Concrete work robot industry size prediction method, system, device, and medium

Abstract

The application discloses a concrete operation robot industry scale prediction method, system, equipment and medium, relates to the computer integrated manufacturing technical field, and includes collecting and processing related data of the concrete operation robot industry; a comprehensive model of the concrete operation robot industry is constructed based on CIM technology; data analysis and prediction are carried out on the comprehensive model, and the prediction result is verified and corrected. The method improves the data quality, ensures the accuracy and timeliness of the model input data, makes the market trend prediction adapt to the rapidly changing industry environment, ensures that the model can comprehensively reflect the complex dynamics of market structure, competition pattern and supply and demand relationship, improves the accuracy of long-term trend prediction, realizes dynamic analysis of market structure, can adapt to industry changes, provides more forward market insight ability, and helps enterprises to arrange future technology development direction in advance.

Description

Technical Field

[0001] This invention relates to the field of computer integrated manufacturing technology, specifically to a method, system, equipment, and medium for predicting the industrial scale of concrete operation robots. Background Technology

[0002] With the increasing demands for automation and intelligence in the construction industry, concrete operation robots have gradually become an important part of modern construction. These robots can significantly improve construction efficiency, reduce labor costs, and effectively ensure construction accuracy and safety. At the same time, industry scale forecasting has become one of the key technologies supporting the development of this industry. However, due to the rapid technological development of the concrete operation robot industry and the constantly changing market demand, traditional industry scale forecasting methods are no longer able to meet the growing demand. Current forecasting methods mostly rely on historical data and empirical analysis, but these methods are poorly adaptable to dynamic market changes and cannot accurately capture the complex relationship between technological progress and market changes. With the continuous development of computer integrated manufacturing (CIM) technology, big data analysis, and artificial intelligence technology, industry scale forecasting based on advanced technologies is gradually becoming an important means to improve forecast accuracy and decision-making efficiency.

[0003] Existing industry scale forecasting technologies in the concrete operation robot field generally rely on historical data and empirical analysis. These methods typically make predictions based on past sales data or market trends. However, they cannot accurately cope with the impact of market demand fluctuations, technological advancements, and changes in the external environment. Due to rapid technological updates, traditional methods mainly rely on linear or simple statistical models for forecasting, lacking adaptability to complex market dynamics, resulting in poor accuracy and foresight in the forecast results. Existing methods mainly depend on experience-based judgments and cannot fully utilize modern technological advancements, especially when dealing with large and complex data volumes. The computational and processing capabilities of traditional forecasting models are extremely limited. Existing technologies fail to fully utilize advanced technologies such as artificial intelligence, big data analysis, and machine learning. The construction robot industry encompasses numerous factors, such as market demand and technological development, which interact in a complex manner. Traditional forecasting methods often fail to comprehensively utilize this complex information and are unable to conduct in-depth data mining and modeling across different dimensions. This results in inaccurate and unreal-time predictions of future market changes. Existing industry scale forecasting methods lack flexibility and struggle to respond quickly to market and technological shifts. As the concrete construction robot industry rapidly develops, its scale is constantly changing. Traditional methods often fail to adjust forecasting models in a timely manner, leading to outdated predictions that are insufficient to provide effective support for decision-makers. Therefore, new forecasting methods are needed that can better utilize modern technology to improve the accuracy, reliability, and real-time performance of forecasts, enabling them to better adapt to the rapidly changing market environment. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by this invention is that existing technologies for predicting the scale of the concrete operation robot industry rely on historical data and empirical analysis, lack multi-dimensional data processing capabilities, fail to effectively utilize advanced technologies, and address the issue of how to use CIM technology, big data analysis, and deep learning algorithms to construct a comprehensive, accurate, and flexible industry scale prediction model.

[0006] To address the aforementioned technical problems, this invention provides the following technical solution: a method for predicting the scale of the concrete operation robot industry, comprising collecting and processing relevant data on the concrete operation robot industry; constructing a comprehensive model of the concrete operation robot industry based on CIM technology; performing data analysis and prediction on the comprehensive model, and verifying and correcting the prediction results; the comprehensive model includes analysis and modeling based on market structure, competitive landscape, and supply and demand relationship; during the data analysis and prediction process, constructing a prediction model of market demand, competitive landscape, and technological development trends, and predicting future trends based on time series and long short-term memory networks.

[0007] As a preferred embodiment of the concrete operation robot industry scale prediction method described in this invention, the comprehensive model includes: modeling the market structure, modeling the competitive landscape, modeling the supply and demand relationship, extracting key variables from the market structure, competitive landscape, and supply and demand relationship, establishing a correlation model between different influencing factors, and comprehensively analyzing the future development trend of the concrete operation robot industry scale.

[0008] As a preferred embodiment of the concrete operation robot industry scale prediction method described in this invention, the market structure modeling includes identifying industry players, concrete operation robot manufacturers, core component suppliers, end-user companies, and industry regulatory agencies, and defining the interaction relationships between these players based on market share, technological capabilities, product iteration speed, and business model classification, thereby forming a hierarchical market network.

[0009] As a preferred embodiment of the concrete operation robot industry scale prediction method described in this invention, the modeling of the competitive landscape includes: constructing a market competition landscape model for concrete operation robots, analyzing the competitive relationships among major companies in the industry, calculating the market concentration, measuring the degree of market competition using the Herfindahl-Hirschman index, establishing a state transition matrix based on a Markov chain, deducing the changing trends of companies' positions in the market, and constructing the state transition matrix.

[0010] As a preferred embodiment of the concrete operation robot industry scale prediction method described in this invention, the modeling of supply and demand relationship includes: constructing a supply and demand relationship model for the concrete operation robot industry; establishing a dynamic supply and demand balance model based on the total industry capacity, the supply chain status of core components, the capacity expansion plans of production enterprises, and the demand of end markets; and predicting future market demand trends through time series analysis.

[0011] As a preferred embodiment of the concrete operation robot industry scale prediction method described in this invention, the establishment of a correlation model among different influencing factors includes: extracting key variables from market structure, competitive landscape and supply and demand relationship models; using principal component analysis to screen highly correlated variables; and quantifying the influence paths between variables through structural equation modeling to form a multi-level causal relationship network.

[0012] As a preferred embodiment of the concrete operation robot industry scale prediction method described in this invention, the comprehensive analysis of the future development trend of the concrete operation robot industry scale includes: establishing a mathematical model for predicting the concrete operation robot industry scale, integrating market structure, competitive landscape, supply and demand relationship and correlation model, constructing an industry scale prediction framework based on computer integrated manufacturing technology, and calculating the future development trend of the concrete operation robot industry scale through computer simulation and data iterative optimization.

[0013] As a preferred embodiment of the concrete operation robot industry scale prediction method described in this invention, the data analysis and prediction includes: constructing a concrete operation robot market demand prediction model, obtaining historical sales data, engineering project procurement data, construction industry investment data, and government policy data of the concrete operation robot market, standardizing the data, using time series decomposition method to extract the long-term trend, periodic fluctuations, and random fluctuations of market demand, screening key influencing factors, and using a long short-term memory network model to predict future market demand.

[0014] A predictive model for the competitive landscape of the concrete operation robot industry is constructed. Market share, product technical parameters, construction project bidding data and patent layout data of enterprises in the industry are obtained. A competitive feature matrix is ​​established, and a Markov chain model is used to analyze changes in market competition status and calculate the state transition probability of enterprises under different market environments.

[0015] This paper constructs a predictive model for the technological development trend of concrete operation robots. It employs a topic modeling approach to cluster technical texts in the field of concrete operation robots, calculates the distribution of technical topics based on a probabilistic topic model, identifies the core technological directions of the current industry, calculates a patent citation network, constructs the technological evolution path of concrete operation robots, and identifies technological development trends by calculating the similarity between technological fields based on graph neural networks. It uses time series regression to analyze the development speed of each technological field, combines technology maturity analysis to determine the development stage of key technologies for concrete operation robots, and predicts future technology iteration cycles. Finally, it combines market demand prediction models and competitive landscape prediction models to analyze the impact of technological innovation on the market demand and corporate competitiveness of concrete operation robots, and infers the development trend of the industry scale.

[0016] As a preferred embodiment of the concrete operation robot industry scale prediction method described in this invention, the prediction results are verified and corrected by comparing them with the actual market situation to verify the accuracy of the prediction results, and by adjusting the model parameters, optimizing the algorithm, and updating the data according to the actual situation.

[0017] Another objective of this invention is to provide a concrete operation robot industry scale prediction system, which can construct a comprehensive model of the concrete operation robot industry based on CIM technology, thus solving the problems of current industry scale prediction technologies that rely on a single data source and lack dynamic market analysis capabilities.

[0018] As a preferred embodiment of the concrete operation robot industry scale prediction system of the present invention, it includes: a data processing module, a model building module, and an analysis, prediction, and verification module; the data processing module includes a data collection module and a data processing module. The data collection module collects key data related to the concrete operation robot industry, and the data integration module integrates data from different sources; the model building module includes a comprehensive model building module and a correlation model building module. The comprehensive model building module is used to build a comprehensive model of the concrete operation robot industry based on CIM technology, modeling market structure, competitive landscape, and supply and demand relationships. The correlation model building module is used to establish correlation models between various influencing factors and comprehensively analyze the future development trend of the concrete operation robot industry scale; the analysis, prediction, and verification module includes an analysis and prediction module and a verification and correction module. The analysis and prediction module performs data analysis and prediction on the comprehensive model, and the verification and correction module verifies and corrects the prediction results.

[0019] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program as a step in implementing a method for predicting the industrial scale of concrete operation robots.

[0020] A computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of a method for predicting the industrial scale of concrete operation robots.

[0021] The beneficial effects of this invention are as follows: The concrete operation robot industry scale prediction method provided by this invention collects and processes relevant data on the concrete operation robot industry, improving data quality and ensuring the accuracy and timeliness of the model input data. This allows market trend prediction to adapt to the rapidly changing industry environment. Based on CIM technology, a comprehensive model of the concrete operation robot industry is constructed, ensuring that the model can comprehensively reflect the complex dynamics of market structure, competitive landscape, and supply and demand. Data analysis and prediction are performed on the comprehensive model, and the prediction results are verified and corrected, improving the accuracy of long-term trend prediction. This enables dynamic analysis of market structure, adapts to industry changes, provides more forward-looking market insights, and helps enterprises plan ahead for future technology development. This invention achieves better results in data integration accuracy, industry dynamic adaptability, and market prediction accuracy. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 The overall flowchart of the concrete operation robot industry scale prediction method provided in the first embodiment of the present invention is shown.

[0024] Figure 2 The demand growth index trend chart of the concrete operation robot industry scale prediction method provided in the second embodiment of the present invention.

[0025] Figure 3 A future market demand forecast diagram for the concrete operation robot industry scale forecasting method provided in the second embodiment of the present invention.

[0026] Figure 4 The overall flowchart of the concrete operation robot industry scale prediction system provided in the third embodiment of the present invention. Detailed Implementation

[0027] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0028] Example 1, referring to Figure 1 As an embodiment of the present invention, a method for predicting the industry scale of concrete operation robots is provided, including:

[0029] S1: Collect and process relevant data on the concrete operation robot industry.

[0030] Furthermore, relevant data, including market sales data, technological development trends, economic environment, and competitor information related to the concrete operation robot industry, are integrated from public databases, industry reports, and internal corporate data.

[0031] It should also be noted that a preferred approach to integrating data from different sources includes standardizing the collected data, expressed as:

[0032] ;

[0033] in, The standardized data matrix ensures that data from different sources can be modeled on the same scale. The original data matrix contains market sales data, technological development data, economic environment data, and competitor information. The mean of the original data. This represents the standard deviation of the original data, used to normalize the scale of different variables. Market sales data includes annual sales volume and market share; technology development trend data includes patent growth rate and R&D investment; economic environment data includes GDP growth rate, construction industry investment, and government subsidies; competitor information data includes market share and market concentration.

[0034] It should be noted that by collecting and integrating multi-dimensional data on market sales, technological development trends, economic environment, and competitor information in the concrete operation robot industry, the comprehensiveness and accuracy of data sources are ensured. This step improves the accuracy and reliability of industry scale forecasting. Data integration not only provides a comprehensive market view but also enables subsequent models to be built with the support of multiple factors, avoiding the limitations of relying on a single data source. This provides a higher level of reference for subsequent supply and demand relationship modeling and market demand forecasting. By using publicly available databases, industry reports, and internal enterprise data, the timeliness and comprehensiveness of the data are improved, making subsequent forecasts more consistent with reality. By comprehensively collecting and processing industry data, the multi-dimensionality, accuracy, and timeliness of the model are ensured. It is not limited to the analysis of historical sales data but integrates information from multiple levels, such as macro policies and technological trends, making the industry forecast results more accurate and forward-looking.

[0035] S2: A comprehensive model for the concrete operation robot industry based on CIM technology.

[0036] Furthermore, a comprehensive model is developed, including modeling the market structure, the competitive landscape, and the supply and demand relationship. Key variables in the market structure, competitive landscape, and supply and demand relationship are extracted, and a correlation model between different influencing factors is established to comprehensively analyze the future development trend of the concrete operation robot industry.

[0037] It should be noted that modeling the market structure includes identifying industry players, such as concrete operation robot manufacturers, core component suppliers, end-user companies, and industry regulatory agencies. Based on market share, technological capabilities, product iteration speed, and business model classification, the interaction relationships between these players are defined to form a hierarchical market network.

[0038] It should also be noted that modeling the competitive landscape includes constructing a market competition landscape model for concrete operation robots, analyzing the competitive relationships among major companies in the industry, calculating market concentration, measuring the degree of market competition using the Herfindahl-Hirschman index, and establishing a state transition matrix based on Markov chains to deduce the changing trends of companies' positions in the market and construct the state transition matrix.

[0039] It should also be noted that a preferred approach to constructing the state transition matrix includes: determining the market competition status of concrete operation robot companies, including market leaders, growth companies, stable companies, declining companies, and companies exiting the market; collecting historical market data of the industry, statistically analyzing the frequency of companies transitioning from one market competition status to another, and constructing the state transition matrix based on conditional probability; optimizing the parameters of the state transition matrix using the maximum likelihood estimation method to ensure that the matrix satisfies the characteristics of a Markov stochastic process; and combining time series regression analysis to construct a state transition prediction model based on changes in the market environment, and to deduce the evolution trend of the future market competition landscape.

[0040] It should also be noted that modeling the supply and demand relationship includes constructing a supply and demand model for the concrete operation robot industry. Based on the total industry capacity, the supply chain status of core components, the capacity expansion plans of production enterprises, and the demand of end markets, a dynamic supply and demand balance model is established, and future market demand trends are predicted through time series analysis.

[0041] It should also be noted that a preferred approach to time series analysis includes selecting historical market demand data, such as annual sales volume of concrete operation robots, new industry orders, and equipment procurement intentions of construction companies, and performing a stationarity test on the data. When the data stationarity test is passed, an autoregressive moving average model is used to calculate the optimal lag order, construct an autoregressive prediction equation based on historical demand, and optimize the model parameters using the Bayesian information criterion. When the data has a nonlinear trend or long-term dependency, a long short-term memory network model is used to construct a recurrent neural network with a variable time step, define the input layer, hidden layer, and output layer, select activation functions and optimization algorithms to improve prediction accuracy, and use the sliding window method to evaluate the model prediction error. Based on the root mean square of the prediction error, the model's hyperparameters are adjusted.

[0042] It should also be noted that establishing a correlation model between different influencing factors involves extracting key variables from market structure, competitive landscape, and supply and demand relationship models, using principal component analysis to screen highly correlated variables, and quantifying the influence paths between variables through structural equation modeling to form a multi-level causal relationship network.

[0043] It should also be noted that a preferred approach to principal component analysis includes: constructing an original data matrix containing variables such as market demand for concrete operation robots, technological innovation speed, industry policies, and the economic environment; standardizing the data to eliminate the influence of different dimensions between variables; calculating the variable covariance matrix; extracting principal component vectors based on eigenvalue decomposition and determining the contribution rate of each principal component; selecting the number of principal components based on the cumulative variance contribution rate and calculating the score coefficient of each principal component; optimizing the principal component loading matrix using the maximum variance rotation method; and combining it with structural equation modeling to construct causal relationship paths between various influencing factors and quantify the impact of changes in industry scale.

[0044] It should also be noted that the comprehensive analysis of the future development trend of the concrete operation robot industry includes establishing a mathematical model for predicting the scale of the concrete operation robot industry, integrating market structure, competitive landscape, supply and demand relationship and correlation models, constructing an industry scale prediction framework based on computer integrated manufacturing technology, and calculating the future development trend of the concrete operation robot industry scale through computer simulation and data iterative optimization.

[0045] It should also be noted that the calculation of market concentration... and supply-demand ratio Constructing a market structure index , is represented as:

[0046] ;

[0047] ;

[0048] ;

[0049] in, It serves as a market structure index, measuring the degree of market competition. The weight of the Herfindahl-Hirschman index in the market structure; This is a market concentration index; a higher value indicates a more concentrated market. For enterprises market share The weight of the enterprise's market share index in the market structure; For enterprises Market share in the industry The total number of firms in the market. For supply and demand ratio Weight in the market structure; The market supply-demand ratio reflects the degree of market supply-demand balance. Total market supply; This represents the total market demand.

[0050] The specific formulas for constructing a state transition prediction model based on changes in the market environment include:

[0051] ;

[0052] ;

[0053] in, For the future Distribution of enterprise market status at any given moment; Current time Distribution of enterprise market status at any given time This is the state transition matrix, describing the probability that a firm will transition from one market state to another. This is the market driver influence coefficient, adjusting for the impact of the economic environment and technological innovation on market conditions. Economic environmental factors (such as GDP growth rate). This is the technology innovation index (patent growth rate, R&D investment, etc.). For enterprises to understand the market situation Become a state The transition probability; From the state of historical data statistics Become a state Number of times, Indicates the company's market status Migrate to different states The total number of times.

[0054] It should also be noted that a specific formula for establishing a dynamic supply and demand balance model includes:

[0055] Total market demand Represented as:

[0056]

[0057] Total market supply Represented as:

[0058]

[0059] Among the demand-side variables, This represents the total market demand. This represents the current GDP growth rate. For product price, This represents the market volatility error term; among the supply-side variables, For market supply, The core component supply index For corporate investment index; , , These are the weight parameters for the demand forecasting model; , , To provide weight parameters for the supply prediction model; This is the error term, reflecting the unpredictable fluctuations in market demand.

[0060] The optimal lag order, calculated using the Autoregressive Moving Average (ARIMA) model, is expressed as follows:

[0061] ;

[0062] in, ,..., Represents the autoregressive coefficient. ,..., This represents the moving average coefficient. Since market demand may exhibit long-term dependence, LSTM networks are used to analyze non-linear demand trends.

[0063] ;

[0064] ;

[0065] in, Network weights; This is the hidden state of the LSTM; For bias terms , As economic environmental variables and technological innovation variables, This is a forecast of future market demand.

[0066] In the principal component analysis method for establishing correlation models among different influencing factors, the correlations include market structure, competitive landscape, and supply and demand relationships. The original data matrix for the correlation model is constructed as follows:

[0067] ;

[0068] in, This is the original data matrix for the correlation model, containing key variables in market structure, competitive landscape, and supply and demand relationships. The forecast for future market demand is derived from supply and demand modeling. The product price is derived from supply and demand relationship modeling.

[0069] In the correlation model, the standardized representation of data is as follows:

[0070] ;

[0071] in, In the correlation model, the standardized data matrix eliminates the influence of different dimensions between variables; This represents the mean of each column of data in the correlation model. This represents the standard deviation of each column of data in the correlation model.

[0072] Calculate the covariance matrix of the correlation model

[0073] ;

[0074] in, In a correlation model, the covariance matrix measures the correlation between variables. This represents the number of samples in the correlation model. For the standardized data matrix in the correlation model The mean vector.

[0075] The eigenvalues ​​and eigenvectors are calculated as follows:

[0076]

[0077] in, In the correlation model, the feature vector matrix represents the principal component directions of the data; This is the diagonalized eigenvalue matrix in the correlation model, representing the contribution of each principal component.

[0078] The principal component selection is represented as:

[0079] ;

[0080] in, In the correlation model, represents the variance information content of each principal component; 'The number of principal components selected in the correlation model, such that the cumulative variance contribution rate is greater than...' Calculate the principal component scores in the correlation model:

[0081] ;

[0082] in, For the first Principal component scores; The eigenvector weights represent the standardized variables. Contribution to principal components For standardized variables, This represents the total number of firms in the market.

[0083] Structural equation modeling (SEM) quantifies the influence paths between variables:

[0084] ;

[0085] in, Industry size forecast These are path coefficients, representing the contribution of each variable to the industry scale. This is the error term, representing unpredictable external factors.

[0086] It should also be noted that CIM (Computer Integrated Manufacturing) technology encompasses all aspects of manufacturing, from product design, production planning, process control to logistics management. Its goal is to improve production efficiency, reduce manufacturing costs, and enhance enterprises' adaptability to market changes through information technology, automation, and intelligentization. It relies on computer technology for data integration and production management optimization, and can acquire, analyze, and provide feedback on information in real time during the manufacturing process, thereby achieving efficient collaborative manufacturing. CIM technology constructs a comprehensive model covering market structure, competitive landscape, and supply and demand relationships, establishing a correlation model between influencing factors. Through comprehensive modeling of all levels of the industry, it can structure and systematize the complex market environment and identify different market players. The model identifies the interactions between entities, such as manufacturers, suppliers, and users. This not only helps clarify the roles of each entity within the industry but also clearly demonstrates the hierarchical nature of the market structure, making the predictive model more consistent with the actual operational rules of the industry. By establishing a comprehensive model, the impact of various internal and external factors on the market can be accurately identified. In particular, the market structure and competitive landscape model can better reflect potential changes in industry development. This not only improves the accuracy of the model but also enhances the ability to predict future market trends. For example, through state transition matrices and Markov chain analysis, it is possible to deeply predict changes in the position of enterprises in the market, thereby providing a more accurate basis for predicting industry scale, which is more in-depth and dynamically adaptable than traditional simple linear models.

[0087] S3: Perform data analysis and prediction on the comprehensive model, and verify and correct the prediction results.

[0088] Furthermore, data analysis and forecasting include building a market demand forecasting model for concrete operation robots, obtaining historical sales data, engineering project procurement data, construction industry investment data, and government policy data for the concrete operation robot market, standardizing the data, using time series decomposition methods to extract long-term trends, periodic fluctuations, and random fluctuations in market demand, screening key influencing factors, and using long short-term memory network models to predict future market demand.

[0089] It should also be noted that a preferred approach for constructing a Long Short-Term Memory (LSTM) network model includes: setting the time series window size; constructing an input sequence with variable time steps based on the sliding window method; and normalizing the sequence data; designing the LSM network structure, defining the input layer, hidden layer, and output layer; using recursive neural units to construct memory gates, input gates, and forget gates to control information transfer between time steps; setting the loss function as the mean squared error function; using an adaptive gradient optimization algorithm to adjust the network weights; optimizing the time step and hidden layer parameters through iterative training; evaluating the prediction error using a sliding window test set; and adaptively adjusting the hyperparameters based on the root mean square error calculation.

[0090] A predictive model for the competitive landscape of the concrete operation robot industry is constructed. Market share, product technical parameters, construction project bidding data and patent layout data of enterprises in the industry are obtained. A competitive feature matrix is ​​established, and a Markov chain model is used to analyze changes in market competition status and calculate the state transition probability of enterprises under different market environments.

[0091] It should also be noted that a preferred approach to analyzing changes in market competition using a Markov chain model includes: setting a set of market competition states for concrete robot companies, including market dominance, growth, stability, decline, and exit states; statistically analyzing the market state distribution of each company at different times; calculating the transition frequency of companies under different market states; establishing a state transition matrix based on historical data; and calculating the state transition probability using the maximum likelihood estimation method; incorporating market dynamics factors and introducing the time dependence of state transitions to construct a time-variable Markov chain model; simulating future changes in competitive states using a multi-step prediction method; calculating the market share trends of each competing company under different market environments; and deducing the evolution of the competitive landscape of the concrete robot market.

[0092] This paper constructs a predictive model for the technological development trend of concrete operation robots. It employs a topic modeling approach to cluster technical texts in the field of concrete operation robots, calculates the distribution of technical topics based on a probabilistic topic model, identifies the core technological directions of the current industry, calculates a patent citation network, constructs the technological evolution path of concrete operation robots, and identifies technological development trends by calculating the similarity between technological fields based on graph neural networks. It uses time series regression to analyze the development speed of each technological field, combines technology maturity analysis to determine the development stage of key technologies for concrete operation robots, and predicts future technology iteration cycles. Finally, it combines market demand prediction models and competitive landscape prediction models to analyze the impact of technological innovation on the market demand and corporate competitiveness of concrete operation robots, and infers the development trend of the industry scale.

[0093] It should also be noted that the prediction results need to be verified and corrected, including verifying the accuracy of the prediction results by comparing them with the actual market situation, and adjusting the model parameters, optimizing the algorithm, and updating the data according to the actual situation.

[0094] It should also be noted that in the process of data analysis and forecasting of the comprehensive model, by combining time series analysis and deep learning techniques, such as the Long Short-Term Memory (LSTM) network model, accurate predictions of future market demand, competitive landscape, and technological development trends can be made. The LSTM model is a deep learning method specifically designed for time series forecasting, effectively addressing the limitations of traditional time series forecasting methods. The LSTM model can identify long-term dependencies, improving the accuracy of market demand forecasting. It is suitable for multivariate inputs, resulting in more comprehensive forecasts. It can handle nonlinear data, improving its adaptability to market changes. Combined with historical data and policy factors, it achieves more accurate industry trend analysis. Through the introduction of deep learning algorithms, the forecasting model can automatically learn and extract complex patterns and trends from the data, especially when facing nonlinear relationships or long-term dependencies, effectively improving the accuracy and precision of forecasts. Through the verification and correction of the forecast results, real-time optimization and adjustment of the model can be achieved, ensuring the accuracy of predictions. The predictive model can continuously adjust according to actual market changes, avoiding the problems of outdated predictions or excessive deviations from reality in traditional methods. The model's error is evaluated using the sliding window method, and hyperparameters are adjusted based on the root mean square error, further improving the model's generalization ability and adaptability, thus achieving long-term effective prediction of the concrete operation robot industry scale. By introducing deep learning models and optimization algorithms, the accuracy and flexibility of industry scale prediction are improved. Compared with traditional methods, deep learning algorithms can capture complex nonlinear relationships in market demand, thereby improving the accuracy and adaptability of prediction results. Simultaneously, the model's real-time verification and correction capabilities enable it to quickly adjust to market changes, effectively avoiding the lag and inaccuracy of traditional methods.

[0095] Example 2, refer to Figures 2-3 As an embodiment of the present invention, a method for predicting the industrial scale of concrete operation robots is provided. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0096] First, market sales data, technological development trends, economic environment information, and market share data of major competitors in the concrete operation robot industry were collected from public databases, industry reports, and internal enterprise data. The data covers the period from 2018 to 2024 to ensure sufficient time span for trend prediction. The collected data underwent standardization to eliminate the influence of different units, and missing value imputation and outlier removal methods were used to ensure data quality. Next, based on CIM technology, the main market players in the concrete operation robot industry were identified, including manufacturers, core component suppliers, end-user companies, and regulatory agencies. Through hierarchical market network analysis, the market share of each company was calculated, and principal component analysis was used to extract key variables such as market share, technological capabilities, and product update cycles. A state transition matrix based on Markov chains was then constructed to analyze the dynamic changes in market competition. Finally, the Herfindahl-Hirschman Index (HHI) was used to calculate the market share of concrete operation robots. The study investigates the degree of market competition and, using Markov chains, analyzes the market competition status of enterprises (dominant, growing, stable, declining, and exiting). Based on historical market data from 2018 to 2024, it statistically analyzes the transition probabilities of each enterprise's market status and optimizes the parameters of the state transition matrix using maximum likelihood estimation. Regarding supply and demand modeling, a dynamic supply and demand balance model for the concrete operation robot industry is constructed, considering factors such as total industry capacity, key component supply chain status, and enterprise expansion plans. Based on time series analysis, an autoregressive moving average (ARIMA) model is used to predict market demand, and a long short-term memory (LSTM) network is used to optimize the prediction accuracy. Finally, the prediction results are backtested using actual market data from 2023. The root mean square error (RMSE) is calculated, and the hyperparameters of the prediction model are adjusted to accurately predict the scale development trend of the concrete operation robot market from 2025 to 2028. Table 1 records and analyzes some experimental data and results.

[0097] Table 1 Experimental Data Recording Table

[0098] years Company A's market share (%) Company B's market share (%) Company C's market share (%) Total market sales volume (units) Average production cost (ten thousand yuan / unit) Demand Growth Index 2018 35 30 25 1500 30 1 2019 37 28 26 1600 29 1.1 2020 40 27 23 1750 28 1.2 2021 42 25 22 1850 27 1.3 2022 45 22 21 2000 26 1.4 2023 47 20 20 2200 25 1.5 2024 50 18 18 2500 24 1.6

[0099] Experimental data shows that the concrete processing robot market exhibited a steady growth trend from 2018 to 2024, primarily reflected in the evolution of market competition, market expansion, reduced production costs, and changes in supply and demand. Regarding market competition, Company A's market share increased from 35% in 2018 to 50% in 2024, demonstrating its advantages in technological innovation, marketing, and production capacity. Meanwhile, the market shares of Companies B and C decreased to 18% and 18% respectively, indicating a market concentration towards leading companies. The market size steadily expanded, with annual sales increasing from 1,500 units in 2018 to 2,500 units in 2024, representing an average annual growth rate of approximately 8.8%. The demand growth index also increased from 1.0 to 1.6, indicating continued growth in market demand. Figure 2From 2018 to 2024, the demand growth index for concrete operation robots continued to rise, showing a stable growth trend. The index increased from 1.0 in 2018 to 1.6 in 2024, indicating a continuously strengthening market demand for this type of robot. The driving force behind this demand growth mainly stems from the increasing demand for intelligent and automated construction in the construction industry, as well as the improved construction efficiency brought about by advancements in robot technology. Furthermore, the optimization of the core component supply chain and the reduction in manufacturing costs further boosted market demand. This trend proves that the supply and demand modeling method (ARIMA+LSTM) constructed based on this invention can effectively predict the market. Demand guides enterprises to rationally plan production capacity and market strategies; meanwhile, production costs continue to decline, with the average production cost decreasing from 300,000 yuan / unit in 2018 to 240,000 yuan / unit in 2024, a decrease of 20%. This is mainly due to factors such as optimized manufacturing processes, improved parts supply chains, and economies of scale. In recent years, the concrete operation robot market has maintained steady growth, increasing from 1,500 units in 2018 to 2,500 units in 2024, with an average annual growth rate of nearly 8.8%. Based on the ARIMA+LSTM forecasting model, future market demand is expected to continue to grow, potentially exceeding 3,400 units by 2028. The main drivers of this market demand growth are... Key drivers include: increased demand for automation in the construction industry, advancements in intelligent robot technology, and expanded demand from enterprises for efficient construction solutions. In particular, the increased market share of leading companies like Company A indicates a trend towards greater concentration in the competitive landscape, with strong companies further consolidating their market position through technological innovation and market expansion. Furthermore, supply and demand analysis shows that the production side is actively expanding capacity and optimizing the component supply chain to adapt to market growth. The line graph clearly illustrates the market demand forecast trend from 2025 to 2028, with the red dotted line representing future projected growth. Combined with historical data, it can be seen that the market demand growth rate is expected to accelerate, with the annual increase projected to reach [a significant percentage] after 2026. The number of units produced exceeded 200. Based on the technology development trend prediction model, it can be inferred that high-end concrete operation robots (such as automated control and intelligent optimization algorithms) will become the market mainstream and influence the further evolution of the market landscape. Overall, the experiment successfully verified the effectiveness of the comprehensive model of concrete operation robots constructed using CIM technology in market structure analysis, competitive landscape prediction, and supply and demand relationship modeling. It also proved that our invention can provide accurate market trend prediction results. Compared with traditional market forecasting methods, the use of Markov chains, principal component analysis, and time series regression techniques improves the accuracy of market forecasting, providing a scientific basis for enterprises to formulate strategic decisions.

[0100] Example 3, referring to Figure 4 As an embodiment of the present invention, a concrete operation robot industry scale prediction system is provided, including a data processing module 100, a model building module 200, and an analysis, prediction and verification module 300.

[0101] S4: Data processing module 100 includes data collection module 101 and data processing module 102. Data collection module 101 collects key data related to the concrete operation robot industry, and data integration module 102 is used to integrate data from different sources.

[0102] It should be noted that the data collection module 101 collects key data related to the concrete operation robot industry from multiple channels, including industry sales data (total market sales volume, enterprise sales revenue), engineering project procurement data (enterprise procurement), production supply chain data (supply status of core components, manufacturer capacity), and competitive environment data (enterprise market share, technology patent data). The data processing module 102 cleans, standardizes, and structures the data collected by the data collection module 101 from different sources, removes redundant data, fills in missing values, and performs data format conversion to ensure the accuracy and consistency of the data. Through operations such as removing redundant data, filling in missing values, and data format conversion, it ensures that the data on which the subsequent model construction depends is of high quality.

[0103] The data processing module 100 provides the model building module 200 with a cleaned and standardized data foundation. The data collection module collects raw data and passes it to the data processing module, which outputs a unified and standardized data source for the model building module to use, reducing potential errors in data processing. Based on this data, the model building module creates a basic industry model, while the correlation model building module relies on this cleaned data to discover complex relationships between data.

[0104] S5: The model building module 200 includes a comprehensive model building module 201 and a correlation model building module 202. The comprehensive model building module 201 is used to build a comprehensive model of the concrete operation robot industry, and will model the market structure, competitive landscape, and supply and demand relationship. The correlation model building module 202 is used to establish a correlation model between various influencing factors and comprehensively analyze the future development trend of the concrete operation robot industry.

[0105] It should be noted that the comprehensive model building module 201 constructs a comprehensive model of the concrete operation robot industry based on CIM technology, mainly including: Market structure modeling: identifying the main market participants in the concrete operation robot industry (manufacturing enterprises, component suppliers, end-user enterprises, and industry regulatory agencies), and constructing a hierarchical market network; Competitive landscape modeling: analyzing the competitive relationships of enterprises, calculating the market concentration (HHI index), and constructing a state transition matrix based on Markov chains to deduce changes in the market position of enterprises; Supply and demand relationship modeling: constructing a dynamic supply and demand balance model based on production capacity, supply chain status, and market demand, and predicting future market changes through time series methods; The correlation model building module 202 is responsible for extracting key variables in market structure, competitive landscape, and supply and demand relationship; using structural equation modeling (SEM) to quantify the influence paths between variables, forming a multi-level causal relationship network; and establishing a predictive framework for the scale of the concrete operation robot industry in conjunction with industry development trends; Once the model is completed, the system will output the model to the analysis, prediction, and verification module 300, entering the data analysis and prediction stage.

[0106] Once the model building module 200 completes the construction of the comprehensive model, the analysis, prediction, and verification module 300 uses the input data from these models to predict future industrial development through various prediction algorithms (such as regression analysis and time series forecasting). These predictions not only cover areas such as market demand and technological trends, but also include the impact of possible changes in the competitive landscape and policy changes. The analysis and prediction module 301 relies on the comprehensive data support provided by the model building module to predict the changing trends of key indicators such as industry scale and market demand over a period of time based on these models. The verification and correction module 302 compares the model prediction results with actual market data. The verification and correction module can identify deviations and errors in the prediction and make timely adjustments. It not only evaluates the prediction accuracy of the model through traditional error assessment methods (such as mean squared error and mean absolute error), but also adjusts the model parameters according to the prediction error, thereby improving the accuracy of future predictions.

[0107] S6: The analysis, prediction and verification module 300 includes an analysis and prediction module 301 and a verification and correction module 302. The analysis and prediction module 301 is used to perform data analysis and prediction on the comprehensive model, and the verification and correction module 302 is used to verify and correct the prediction results.

[0108] It should be noted that the analysis and prediction module 301 uses a Long Short-Term Memory (LSTM) network to predict the market demand for concrete operation robots; calculates competitive landscape indicators such as enterprise market share and technology patent distribution; uses topic modeling (LDA) to analyze industry technology development trends; and combines graph neural networks (GNN) to calculate the similarity between different technology fields in order to identify the development path of key technologies in the future.

[0109] Combining supply and demand models, the system predicts the future market size of concrete operation robots and provides visualized prediction results. The verification and correction module 302 performs error analysis on the prediction results and compares them with actual market data. Bayesian optimization is used to adjust model parameters to improve prediction accuracy. The system dynamically corrects the model based on the latest market data to ensure the timeliness and accuracy of the prediction results. The prediction data generated by the system will be used for enterprise market strategic planning, industry development trend research, and government policy decision support.

[0110] The output of the data processing module 100 directly affects the accuracy of the analysis, prediction, and verification module. During each data collection and processing process, the system ensures the quality and timeliness of the data, which is crucial for subsequent analysis and prediction. The data processing module provides the analysis and prediction module 300 with a continuously updated and reliable data source. After the prediction results are verified, if the error is large, the data processing module will re-collect and process the data to improve the model accuracy. The verification and correction module ensures that the system can make necessary adjustments based on the actual situation through continuous feedback.

[0111] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0112] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0113] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0114] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0115] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for predicting the industry scale of concrete operation robots, characterized in that, include: Collect and process relevant data on the concrete operation robot industry; A comprehensive model of the concrete operation robot industry is built based on CIM technology; Perform data analysis and prediction on the comprehensive model, and verify and revise the prediction results; The comprehensive model includes analysis and modeling based on market structure, competitive landscape, and supply and demand. In the process of data analysis and forecasting, predictive models are built for market demand, competitive landscape and technological development trends, and future trends are predicted based on time series and long short-term memory networks. The aforementioned data analysis and prediction, include, To construct a market demand forecasting model for concrete operation robots, historical sales data, engineering project procurement data, construction industry investment data, and government policy data of the concrete operation robot market are obtained. After standardizing the data, the long-term trend, periodic fluctuations, and random fluctuations of market demand are extracted using the time series decomposition method. Key influencing factors are screened, and a long short-term memory network model is used to predict future market demand. To construct a predictive model of the competitive landscape of the concrete operation robot industry, we obtain the market share, product technical parameters, construction project bidding data and patent layout data of enterprises in the industry, establish a competitive feature matrix, and use the Markov chain model to analyze the changes in market competition status and calculate the state transition probability of enterprises under different market environments. This paper constructs a predictive model for the technological development trend of concrete operation robots. It employs a topic modeling approach to cluster technical texts in the field of concrete operation robots, calculates the distribution of technical topics based on a probabilistic topic model, identifies the core technological directions of the current industry, calculates a patent citation network, constructs the technological evolution path of concrete operation robots, and identifies technological development trends by calculating the similarity between technological fields based on graph neural networks. It uses time series regression to analyze the development speed of each technological field, combines technology maturity analysis to determine the development stage of key technologies for concrete operation robots, and predicts future technology iteration cycles. Finally, it combines market demand prediction models and competitive landscape prediction models to analyze the impact of technological innovation on the market demand and corporate competitiveness of concrete operation robots, and infers the development trend of the industry scale.

2. The method for predicting the industry scale of concrete operation robots as described in claim 1, characterized in that: The comprehensive model includes, The market structure, competitive landscape, and supply and demand relationship are modeled. Key variables in the market structure, competitive landscape, and supply and demand relationship are extracted, and a correlation model between different influencing factors is established to comprehensively analyze the future development trend of the concrete operation robot industry.

3. The method for predicting the industry scale of concrete operation robots as described in claim 1 or 2, characterized in that: Modeling the market structure include, Identify the main players in the industry, including concrete operation robot manufacturers, core component suppliers, end-user companies, and industry regulatory agencies. Classify these entities based on market share, technological capabilities, product iteration speed, and business models, and define the interaction relationships between them to form a hierarchical market network.

4. The method for predicting the industry scale of concrete operation robots as described in claim 1 or 2, characterized in that: Modeling the competitive landscape include, A market competition model for concrete operation robots is constructed to analyze the competitive relationships among major companies in the industry, calculate the market concentration, measure the degree of market competition using the Herfindahl-Hirschman index, and establish a state transition matrix based on Markov chains to deduce the changing trends of companies' positions in the market and construct the state transition matrix.

5. The method for predicting the industry scale of concrete operation robots as described in claim 1 or 2, characterized in that: Model the supply and demand relationship. include, A supply and demand model for the concrete operation robot industry is constructed. Based on the total industry capacity, the supply chain status of core components, the capacity expansion plans of manufacturers, and the demand of end markets, a dynamic supply and demand balance model is established, and the future market demand trend is predicted through time series analysis.

6. The method for predicting the industry scale of concrete operation robots as described in claim 2, characterized in that: The establishment of a correlation model between different influencing factors includes, Key variables were extracted from the market structure, competitive landscape, and supply and demand relationship models. Principal component analysis was used to screen highly correlated variables, and structural equation modeling was used to quantify the influence paths between variables, forming a multi-level causal relationship network.

7. The method for predicting the industry scale of concrete operation robots as described in claim 2, characterized in that: The analysis provides a comprehensive overview of the future development trends of the concrete operation robot industry. include, A mathematical model for predicting the scale of the concrete operation robot industry was established. This model integrates market structure, competitive landscape, supply and demand relationship, and correlation models to construct an industry scale prediction framework based on computer integrated manufacturing technology. Through computer simulation and data iterative optimization, the future development trend of the concrete operation robot industry scale was calculated.

8. The method for predicting the industry scale of concrete operation robots as described in claim 1, characterized in that: The verification and correction of the prediction results includes, By comparing the results with actual market conditions, the accuracy of the predictions is verified, and the model parameters are adjusted, the algorithm is optimized, and the data is updated according to the actual situation.

9. A concrete operation robot industry scale prediction system, employing the concrete operation robot industry scale prediction method as described in any one of claims 1 to 8, characterized in that: It includes a data processing module (100), a model building module (200), and an analysis, prediction, and verification module (300). The data processing module (100) includes a data collection module (101) and a data processing module (102). The data collection module (101) collects key data related to the concrete operation robot industry, and the data integration module (102) is used to integrate data from different sources. The model building module (200) includes a comprehensive model building module (201) and a correlation model building module (202). The comprehensive model building module (201) is used to build a comprehensive model of the concrete operation robot industry based on CIM technology, and will model the market structure, competitive landscape, and supply and demand relationship. The correlation model building module (202) is used to establish a correlation model between various influencing factors and comprehensively analyze the future development trend of the concrete operation robot industry. The analysis, prediction and verification module (300) includes an analysis and prediction module (301) and a verification and correction module (302). The analysis and prediction module (301) is used to perform data analysis and prediction on the comprehensive model, and the verification and correction module (302) is used to verify and correct the prediction results.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the concrete operation robot industry scale prediction method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the concrete operation robot industry scale prediction method according to any one of claims 1 to 8.

Images