industry screening and prioritization.

[0035] like Figure 2As shown in the embodiments of this application, a global industry trend prediction and analysis system is provided, comprising: an acquisition module, used to acquire cross-sectional data of various industries around the world at different periods, and analyze the cross-sectional data to determine the indicator data characteristics corresponding to each preset indicator at different periods; a calculation module, used to calculate the indicator characteristic values ​​of each preset indicator at different periods based on the indicator data characteristics, and construct datasets based on the indicator characteristic values ​​of each preset indicator at different periods; a prediction module, used to extract the data change characteristics of each dataset, and construct a data prediction model for each preset indicator based on the data change characteristics and a preset prediction model to make predictions and obtain the indicator characteristic prediction values; a determination module, used to determine the future competitive prediction values ​​of each industry based on the indicator characteristic prediction values ​​of each preset indicator, and determine the historical competitive development coefficient of each industry based on the indicator characteristic values ​​of each preset indicator; and an analysis module, used to comprehensively analyze the competitive prediction values ​​and competitive development coefficients of each industry to determine the development trend analysis values ​​of each industry.

[0036] In summary, this invention provides a global industry trend forecasting and analysis method and system, comprising: acquiring and analyzing cross-sectional data of various industries globally at different times, and determining the indicator data characteristics of each preset indicator at different times; calculating the indicator characteristic values ​​of each preset indicator at different times based on the indicator data characteristics, and constructing datasets respectively; extracting the data change characteristics of each dataset, and constructing a data prediction model for each preset indicator based on the data change characteristics and a preset prediction model to predict the indicator characteristic values; determining the future competitive prediction values ​​of each industry based on the indicator characteristic prediction values ​​of each preset indicator, and determining the historical competitive development coefficient of each industry based on the indicator characteristic values ​​of each preset indicator; and determining the development trend analysis value based on the competitive prediction values ​​and competitive development coefficients of each industry. This invention realizes the transformation from static description to dynamic prediction, and from isolated judgment to systematic analysis, providing accurate quantitative analysis basis for industrial strategic layout.

[0037] Finally, it should be noted that those skilled in the art can obviously make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A global industry trend forecasting and analysis method, characterized in that, include: Obtain cross-sectional data of various industries around the world at different times, analyze the cross-sectional data, and determine the characteristics of the indicator data corresponding to each preset indicator at different times; The characteristic values ​​of each preset indicator in different periods are calculated based on the characteristics of the indicator data, and datasets are constructed based on the characteristic values ​​of each preset indicator in different periods. Extract the data change characteristics of each dataset, and construct a data prediction model for each preset indicator based on the data change characteristics and the preset prediction model to make predictions and obtain the predicted values ​​of the indicator characteristics; The future competitive forecast value of each industry is determined based on the indicator characteristic prediction value of each preset indicator, and the historical competitive development coefficient of each industry is determined based on the indicator characteristic value of each preset indicator. A comprehensive analysis of the competitive forecast values ​​and competitive development coefficients of each industry is conducted to determine the development trend analysis values ​​of each industry.

2. The global industry trend forecasting and analysis method according to claim 1, characterized in that, The process of acquiring cross-sectional data of various industries worldwide at different times, analyzing the cross-sectional data, and determining the data characteristics of each preset indicator at different times includes: Obtain cross-sectional data of various industries around the world at different times, and determine pre-set indicators, including industry growth indicators, market share indicators, investment scale indicators, and innovation index indicators. Data analysis of cross-sectional data is conducted to determine the industry growth rate corresponding to the industry growth index, the industry economic share corresponding to the market share index, the total investment corresponding to the investment scale index, and the R&D investment share corresponding to the innovation index index for each industry in different periods. These are identified as the data characteristics of each preset index in different periods.

3. The global industry trend forecasting and analysis method according to claim 2, characterized in that, The step of calculating the indicator feature values ​​of each preset indicator at different times based on indicator data characteristics, and constructing datasets based on the indicator feature values ​​of each preset indicator at different times, includes: Determine the average and median of the corresponding indicator data characteristics for each preset indicator in the same period, and calculate the difference between the corresponding indicator data characteristics and the average and median for each preset indicator in the same period to obtain the difference in the mean and the difference in the median of each preset indicator in the same period. The mean difference and median difference of each preset indicator in the same period are evaluated and valued respectively to obtain the mean difference evaluation value and median difference evaluation value of each preset indicator in the same period, and the preset weights corresponding to the mean difference evaluation value and median difference evaluation value are determined. The characteristic values ​​of each preset indicator in the same period are obtained by weighted summation of the mean difference assessment value and median difference assessment value of each preset indicator in the same period, along with their corresponding preset weights. The characteristic values ​​of each preset indicator at different times are sorted and set in chronological order to construct the dataset corresponding to each preset indicator.

4. The global industry trend forecasting and analysis method according to claim 3, characterized in that, The process involves extracting data change characteristics from each dataset, constructing data prediction models for each preset indicator based on these characteristics and a preset prediction model, and obtaining predicted values ​​for the indicator features, including: Extract the data change characteristics of each dataset, and input the dataset and data change characteristics into the corresponding preset time series prediction models to construct the initial data prediction models for each preset indicator; The dataset is divided into training and test sets according to a preset ratio, and the training and test sets are respectively input into the initial data prediction model for each preset indicator; The initial data prediction model is trained and tested until it meets the preset convergence conditions, thus obtaining the data prediction model for each preset indicator. Based on the data prediction model of each preset indicator, the predicted value of the indicator characteristics of each preset indicator is obtained.

5. The global industry trend forecasting and analysis method according to claim 4, characterized in that, The determination of future competitive forecasts for each industry based on the predicted values ​​of indicator characteristics of each preset indicator includes: Determine the preset weights corresponding to each preset indicator, and then calculate the weighted sum of the predicted value of the indicator characteristics of each preset indicator with the corresponding preset weight to obtain the predicted value of future competition for each industry.

6. The global industry trend forecasting and analysis method according to claim 5, characterized in that, The determination of the historical competitive development coefficient of each industry based on the characteristic values ​​of each preset indicator includes: Based on the characteristic values ​​of each preset indicator, a time progress change curve is constructed, and the peak and trough points of each change curve are determined. The variation curve is divided into multiple curve segments based on the peak and valley points, and the slope of each curve segment is determined. Calculate the average slope of all curve segments to obtain the average slope of the changing curve, and determine the standard deviation of the changing curve; The development coefficients of each preset indicator are determined based on the average slope and standard deviation of the change curves, and the development coefficients of each preset indicator are added together to obtain the historical competitive development coefficients of each industry.

7. The global industry trend forecasting and analysis method according to claim 6, characterized in that, The determination of the development coefficients for each preset index based on the average slope and standard deviation of the change curve includes: The average slope and standard deviation of the change curve are evaluated and normalized to obtain the slope coefficient and standard deviation coefficient. The weights corresponding to the slope coefficient and standard deviation coefficient are determined respectively, and the slope coefficient and standard deviation coefficient are weighted and added to the corresponding weights to obtain the development coefficient of each preset indicator.

8. The global industry trend forecasting and analysis method according to claim 6, characterized in that, The comprehensive analysis of the competitive forecast values ​​and competitive development coefficients of each industry determines the development trend analysis values ​​of each industry, including: Based on the competitive development coefficient of each industry, a correction coefficient is determined, and the correction coefficient is multiplied by the competitive forecast value to obtain the development trend analysis value of each industry.

9. The global industry trend forecasting and analysis method according to claim 8, characterized in that, The determination of correction coefficients based on the competitive development coefficients of each industry includes: A pre-defined correspondence between the preset correction coefficient and the competitive development coefficient interval is established. For each competitive development coefficient interval, a corresponding preset correction coefficient is associated with it. Determine the competitive development coefficient of each industry, and based on the mapping relationship between the competitive development coefficient interval to which the competitive development coefficient belongs and the corresponding relationship between the preset correction coefficient and the competitive development coefficient interval, select the preset correction coefficient corresponding to the competitive development coefficient interval as the correction coefficient of each industry.

10. A global industry trend forecasting and analysis system, characterized in that, include: The acquisition module is used to acquire cross-sectional data of various industries around the world at different times, and to analyze the cross-sectional data to determine the characteristics of the indicator data corresponding to each preset indicator at different times. The calculation module is used to calculate the indicator feature values ​​of each preset indicator in different periods based on the indicator data characteristics, and to construct datasets based on the indicator feature values ​​of each preset indicator in different periods. The prediction module is used to extract the data change characteristics of each dataset, and to construct a data prediction model for each preset indicator based on the data change characteristics and the preset prediction model to make predictions and obtain the predicted values ​​of the indicator characteristics. The determination module is used to determine the future competitive forecast value of each industry based on the indicator characteristic prediction value of each preset indicator, and to determine the historical competitive development coefficient of each industry based on the indicator characteristic value of each preset indicator. The analysis module is used to comprehensively analyze the competitive forecast values ​​and competitive development coefficients of various industries, and determine the development trend analysis values ​​of each industry.

Images