Multi-dimensional environment sensing platform and sensing method oriented to development of emerging industries of companies

Abstract

The invention provides a multi-dimensional environment perception platform and perception method for company emerging industry development, and the platform comprises a macroscopic environment perception module which determines the macroscopic environment and key factors faced by the strategic emerging industry of a company according to the monitored key market dynamics and policies and regulations; the policy environment, the economic environment, the social environment and the technical environment faced by the strategic emerging industry of the company are analyzed and determined through a macroscopic environment analysis method, and the operation strategy and the long-term plan of the company are adjusted and formulated; the market situation faced by the strategic emerging industry of a company is analyzed, the environmental influence evaluation module associates environmental elements with enterprise strategic planning, historical environmental data monitored by the environment in the life cycle of the industry or a product is obtained, and prediction results of environmental influence indexes in different stages are determined through regression analysis of a machine learning algorithm.

Description

Technical Field

[0001] The present invention relates to the field of information analysis technology, and in particular to a multi-dimensional environment perception platform, perception method, equipment and medium for the company's emerging industry development. Background Art

[0002] Given that digital transformation has become a core competitive advantage for reshaping manufacturing companies, companies urgently need to develop operational monitoring and management decision support tools to provide accurate market environment perception and strategic development support. In terms of how to provide companies with accurate market environment perception and strategic development support, market research, competition analysis and policy monitoring of strategic emerging industries have become a problem that companies need to solve urgently. Environmental perception is the process of acquiring and understanding environmental factors and speculating on future states under specific time and space conditions. Although some progress has been made in the perception of corporate market environment and strategic development support, there are still some technical and methodological limitations. For example, traditional methods consider limited factors in the environmental perception module and usually rely on manual analysis and subjective judgment. There are problems such as incomplete information collection, large amounts of data that are difficult to process, and difficulty in in-depth analysis. Therefore, there is still room for improvement in comprehensive, real-time and accurate market dynamic information and strategic environmental perception. Developing an enterprise operation monitoring and management improvement decision support architecture is crucial for enterprises to achieve long-term development, improve operational efficiency and respond to market challenges. In the big data economy, strengthening the innovation mechanism of enterprise operation management and services is one of the important means to enhance the core competitiveness of enterprises.

[0003] With the rapid development of digital technology, it is extremely important to build a multi-dimensional environmental perception platform architecture for the development of the company's emerging industries. The existing corporate development control architecture only considers some factors that affect environmental perception, and fails to comprehensively integrate the impact of various key factors on the development of the company's strategic emerging industries, thereby limiting the accurate analysis and comprehensive evaluation of the overall environment. At the same time, the existing architecture often relies on a single or limited information channel when collecting information, fails to make full use of a wide range of data sources, and the existing architecture usually relies on manual or simple rule systems, making it difficult to achieve intelligent, multi-dimensional automatic integration analysis. The proposed architecture uses data analysis and artificial intelligence and other technologies to efficiently analyze and predict data from different sources. This leads to incomplete, delayed or inaccurate information, which in turn affects the timely response to environmental changes and decision-making. In addition, the existing architecture relies too much on data preprocessing and manual intervention, lacks intelligence in learning historical experience knowledge, and fails to fully consider the impact mechanism of environmental factors on various links in the industrial chain in the environmental impact assessment module. This may lead to insufficient accuracy and feasibility assessment of the company's strategic emerging industry development path. These deficiencies will restrict the comprehensive grasp and accurate evaluation of the multi-dimensional environment, making strategic planning and business development more complex and difficult.

[0004] In view of this, there is an urgent need to provide a more comprehensive, efficient and dynamic multi-dimensional environmental perception platform for the development of the company's emerging industries to meet the challenges faced by the development of the company's emerging industries. Summary of the invention

[0005] In order to overcome the problems existing in the related technologies, the present disclosure provides a multi-dimensional environmental perception platform, perception method, equipment and medium for the development of the company's emerging industries to solve the technical problems in the related technologies.

[0006] One or more embodiments of this specification provide a multi-dimensional environment perception platform for the development of emerging industries of a company, including:

[0007] The macro-environment perception module is used to determine the macro-environment faced by the company's strategic emerging industries and the key factors affecting the development of the company's strategic emerging industries in each macro-environment based on the key market dynamics and policies and regulations monitored. Based on the key factors, the macro-environment analysis method is used to analyze and determine the policy environment, economic environment, social environment and technological environment faced by the company's strategic emerging industries, as well as the potential risks and opportunities in the external environment, so as to adjust and formulate the company's operating strategy and long-term plan. Among them, the key factors affecting the development of the company's strategic emerging industries in the macro-environment include market factors, environmental factors and enterprise factors themselves;

[0008] The industrial environment perception module is used to analyze the industrial environment faced by the company's strategic emerging industries, determine the key factors in various industrial environments that affect the development of the company's strategic emerging industries, and analyze the market situation faced by the company's strategic emerging industries based on the key factors. The market situation includes competition situation analysis, technology trend forecast and economic situation analysis; the key factors in the industrial environment that affect the development of the company's strategic emerging industries include industrial policy factors, regulatory factors, and policy characteristic factors; and

[0009] The environmental impact assessment module is used to link environmental factors with corporate strategic planning, and obtain historical environmental data monitored during the industry or product life cycle, the company's internal energy use or waste emission operation data, and data obtained through experiments or simulations during product development or manufacturing. Based on the acquired data, the prediction results of environmental impact indicators at different stages are determined through regression analysis using machine learning algorithms.

[0010] One or more embodiments of this specification provide a multi-dimensional environment perception method for the development of emerging industries of a company, including the following steps:

[0011] According to the key market dynamics and policies and regulations monitored, determine the macro environment faced by the company's strategic emerging industries, as well as the key factors in each macro environment that affect the development of the company's strategic emerging industries. Based on the key factors, use the macro environment analysis method to analyze and determine the policy environment, economic environment, social environment and technological environment faced by the company's strategic emerging industries, as well as the potential risks and opportunities in the external environment, so as to adjust and formulate the company's operating strategy and long-term plan. Among them, the key factors in the macro environment that affect the development of the company's strategic emerging industries include market factors, environmental factors and enterprise factors themselves;

[0012] By analyzing the industrial environment faced by the company's strategic emerging industries, determine the key factors in each industrial environment that affect the development of the company's strategic emerging industries, and analyze the market situation faced by the company's strategic emerging industries based on the key factors. The market situation includes competition situation analysis, technology trend forecast and economic situation analysis; the key factors in the industrial environment that affect the development of the company's strategic emerging industries include industrial policy factors, regulatory factors, and policy characteristics factors; and

[0013] Link environmental factors with corporate strategic planning, obtain historical environmental data from environmental monitoring during the industry or product life cycle, the company's internal energy use or waste emission operation data, and data obtained through experiments or simulations during product development or manufacturing, and then determine the prediction results of environmental impact indicators at different stages through machine learning algorithm regression analysis based on the acquired data.

[0014] One or more embodiments of the present specification provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the multi-dimensional environment perception method for the development of emerging industries of a company as described above when executing the computer program.

[0015] One or more embodiments of the present specification provide a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the multi-dimensional environment perception method for the development of emerging industries of a company as described above is implemented.

[0016] The multi-dimensional environment perception platform, perception method, device and medium provided by the present disclosure for the development of emerging industries of the company have the following advantages:

[0017] First, by integrating the macro-environment perception module, the industrial environment perception module and the environmental impact assessment module, comprehensive consideration and comprehensive analysis of multi-dimensional data and unstructured data are achieved. This comprehensive information coverage and in-depth analysis ensure that companies can make more accurate strategic decisions under complex and changing market conditions.

[0018] Second, by adopting advanced business management, data analysis and artificial intelligence technologies, such as macro-environment analysis and technology trend forecasting, this platform can provide a more comprehensive macro and industrial environment analysis, enabling companies to identify and utilize emerging technologies and market trends, promote the development of innovation and differentiation strategies, and greatly improve the speed and accuracy of data processing. This forward-looking analysis and forecasting technology support helps companies seize technological high ground and enhance their competitiveness in the market.

[0019] Third, in the environmental impact assessment module, through the calculation and report generation of environmental indicators, the present invention helps enterprises identify and utilize key environmental variables and optimize resource allocation. Potential risks and opportunities can be identified in advance and utilized or avoided, thereby optimizing cost-effectiveness and supporting sustainable development strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate one or more embodiments of this specification 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 recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 A schematic diagram of a multi-dimensional environment perception platform for the development of emerging industries of a company provided by one or more embodiments of this specification;

[0022] Figure 2 A multi-dimensional environment perception architecture diagram for the development of the company's emerging industries provided for one or more embodiments of this specification

[0023] Figure 3 A flowchart of a multi-dimensional environment perception method for the development of a company's emerging industries provided for one or more embodiments of this specification; and

[0024] Figure 4 A schematic diagram of the structure of a computer device provided for one or more embodiments of this specification. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0026] The present invention is described in detail below in conjunction with specific implementation methods and the accompanying drawings.

[0027] Platform Implementation

[0028] According to an embodiment of the present invention, a multi-dimensional environment perception platform for the development of emerging industries of a company is provided. Figure 1-2 As shown, Figure 1 This is a schematic diagram of a multi-dimensional environment perception platform for the development of emerging industries of the company provided in this embodiment. Figure 2 The multi-dimensional environment perception architecture diagram for the development of emerging industries of the company provided in this embodiment, the multi-dimensional environment perception platform for the development of emerging industries of the company in this embodiment of the present invention includes:

[0029] The macro-environment perception module 10 is used to determine the macro-environment faced by the company's strategic emerging industries, as well as the key factors affecting the development of the company's strategic emerging industries in each macro-environment based on the key market dynamics and policies and regulations monitored. Based on the key factors, the policy environment, economic environment, social environment and technological environment faced by the company's strategic emerging industries are determined through macro-environment analysis method.

[0030] In this embodiment, according to the various environments faced by the company's strategic emerging industries determined by analysis, potential risks and opportunities in the external environment can be determined, so as to adjust and formulate the company's operating strategy and long-term plan to maximize the company's competitive advantage and resist external risks. Among them, the key factors affecting the development of the company's strategic emerging industries in the macro environment include market factors, environmental factors and enterprise factors themselves;

[0031] Market factors include market size, market growth rate, potential market demand and other factors; environmental factors include target market characteristics, competitive market conditions, the importance and impact of different environmental factors on the market; and enterprise factors include strengths, weaknesses, opportunities and threats.

[0032] In this embodiment, the macro-environment perception module 10 is configured to execute the following steps to adjust and formulate the company's operating strategy and long-term plan. The specific steps are as follows:

[0033] Step A1, key market dynamics monitoring: monitor the real-time dynamic data of strategic emerging industry markets, including key indicators such as market size, market growth rate, potential demand, etc., and use strategic tools to evaluate the strengths, weaknesses, opportunities and threats of companies or products in the market; and then obtain comprehensive reports on market trends and industry development through data analysis;

[0034] The process of determining the market growth rate is as follows:

[0035] First, collect market information and identify key markets, including target markets and competitive markets. Then collect market size data, industry reports, market trend analysis and market research results. Finally, conduct a comprehensive analysis of the collected information and calculate the market growth rate as follows:

[0036]

[0037] Among them, the future expected market size and current market size can be estimated based on data obtained from industry reports or market research.

[0038] In this embodiment, the strategic tool can be a SWOT tool, which evaluates the strengths, weaknesses, opportunities and threats of a company or product in the market based on key indicators. Based on the results of cross-analysis, a more comprehensive assessment of the market situation can be made to maintain market sensitivity and responsiveness.

[0039] Step A2, industrial policy and regulation monitoring, determines the industrial policy environment by tracking the data on changes in relevant policies and regulations on strategic emerging industries in countries and regions, including industrial policy elements, regulatory elements, and policy characteristic elements. Among them, industrial policy elements include industrial support, tax reduction policies, and environmental regulations; regulatory elements include incentive policies, regulatory requirements, and industry entry barriers; policy characteristic elements include policy stability, consistency, and predictability.

[0040] In a specific embodiment, the above policy elements can be determined through relevant policy and regulatory documents and government policy announcements, and then the impact of the policy on the company's strategic emerging industries is studied, the stability, consistency and predictability of the policy are evaluated, and the support or restriction factors for the company's industrial development can be determined, among which:

[0041] Step A3, integration analysis and strategy formulation; the market dynamics data and market environment data collected in steps A1 and A2 are used to determine the main factors affecting the development of the company's strategic emerging industries through the PEST analysis method as key factors, and based on the key factor analysis, the policy environment, economic environment, social environment and technological environment faced by the company's strategic emerging industries are determined. The potential risks and opportunities in the external environment can also be evaluated, so as to adjust and formulate the company's strategies and long-term plans to maximize the company's competitive advantage and resist external risks.

[0042] In this embodiment, the PEST analysis process includes the following steps:

[0043] 1) List the key factors identified during the environmental change analysis process;

[0044] 2) Determine the weight of each key factor based on its specific impact on the enterprise;

[0045] 3) Score each key factor according to the company's current strategy;

[0046] 4) Multiply the weight of each key factor by its score to get the corresponding weighted score;

[0047] 5) Add up the weighted scores of all key factors to obtain the total weighted score of the company's macroeconomic environment.

[0048] In this embodiment, some open source PEST analysis tools are used for integrated analysis, such as PESTLE Analysis Tool and SWOT and PEST Analysis Tool, etc. The specific implementation of the strategy formulation process based on key factors is a prior art and will not be described in detail here.

[0049] The industrial environment perception module 20 is used to determine the key factors affecting the development of the company's strategic emerging industries in various industrial environments by analyzing the industrial environment faced by the company's strategic emerging industries, and analyze the market situation faced by the company's strategic emerging industries based on the key factors, where the market situation includes competition situation analysis, technology trend forecasting and economic situation analysis.

[0050] In this embodiment, the industrial environment perception module 20 is configured to perform the following steps to analyze the market situation faced by the company's strategic emerging industries. The specific steps are as follows:

[0051] Step B1, market competition situation analysis; by tracking competitors' trends, including product launches, pricing strategies, market share changes, etc., use complex network analysis methods to analyze the competition landscape, determine the company's own strengths and weaknesses, and formulate response strategies; complex network analysis methods provide a variety of network analysis indicators, such as degree centrality, betweenness centrality, proximity centrality, etc., which can be used to identify key competitors. Community detection can also be performed to divide different competitive groups. Through this network analysis method, we can better understand the market competition situation, discover hidden competitive relationships, and provide decision-making support for the company's strategic emerging industry development. This analysis process is automated and does not require human intervention, thus ensuring the objectivity and reliability of the analysis results.

[0052] In this embodiment, the complex network analysis method can be implemented by using the open source Gephi software.

[0053] Step B2, technology trend prediction: Using the K-means algorithm to predict the technology trends of emerging industries based on competitors' data on product releases, pricing strategies, market share, etc., can help companies seize the commanding heights of the future market, thereby realizing technology research and development and innovation direction planning. The specific steps are as follows:

[0054] First, collect data about competitors' product releases, pricing strategies, market share, etc. This can be done through public financial reports, news reports, social media monitoring, market research reports, etc. Then, clean the data, remove incomplete or erroneous data entries, and standardize the data to ensure that each data point is comparable. Then, use the improved K-means clustering algorithm to cluster the data and obtain clustering results, thereby realizing technology trend prediction.

[0055] Since the original K-means algorithm may not work well when processing data with different densities and sizes, in order to better serve the development of the company's strategic emerging industries and provide more accurate market insights and trend analysis, this embodiment uses an improved K-means clustering algorithm. The purpose is to identify potential customer groups or market segments contained in the data based on data of different densities and sizes, and provide a basis for the company's strategic planning, including accurate market positioning, product / service design, and resource allocation. By comparing clustering results in different periods, dynamic market development trends can also be revealed.

[0056] In this embodiment, the improved K-means clustering algorithm is mainly used to better serve the development of the company's strategic emerging industries and provide more accurate market insights and trend analysis, because the traditional K-means clustering algorithm is difficult to directly apply to the development analysis of the company's strategic emerging industries.

[0057] In this embodiment, the improved K-means clustering algorithm is improved on the basis of the original clustering algorithm, and the specific improvements are as follows:

[0058] 1. Use the silhouette coefficient to determine the appropriate number of clusters; the original K-means algorithm requires manual specification of the number of clusters in advance, which may be subjective. The improved algorithm recommends using the silhouette coefficient to evaluate the optimal number of clusters, which can more objectively determine the appropriate K value.

[0059] 2. Calculate cluster centers and determine cluster center characteristics; when calculating cluster centers, the improved algorithm not only gives the coordinate values ​​of cluster centers, but also calculates descriptive statistics such as the standard deviation of cluster centers, which helps to better understand the characteristics of each cluster and identify key customer characteristics or market opportunities.

[0060] 3. Indicating data point affiliation through iteratively calculated indicator variables: The improved algorithm uses adaptive indicator variables to determine the cluster to which each data point belongs, which is important for accurate market positioning and resource allocation.

[0061] Cluster centers represent typical characteristics of different market segments or customer groups, which helps enterprises identify key customer characteristics or market opportunities. Analyze the statistical characteristics of each cluster, such as cluster center and standard deviation, to identify key characteristics of different customer groups or market segments. Classify each user into the most inappropriate group.

[0062] In a specific embodiment, the core of the improved K-means algorithm is to minimize the sum of the squares of the distances from each point to its cluster center, that is, to optimize the following objective function as follows:

[0063]

[0064] Where n represents the total number of data points;

[0065] K represents the number of clusters, which represents the number of parts into which a market or customer group is divided. In this embodiment, selecting a suitable K value helps enterprises to accurately identify different market segments or customer types, and then design products or services in a targeted manner;

[0066] x i represents the i-th data point, which represents a customer, a transaction, a product unit, or a response in a market survey; these data points contain information that is critical to the company's strategic planning, such as customer purchasing behavior, preferences, or feedback;

[0067] μ k represents the center of the kth cluster, which can be regarded as the typical characteristics or average behavior of the corresponding group or market segment;

[0068] r ik represents an indicator variable. Understanding the characteristics of each center helps identify key customer characteristics or market opportunities. ik is an indicator variable, if the data point x i belongs to cluster k, then r ik =1, otherwise r ik =0, this parameter is crucial for determining which customers belong to a specific market segment, enabling enterprises to conduct accurate market positioning and resource allocation, |x i -μ k | 2 is the data point x i to μ k The square of the Euclidean distance.

[0069] The clustering iteration process of the improved K-means algorithm in this embodiment is as follows:

[0070] The first step is initialization; randomly select k data points from the data set as the initial cluster center μ k .

[0071] The second step is the allocation step; for each data point x i , determine the nearest cluster center and update r ik , specifically if k = argmin j |x i -μ k | 2 , then r ik =1, otherwise r ik =0.

[0072] The third step is the update step; that is, recalculating the cluster center for each cluster.

[0073] In the fourth step, the allocation and update steps are repeated until the cluster center no longer changes significantly or the preset number of iterations is reached.

[0074] In this embodiment, the silhouette coefficient can be used to evaluate the selection of the optimal number of clusters K. The silhouette coefficient is a standard for measuring the compactness of data points in each cluster and the degree of separation between clusters. A high silhouette coefficient indicates that the objects within the cluster are very similar while the objects between clusters are different, which helps to evaluate the effectiveness of market segmentation. The formula for calculating the optimal number of clusters K is:

[0075]

[0076] Among them, a(i) is the average distance from data point i to all other data points in its cluster, and b(i) is the average distance from data point i to all points in the nearest cluster.

[0077] In this embodiment, after all clusters are obtained through clustering, descriptive statistics of each cluster can be calculated to determine key features, including cluster center and cluster center standard deviation, which are specifically calculated as follows:

[0078]

[0079] Among them, C k is the set of data points in cluster k, N k For set C k The number of data points in , σ k is the cluster center standard deviation.

[0080] In this embodiment, the improved K-means algorithm can also be used to perform trend analysis based on the labeled data with time tags that change over time. By using a data set containing time tags, it is possible to track the development direction of a specific technology or market trend.

[0081] Step B3, economic situation analysis: Use economic data analysis tools to determine the impact of the macroeconomic environment on emerging industries, including inflation rate, interest rate level, domestic and foreign trade policies, etc., analyze the regression coefficients of various macroeconomics, and determine the positive or negative impact of each key factor on the development of emerging industries, thereby analyzing and determining emerging technologies, market trends, competitive situations and economic situations.

[0082] Use Statsmodels, an open source economic data analysis tool in Python, to analyze the impact of the macroeconomic environment on emerging industries, including inflation rates, interest rates, domestic and foreign trade policies, etc. These factors will have a significant impact on business operations and market development. Statsmodels is an open source statistical and econometric software package in Python that can perform time series analysis, regression analysis, etc. This can help companies analyze the relationship between economic indicators (such as inflation rates, interest rates, etc.) and the development of emerging industries. In the Statsmodels model, by analyzing the regression coefficients of various macroeconomic variables, their positive or negative impact on the development of emerging industries can be determined. The size and significance of the coefficients can help companies determine which economic indicators have the greatest impact on their industries.

[0083] The environmental impact assessment module 30 is used to link environmental factors with corporate strategic planning, and obtain historical environmental data monitored during the industry or product life cycle, the company's internal energy use or waste emission operation data, and data obtained through experiments or simulations during product development or manufacturing. Based on the acquired data, the prediction results of environmental impact indicators at different stages are determined through regression analysis using a machine learning algorithm.

[0084] In this embodiment, the training of the machine learning algorithm and the prediction results of environmental impact indicators at different stages determined based on the trained machine learning algorithm regression analysis are as follows:

[0085] Problem definition and variable selection: In the process of calculating environmental indicators, we first need to determine the environmental indicators that need to be evaluated (such as carbon footprint) and the factors that affect these indicators, that is, characteristic variables, such as energy consumption, production efficiency, etc. The characteristic variables are the input parameters of the machine learning algorithm, and the response variables are the environmental impact indicators that we hope to predict and output through the machine learning algorithm, such as carbon dioxide emissions; the characteristic variables and response variables serve as the input parameters and output of the machine learning algorithm respectively.

[0086] Model construction and parameter estimation: The influencing factors of environmental indicators are estimated through a linear regression model, and the contribution of each influencing factor to the environmental impact indicator is calculated. In this step, the least squares method is used to estimate the model parameters, which echoes the calculation step of the environmental impact assessment model and helps quantify the impact of each influencing factor on the environment.

[0087] Model evaluation and validation: The regression model is trained and evaluated through methods such as cross-validation to ensure its predictive power for new data. This process is consistent with the validation phase in the calculation of environmental indicators, ensuring that the established model can accurately reflect the actual environmental impact.

[0088] Strategy optimization and feedback: Based on the prediction results of regression analysis, enterprises can adjust production strategies to optimize environmental performance. This is consistent with the optimization process in the calculation of environmental indicators. Ultimately, the regression model is updated through real-time data to continuously optimize production and environmental strategies.

[0089] In summary, each step of the linear regression calculation is directly used in the evaluation and calculation process of environmental indicators, ensuring that the model can effectively predict and reduce environmental impacts.

[0090] The following is a specific example to illustrate how the environmental impact assessment module 30 implements the assessment and calculation process of environmental indicators through a regression model. The specific steps are as follows:

[0091] The first step is to define the problem as predicting the carbon dioxide emissions in the production process of the company's products. This emission is regarded as the response variable Y, and the influencing factors (characteristic variables) that affect this emission include energy consumption E, production volume Q, production efficiency η, and the proportion of recycled materials that may be used R. The regression model is expressed as:

[0092] Y=β0+β1E+β2Q+β3η+β4R+ε;

[0093] Among them, β0, β1, β2, β3, and β4 are all model parameters; ε is the error term, representing other influencing factors not explained by the model.

[0094] In the second step, the least squares method is used to estimate the model parameters. The calculation formula is:

[0095]

[0096] Where X is the design matrix, which contains all the predictor variables. is the estimated parameter vector.

[0097] The third step is to use the training set and test set or cross-validation to train and evaluate the model's predictive ability for new data and obtain the trained model based on the convergence condition.

[0098] The fourth step is to use the trained model prediction results to adjust production strategies, such as increasing production efficiency and increasing the proportion of recycled materials to reduce overall carbon emissions. Use real-time data to update the model, continuously adjust the production process, reduce environmental impact, and respond to policy and market changes.

[0099] In this embodiment, a detailed environmental impact assessment report can also be generated based on the forecast assessment results to provide a scientific basis to corporate executives and relevant departments to assist in decision-making and strategic planning.

[0100] In this embodiment, by monitoring environmental policies, resource conditions, and demand for environmentally friendly technologies, enterprises can be helped to actively participate in environmental protection actions in emerging industries and achieve sustainable development goals.

[0101] The multi-dimensional environment perception platform for the development of the company's emerging industries provided in this embodiment has significant advantages in multiple dimensions compared to the existing technology, as follows:

[0102] First, by integrating the macro-environment perception module 10, the industrial environment perception module 20 and the environmental impact assessment module 30, comprehensive consideration and comprehensive analysis of multi-dimensional data and unstructured data are achieved. This comprehensive information coverage and in-depth analysis ensure that enterprises can make more accurate strategic decisions under complex and changing market conditions.

[0103] Second, by adopting advanced business management, data analysis and artificial intelligence technologies, such as PEST analysis and technology trend forecasting, this platform can provide a more comprehensive macro and industrial environment analysis, enabling companies to identify and utilize emerging technologies and market trends, promote the development of innovation and differentiation strategies, and greatly improve the speed and accuracy of data processing. This forward-looking analysis and forecasting technology support helps companies seize technological high ground and enhance their competitiveness in the market.

[0104] Third, in the environmental impact assessment module, through the calculation and report generation of environmental indicators, the present invention helps enterprises identify and utilize key environmental variables and optimize resource allocation. Potential risks and opportunities can be identified in advance and utilized or avoided, thereby optimizing cost-effectiveness and supporting sustainable development strategies.

[0105] In short, through this multi-dimensional environmental perception platform, the company can fully grasp the changes in the external environment, accurately assess the opportunities and challenges of industrial development, and improve the accuracy and flexibility of decision-making.

[0106] Method Embodiment

[0107] According to an embodiment of the present invention, a multi-dimensional environment perception method for the development of emerging industries of a company is provided. Figure 3 As shown, it is a flow chart of the multi-dimensional environment perception method for the development of emerging industries of a company provided in this embodiment. The multi-dimensional environment perception method for the development of emerging industries of a company according to an embodiment of the present invention includes the following steps:

[0108] Step S1, based on the key market dynamics and policies and regulations monitored, determine the macro environment faced by the company's strategic emerging industries, as well as the key factors affecting the development of the company's strategic emerging industries in each macro environment; based on the key factors, determine the policy environment, economic environment, social environment and technological environment faced by the company's strategic emerging industries through macro-environment analysis method.

[0109] In this embodiment, according to the various environments faced by the company's strategic emerging industries determined by analysis, potential risks and opportunities in the external environment can be determined, so as to adjust and formulate the company's operating strategy and long-term plan to maximize the company's competitive advantage and resist external risks. Among them, the key factors affecting the development of the company's strategic emerging industries in the macro environment include market factors, environmental factors and enterprise factors themselves;

[0110] Market factors include market size, market growth rate, potential market demand and other factors; environmental factors include target market characteristics, competitive market conditions, the importance and impact of different environmental factors on the market; and enterprise factors include strengths, weaknesses, opportunities and threats.

[0111] In this embodiment, further, step S1 implements the following steps to adjust and formulate the company's operating strategy and long-term plan:

[0112] Step A1, key market dynamics monitoring: monitor the real-time dynamic data of strategic emerging industry markets, including key indicators such as market size, market growth rate, potential demand, etc., evaluate the strengths, weaknesses, opportunities and threats of companies or products in the market through strategic tools, and then obtain comprehensive reports on market trends and industry development through data analysis;

[0113] Step A2, industrial policy and regulation monitoring, determines the industrial policy environment by tracking the data on changes in relevant policies and regulations on strategic emerging industries in countries and regions, including industrial policy elements, regulatory elements, and policy characteristic elements. Among them, industrial policy elements include industrial support, tax reduction policies, and environmental regulations; regulatory elements include incentive policies, regulatory requirements, and industry entry barriers; policy characteristic elements include policy stability, consistency, and predictability.

[0114] Step A3, integration analysis and strategy formulation; the market dynamics data and market environment data collected in steps A1 and A2 are used to determine the main factors affecting the development of the company's strategic emerging industries through the PEST analysis method as key factors, and based on the key factor analysis, determine the policy environment, economic environment, social environment and technological environment faced by the company's strategic emerging industries, as well as the potential risks and opportunities in the external environment, so as to adjust and formulate the company's operating strategy and long-term plan.

[0115] Step S2, by analyzing the industrial environment faced by the company's strategic emerging industries, determine the key factors in various industrial environments that affect the development of the company's strategic emerging industries, and analyze the market situation faced by the company's strategic emerging industries based on the key factors, where the market situation includes competition situation analysis, technology trend forecast and economic situation analysis.

[0116] Furthermore, step S2 implements the following steps to analyze the market situation faced by the company's strategic emerging industries:

[0117] Step B1, market competition situation analysis; by tracking competitors' trends, including product launches, pricing strategies, market share changes, etc., use complex network analysis methods to analyze the competitive landscape, determine the company's own strengths and weaknesses, and formulate response strategies.

[0118] In this embodiment, the complex network analysis method can be implemented by using the open source Gephi software.

[0119] Step B2, technology trend prediction: Use artificial intelligence algorithms and data mining technology to predict the technology trends of emerging industries, so as to achieve technology research and development and innovation direction planning. The specific steps are as follows:

[0120] First, data about competitors’ product launches, pricing strategies, market shares, etc. are collected. Then, the data is cleaned, incomplete or erroneous data entries are removed, and the data is standardized. Finally, the data is clustered using an improved K-means clustering algorithm to obtain clustering results, thereby achieving technology trend prediction.

[0121] In this embodiment, the improved K-means clustering algorithm is improved on the basis of the original clustering algorithm, and the specific improvements are as follows:

[0122] 1. Use the silhouette coefficient to determine the appropriate number of clusters; the original K-means algorithm requires manual specification of the number of clusters in advance, which may be subjective. The improved algorithm recommends using the silhouette coefficient to evaluate the optimal number of clusters, which can more objectively determine the appropriate K value.

[0123] 2. Calculate cluster centers and determine cluster center characteristics; when calculating cluster centers, the improved algorithm not only gives the coordinate values ​​of cluster centers, but also calculates descriptive statistics such as the standard deviation of cluster centers, which helps to better understand the characteristics of each cluster and identify key customer characteristics or market opportunities.

[0124] 3. Indicating data point affiliation through set indicator variables: The improved algorithm uses adaptive indicator variables to determine the cluster to which each data point belongs, which is important for accurate market positioning and resource allocation.

[0125] Cluster centers represent typical characteristics of different market segments or customer groups, which helps companies identify key customer characteristics or market opportunities. Analyze the statistical characteristics of each cluster, such as cluster center and standard deviation, to identify key characteristics of different customer groups or market segments. Classify each user into the most inappropriate group.

[0126] In a specific embodiment, the core of the improved K-means algorithm is to minimize the sum of the squares of the distances from each point to its cluster center, that is, to optimize the following objective function as follows:

[0127]

[0128] Where n represents the total number of data points;

[0129] K represents the number of clusters, which represents the number of parts into which a market or customer group is divided. In this embodiment, selecting a suitable K value helps enterprises to accurately identify different market segments or customer types, and then design products or services in a targeted manner;

[0130] x i represents the i-th data point, which represents a customer, a transaction, a product unit, or a response in a market survey; these data points contain information that is critical to the company's strategic planning, such as customer purchasing behavior, preferences, or feedback;

[0131] μ k represents the center of the kth cluster, which can be regarded as the typical characteristics or average behavior of the corresponding group or market segment;

[0132] r ik represents an indicator variable. Understanding the characteristics of each center helps identify key customer characteristics or market opportunities. If a data point x i belongs to cluster k, then r ik =1, otherwise r ik =0, this parameter is crucial for determining which customers belong to a specific market segment, enabling enterprises to conduct accurate market positioning and resource allocation, |x i -μ k | 2 is the data point x i to μ k The square of the Euclidean distance.

[0133] The clustering iteration process of the improved K-means algorithm in this embodiment is as follows:

[0134] The first step is initialization; randomly select k data points from the data set as the initial cluster center μ k .

[0135] The second step is the allocation step; for each data point x i, determine the nearest cluster center and update r ik , specifically if k = argmin j |x i -μ k | 2 , then r ik =1, otherwise r ik =0.

[0136] The third step is the update step; that is, recalculating the cluster center for each cluster.

[0137] In the fourth step, the allocation and update steps are repeated until the cluster center no longer changes significantly or the preset number of iterations is reached.

[0138] In this embodiment, the silhouette coefficient can be used to evaluate the selection of the optimal number of clusters K. The silhouette coefficient is a standard for measuring the compactness of data points in each cluster and the degree of separation between clusters. A high silhouette coefficient indicates that the objects within the cluster are very similar while the objects between clusters are different, which helps to evaluate the effectiveness of market segmentation. The formula for calculating the optimal number of clusters K is:

[0139]

[0140] Among them, a(i) is the average distance from data point i to all other data points in its cluster, and b(i) is the average distance from data point i to all points in the nearest cluster.

[0141] In this embodiment, after all clusters are obtained through clustering, descriptive statistics of each cluster can be calculated to determine key features, including cluster center and cluster center standard deviation, which are specifically calculated as follows:

[0142]

[0143] Among them, C k is the set of data points in cluster k, N k For set C k The number of data points in , σ k is the cluster center standard deviation.

[0144] In this embodiment, the improved K-means algorithm can also be used to perform trend analysis based on the labeled data with time tags that change over time. By using a data set containing time tags, it is possible to track the development direction of a specific technology or market trend.

[0145] Step B3, economic situation analysis: Use economic data analysis tools to determine the impact of the macroeconomic environment on emerging industries, including inflation rate, interest rate level, domestic and foreign trade policies, etc., analyze the regression coefficients of various macroeconomics, and determine the positive or negative impact of each key factor on the development of emerging industries, thereby analyzing and determining emerging technologies, market trends, competitive situations and economic situations.

[0146] Step S3, associate environmental factors with corporate strategic planning, and obtain historical environmental data from environmental monitoring during the industry or product life cycle, the company's internal energy use or waste emission operation data, and data obtained through experiments or simulations during product development or manufacturing. Based on the obtained data, the prediction results of environmental impact indicators at different stages are determined through regression analysis using a machine learning algorithm.

[0147] In this embodiment, the training of the machine learning algorithm and the prediction results of environmental impact indicators at different stages determined based on the trained machine learning algorithm regression analysis are as follows:

[0148] Problem definition and variable selection: In the process of calculating environmental indicators, we first need to determine the environmental indicators that need to be evaluated (such as carbon footprint) and the factors that affect these indicators, that is, characteristic variables, such as energy consumption, production efficiency, etc. The characteristic variables are the input parameters of the machine learning algorithm, and the response variables are the environmental impact indicators that we hope to predict and output through the machine learning algorithm, such as carbon dioxide emissions; the characteristic variables and response variables serve as the input parameters and output of the machine learning algorithm respectively.

[0149] Model construction and parameter estimation: The influencing factors of environmental indicators are estimated through a linear regression model, and the contribution of each influencing factor to the environmental impact indicator is calculated. In this step, the least squares method is used to estimate the model parameters, which echoes the calculation step of the environmental impact assessment model and helps quantify the impact of each influencing factor on the environment.

[0150] Model evaluation and validation: The regression model is trained and evaluated through methods such as cross-validation to ensure its predictive power for new data. This process is consistent with the validation phase in the calculation of environmental indicators, ensuring that the established model can accurately reflect the actual environmental impact.

[0151] Strategy optimization and feedback: Based on the prediction results of regression analysis, enterprises can adjust production strategies to optimize environmental performance. This is consistent with the optimization process in the calculation of environmental indicators. Ultimately, the regression model is updated through real-time data to continuously optimize production and environmental strategies.

[0152] In summary, each step of the linear regression calculation is directly used in the evaluation and calculation process of environmental indicators, ensuring that the model can effectively predict and reduce environmental impacts.

[0153] The embodiment of the present invention is a method embodiment corresponding to the above-mentioned platform embodiment. The specific operations of each processing step can be understood by referring to the description of the platform module embodiment, which will not be repeated here.

[0154] like Figure 4 As shown, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the multi-dimensional environmental perception method for the development of the company's emerging industries in the above-mentioned embodiment is implemented.

[0155] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the multi-dimensional environmental perception method for the development of the company's emerging industries in the above-mentioned embodiment is implemented; or when the computer program is executed by a processor, the multi-dimensional environmental perception method for the development of the company's emerging industries in the above-mentioned embodiment is implemented.

[0156] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0157] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0158] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and the contents not described in detail in the specification of the present invention belong to the common knowledge of those skilled in the art.

Claims

1. A multi-dimensional environment perception platform for the development of emerging industries of the company, characterized by: include: The macro-environment perception module is used to determine the macro-environment faced by the company's strategic emerging industries and the key factors affecting the development of the company's strategic emerging industries in each macro-environment based on the key market dynamics and policies and regulations monitored. Based on the key factors, the macro-environment analysis method is used to analyze and determine the policy environment, economic environment, social environment and technological environment faced by the company's strategic emerging industries, as well as the potential risks and opportunities in the external environment, so as to adjust and formulate the company's operating strategy and long-term plan. Among them, the key factors affecting the development of the company's strategic emerging industries in the macro-environment include market factors, environmental factors and enterprise factors themselves; The industrial environment perception module is used to analyze the industrial environment faced by the company's strategic emerging industries, determine the key factors in various industrial environments that affect the development of the company's strategic emerging industries, and analyze the market situation faced by the company's strategic emerging industries based on the key factors. The market situation includes competition situation analysis, technology trend forecast and economic situation analysis; the key factors in the industrial environment that affect the development of the company's strategic emerging industries include industrial policy factors, regulatory factors, and policy characteristic factors; and The environmental impact assessment module is used to link environmental factors with corporate strategic planning, and obtain historical environmental data monitored during the industry or product life cycle, the company's internal energy use or waste emission operation data, and data obtained through experiments or simulations during product development or manufacturing. Based on the acquired data, the prediction results of environmental impact indicators at different stages are determined through regression analysis using machine learning algorithms.

2. The multi-dimensional environment perception platform for the development of emerging industries of the company as claimed in claim 1 is characterized in that: Furthermore, the macro-environment perception module is configured to perform the following steps to adjust and formulate the company's operating strategy and long-term plan. The specific steps are as follows: A1, key market dynamics monitoring; monitor the real-time dynamic data of strategic emerging industry markets, including market size, market growth rate and key indicators of potential demand, and evaluate the strengths, weaknesses, opportunities and threats of companies or products in the market through strategic tools; A2, industrial policy and regulation monitoring, by tracking the data on changes in national and regional policies and regulations on strategic emerging industries, determine the industrial policy environment, including industrial policy elements, regulatory elements, and policy characteristic elements. Among them, industrial policy elements include industrial support, tax reduction policies, and environmental regulations; regulatory elements include incentive policies, regulatory requirements, and industry entry barriers; and policy characteristic elements include policy stability, consistency, and predictability; A3, integrated analysis and strategy formulation; the market dynamics data and market environment data collected in steps A1 and A2 are used to determine the main factors affecting the development of the company's strategic emerging industries through the PEST analysis method as key factors, and based on the key factor analysis, the policy environment, economic environment, social environment and technological environment faced by the company's strategic emerging industries, as well as the potential risks and opportunities in the external environment, so as to adjust and formulate the company's operating strategy and long-term plan.

3. The multi-dimensional environment perception platform for the development of emerging industries of the company as claimed in claim 1 is characterized in that: Furthermore, the industrial environment perception module is configured to perform the following steps to analyze the market situation faced by the company's strategic emerging industries. The specific steps are as follows: Step B1, market competition situation analysis: by tracking competitors’ trends, including product launches, pricing strategies, and market share changes, use complex network analysis methods to analyze the competition landscape, identify the company’s own strengths and weaknesses, and develop response strategies; Step B2, technology trend prediction; Use the improved K-means algorithm to predict technology trends in emerging industries based on competitor data on product launches, pricing strategies, and market share; Step B3, economic situation analysis: Use economic data analysis tools to determine the impact of the macroeconomic environment on emerging industries, including inflation rate, interest rate level, domestic and foreign trade policies, and analyze the regression coefficients of various macroeconomics to determine the positive or negative impact of each key factor on the development of emerging industries, thereby determining emerging technologies and market trends, competitive situations and economic situations.

4. The multi-dimensional environment perception platform for the development of emerging industries of the company as claimed in claim 3 is characterized in that: The improved K-means clustering algorithm is improved on the basis of the original clustering algorithm. The specific improvements are as follows: 1) Use the silhouette coefficient to determine the appropriate number of clusters; 2) Calculate cluster centers and determine cluster center characteristics; 3) Indicate the affiliation of data points by setting indicator variables.

5. The multi-dimensional environment perception platform for the development of emerging industries of the company as claimed in claim 4 is characterized in that: The clustering iteration process of the improved K-means algorithm is as follows: The first step is initialization; randomly select k data points from the data set as the initial cluster center μ k ; The second step is the allocation step; for each data point x i , determine the nearest cluster center and update r ik , that is, if k = argmin j x i -μ k 2 , then r ik =1, otherwise r ik =0; The third step is the update step, that is, recalculating the cluster center for each cluster; In the fourth step, the allocation and update steps are repeated until the cluster center no longer changes significantly or the preset number of iterations is reached.

6. The multi-dimensional environment perception platform for the development of emerging industries of the company as claimed in claim 5 is characterized in that: The specific calculation of using the silhouette coefficient to determine the appropriate number of clusters is as follows: Where a(i) is the average distance from data point i to all other data points in its cluster, and b(i) is the average distance from data point i to all points in the nearest cluster; The calculation of cluster center and determination of cluster center characteristics are as follows: Among them, x i represents the i-th data point, μ k represents the center of the kth cluster, C k is the set of data points in cluster k, N k For set C k The number of data points in , σ k is the cluster center standard deviation.

7. A multi-dimensional environmental perception method for the development of emerging industries of a company, characterized in that: Includes steps: According to the key market dynamics and policies and regulations monitored, determine the macro environment faced by the company's strategic emerging industries, as well as the key factors in each macro environment that affect the development of the company's strategic emerging industries. Based on the key factors, use the macro environment analysis method to analyze and determine the policy environment, economic environment, social environment and technological environment faced by the company's strategic emerging industries, as well as the potential risks and opportunities in the external environment, so as to adjust and formulate the company's operating strategy and long-term plan. Among them, the key factors in the macro environment that affect the development of the company's strategic emerging industries include market factors, environmental factors and enterprise factors themselves; By analyzing the industrial environment faced by the company's strategic emerging industries, determine the key factors in each industrial environment that affect the development of the company's strategic emerging industries, and analyze the market situation faced by the company's strategic emerging industries based on the key factors. The market situation includes competition situation analysis, technology trend forecast and economic situation analysis; the key factors in the industrial environment that affect the development of the company's strategic emerging industries include industrial policy factors, regulatory factors, and policy characteristics factors; and Environmental factors are projected onto each link of the industrial chain, and historical environmental data from environmental monitoring during the life cycle of the industry or product, the company's internal energy usage or waste emission operation data, and data obtained through experiments or simulations during product development or manufacturing are obtained. Based on the acquired data, regression analysis using machine learning algorithms is used to determine the prediction results of environmental impact indicators at different stages.

8. The multi-dimensional environment perception method for the development of emerging industries of a company as claimed in claim 7, characterized in that: Furthermore, the macro-environment analysis method is used to analyze and determine the policy environment, economic environment, social environment and technological environment faced by the company's strategic emerging industries, as well as the potential risks and opportunities in the external environment, so as to adjust and formulate the company's operating strategy and long-term plan. The specific steps are as follows: A1, key market dynamics monitoring; monitor the real-time dynamic data of strategic emerging industry markets, including market size, market growth rate and key indicators of potential demand, and evaluate the strengths, weaknesses, opportunities and threats of companies or products in the market through strategic tools; A2, industrial policy and regulation monitoring, by tracking the data on changes in national and regional policies and regulations on strategic emerging industries, determine the industrial policy environment, including industrial policy elements, regulatory elements, and policy characteristic elements. Among them, industrial policy elements include industrial support, tax reduction policies, and environmental regulations; regulatory elements include incentive policies, regulatory requirements, and industry entry barriers; and policy characteristic elements include policy stability, consistency, and predictability; A3, integrated analysis and strategy formulation; the market dynamics data and market environment data collected in steps A1 and A2 are used to determine the main factors affecting the development of the company's strategic emerging industries through the PEST analysis method as key factors, and based on the key factor analysis, the policy environment, economic environment, social environment and technological environment faced by the company's strategic emerging industries, as well as the potential risks and opportunities in the external environment, so as to adjust and formulate the company's operating strategy and long-term plan.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the multi-dimensional environment perception method for the development of emerging industries of the company as described in claim 7 or 8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the multi-dimensional environment perception method for the development of emerging industries of the company as described in claim 7 or 8 is implemented.

Images