Enterprise project informatization data processing method, device and system and storage medium

Abstract

The invention relates to an enterprise project informatization data processing method, device and system and a storage medium. The method comprises the steps of obtaining enterprise project operation data, enterprise project target information and market project constraint conditions corresponding to a target enterprise; determining each network analysis model and each mathematical analysis model according to the data type and data complexity information of the enterprise project operation data; performing series market dynamic analysis on the enterprise project operation data by using each network analysis model to obtain network model analysis data; performing series market dynamic analysis on the enterprise project operation data by using each mathematical analysis model to obtain mathematical model analysis data; and performing resource utilization analysis according to the network model analysis data and the mathematical model analysis data by taking the target information of each enterprise project and the constraint condition of each market project as limitation information to obtain an enterprise operation analysis result. By adopting the method, the enterprise project informatization data processing efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, system and storage medium for processing enterprise project information data. Background Art

[0002] With the development of computer technology, enterprise project information data processing technology has emerged. This technology uses information technology to effectively collect, store, process and analyze various types of data in enterprise projects to provide support for decision-making. This method usually involves data integration and cleaning, modeling and prediction, and the application of decision support systems to help managers make more accurate business decisions.

[0003] When processing enterprise project information data, traditional technology usually uses a single database management system (such as a relational database) to store data and uses simple statistical analysis methods to generate reports or evaluate project progress. However, traditional technology methods rely on preset rules and static data models, and lack the ability to handle dynamic changes and complex relationships, resulting in inefficient processing of enterprise project information data. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, system and storage medium for processing enterprise project information data that can handle dynamic changes and complex relationships, thereby improving the efficiency of enterprise project information data processing, in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for processing enterprise project information data, comprising: Obtain enterprise project operation data, enterprise project target information and market project constraints corresponding to the target enterprise; Determine each network analysis model and each mathematical analysis model corresponding to the target enterprise according to the data type and data complexity information of the enterprise project operation data; Using each of the network analysis models, respectively conduct serial market dynamic analysis on the enterprise project operation data to obtain network model analysis data; Using each of the mathematical analysis models, respectively perform the series market dynamic analysis on the enterprise project operation data to obtain mathematical model analysis data; Using the target information of each enterprise project and the constraint conditions of each market project as limiting information, performing resource utilization analysis according to the network model analysis data and the mathematical model analysis data, and obtaining enterprise operation analysis results; the enterprise operation analysis results are used to generate enterprise operation analysis strategies; The target information of each enterprise project and the constraint conditions of each market project are used as limiting information, and resource utilization analysis is performed according to each network model analysis data and each mathematical model analysis data to obtain enterprise operation analysis results, including: Using the target information of each enterprise project and the constraint conditions of each market project as limiting information, constructing a resource analysis target function corresponding to the target enterprise; Solving the resource analysis objective function to obtain various solved operation analysis results corresponding to any resource allocation stage; The Pareto front is found in each of the solved operation analysis results corresponding to any resource allocation stage to obtain the enterprise operation analysis result.

[0006] In a second aspect, the present application also provides a device for processing enterprise project information data, including: The data acquisition module is used to obtain the enterprise project operation data, enterprise project target information and market project constraints corresponding to the target enterprise; A model determination module, used to determine each network analysis model and each mathematical analysis model corresponding to the target enterprise according to the data type and data complexity information of the enterprise project operation data; A data analysis module, used to use each of the network analysis models to perform serial market dynamic analysis on the enterprise project operation data to obtain network model analysis data; The data analysis module is further used to use each of the mathematical analysis models to perform the series market dynamic analysis on the enterprise project operation data to obtain mathematical model analysis data; A strategy generation module is used to use the target information of each enterprise project and the constraint conditions of each market project as limiting information, perform resource utilization analysis according to the network model analysis data and the mathematical model analysis data, and obtain enterprise operation analysis results; the enterprise operation analysis results are used to generate enterprise operation analysis strategies; The target information of each enterprise project and the constraint conditions of each market project are used as limiting information, and resource utilization analysis is performed according to each network model analysis data and each mathematical model analysis data to obtain enterprise operation analysis results, including: Using the target information of each enterprise project and the constraint conditions of each market project as limiting information, constructing a resource analysis target function corresponding to the target enterprise; Solving the resource analysis objective function to obtain various solved operation analysis results corresponding to any resource allocation stage; The Pareto front is found in each of the solved operation analysis results corresponding to any resource allocation stage to obtain the enterprise operation analysis result.

[0007] In a third aspect, the present application also provides a system for processing enterprise project information data, comprising: a computer device, wherein the computer device comprises a memory and a processor, the memory comprises a storage medium, the storage medium stores a computer program, and when the processor executes the computer program, it implements a method as described in any one of the methods for processing enterprise project information data.

[0008] The above-mentioned method, device, system and storage medium for processing enterprise project information data obtain the enterprise project operation data, enterprise project target information and market project constraints corresponding to the target enterprise; determine the network analysis models and mathematical analysis models corresponding to the target enterprise according to the data type and data complexity information of the enterprise project operation data; use each network analysis model to conduct a series market dynamic analysis on the enterprise project operation data respectively to obtain network model analysis data; use each mathematical analysis model to conduct a series market dynamic analysis on the enterprise project operation data respectively to obtain mathematical model analysis data; use each enterprise project target information and each market project constraint as limiting information, according to the network model analysis data and Mathematical model analysis data is used to perform resource utilization analysis to obtain enterprise operation analysis results; the enterprise operation analysis results are used to generate enterprise operation analysis strategies; wherein, using the target information of each enterprise project and the constraints of each market project as limiting information, resource utilization analysis is performed based on each network model analysis data and each mathematical model analysis data to obtain enterprise operation analysis results, including: using the target information of each enterprise project and the constraints of each market project as limiting information, constructing a resource analysis objective function corresponding to the target enterprise; solving the resource analysis objective function to obtain each solved operation analysis result corresponding to any resource allocation stage; finding the Pareto front in each solved operation analysis result corresponding to any resource allocation stage to obtain the enterprise operation analysis result.

[0009] By using network analysis models and mathematical analysis models in combination, the enterprise project operation data is analyzed in series with market dynamics, which can effectively reveal potential problems and optimization space in enterprise operations; further introducing enterprise project target information and market constraints, it realizes accurate analysis of resource utilization, thus providing enterprises with practical operation analysis strategies. This multi-model fusion analysis method can not only handle dynamic changes and complex relationships, thereby improving the efficiency of enterprise project information data processing, but also enhance the scientificity and accuracy of decision support, improve the ability of enterprises to respond to market changes and optimize resource allocation, and ultimately promote the improvement of enterprise operation efficiency and market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0011] Figure 1 An application environment diagram of a method for processing enterprise project information data in one embodiment; Figure 2 A flowchart of a method for processing enterprise project information data in one embodiment; Figure 3 A schematic diagram of a flow chart of a method for obtaining network model analysis data in one embodiment; Figure 4 A schematic diagram of a process for obtaining initial network model analysis data in one embodiment; Figure 5 A schematic diagram of a flow chart of a method for obtaining network model analysis data in another embodiment; Figure 6 A schematic diagram of a flow chart of a method for obtaining data by analyzing a mathematical model in one embodiment; Figure 7 A schematic diagram of a process for obtaining data by analyzing an initial mathematical model in one embodiment; Figure 8 A schematic flow chart of a method for obtaining data by mathematical model analysis in another embodiment; Fig. 9 A flowchart of a method for obtaining enterprise operation analysis results in one embodiment; Fig.10 It is a structural block diagram of a device for processing enterprise project information data in one embodiment; Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0012] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0013] The present application provides a method for processing enterprise project information data, which can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 obtains the enterprise project operation data, enterprise project target information and market project constraints corresponding to the target enterprise from the terminal 102; according to the data type and data complexity information of the enterprise project operation data, the network analysis models and the mathematical analysis models corresponding to the target enterprise are determined; using each network analysis model, the enterprise project operation data are respectively connected in series with the market dynamics analysis to obtain network model analysis data; using each mathematical analysis model, the enterprise project operation data are respectively connected in series with the market dynamics analysis to obtain mathematical model analysis data; using each enterprise project target information and each market project constraint as limiting information, according to the network model analysis data and the mathematical model analysis data Perform resource utilization analysis to obtain enterprise operation analysis results; the enterprise operation analysis results are used to generate enterprise operation analysis strategies; wherein, using the target information of each enterprise project and the constraints of each market project as limiting information, performing resource utilization analysis according to each network model analysis data and each mathematical model analysis data to obtain enterprise operation analysis results, including: using the target information of each enterprise project and the constraints of each market project as limiting information, constructing a resource analysis objective function corresponding to the target enterprise; solving the resource analysis objective function to obtain each solved operation analysis result corresponding to any resource allocation stage; finding the Pareto frontier in each solved operation analysis result corresponding to any resource allocation stage to obtain the enterprise operation analysis result. Among them, the server 104 can be implemented with an independent server or a server cluster composed of multiple servers.

[0014] In an exemplary embodiment, Figure 2 As shown, a method for processing enterprise project information data is provided, and the method is applied to Figure 1 The server in the example is used to illustrate, including the following steps 202 to 210. Among them: Step 202, obtaining enterprise project operation data, enterprise project target information and market project constraints corresponding to the target enterprise.

[0015] Among them, enterprise project operation data can be various types of operation information reflecting the implementation process of enterprise projects, including financial data, progress data, cost control, staffing, resource consumption, etc.

[0016] Among them, enterprise project goal information can be specific goals and expectations set at the beginning of the project, including financial goals (such as profit, revenue), market goals (such as market share, brand influence), operational goals (such as cost control, efficiency improvement), etc.

[0017] Among them, market project constraints can be the restrictive factors that the market environment imposes on enterprise projects during project implementation, including external factors such as market competition, technological changes, and resource supply restrictions.

[0018] Specifically, the server 104 traverses all the terminals 102 and collects the enterprise project operation data of the target enterprise from the target terminal 102 according to the traversal information, including financial data, market performance, project execution progress, resource usage, etc. These data will provide a basis for subsequent analysis. At the same time, it is also necessary to obtain enterprise project target information (such as income, profit, market share, etc.) and market project constraints (such as policy restrictions, competitive environment, technical constraints, etc.) from the terminal 102 to ensure that the analysis can be carried out within the framework of actual operation and market environment.

[0019] Step 204 , determining each network analysis model and each mathematical analysis model corresponding to the target enterprise according to the data type and data complexity information of the enterprise project operation data.

[0020] Among them, data complexity information can be the nature, scale and dimension of enterprise project operation data. It includes the complexity of data diversity (such as structured data, unstructured data), quantity, correlation between data, dynamic changes, etc.

[0021] Among them, the network analysis model can be a model that analyzes the interconnections and dynamic changes between various elements within the system (such as internal departments, supply chains, customers, etc.) based on methods such as neural networks.

[0022] Among them, the mathematical analysis model can be a model that performs quantitative analysis on data through mathematical methods (such as regression analysis, optimization algorithm, prediction model, etc.).

[0023] Specifically, according to the data types (such as time series data, structured data or unstructured data) and data complexity information (such as the size of the data, the diversity of data dimensions, etc.) identified from the enterprise project operation data provided by the target enterprise, select each network analysis model and each mathematical analysis model that matches the data type and data complexity information from the network analysis model set and the mathematical analysis model set. For example, for data with strong time series and significant causal relationships and interactive effects in the data, a mathematical model based on time series analysis can be selected, as well as a graph theory or social network model as a network analysis model to identify key nodes and connections in enterprise operations.

[0024] Step 206, using each network analysis model, respectively conduct serial market dynamic analysis on the enterprise project operation data to obtain network model analysis data.

[0025] Among them, serial market dynamics analysis can be a process of using each network analysis model in sequence to combine enterprise project operation data with market dynamic changes (such as market demand, price fluctuations, competitive behavior, etc.) for analysis.

[0026] The network model analysis data may be result data obtained in sequence through various network analysis models, usually including information such as the relationship strength, interaction pattern, and transmission efficiency between different elements.

[0027] Specifically, the selected network analysis models are used to analyze the interactive relationships and dynamic trends in the enterprise project operation data in the selected model calling order. Since the network analysis model can reveal the connection between different departments or links within the enterprise, as well as the impact of the external market environment on the enterprise operation. For example, by modeling the enterprise supply chain, sales network, etc., the synergy and potential bottleneck problems of different links can be analyzed. By analyzing the market dynamics in a serial form, the chain reaction of factors such as changes in market demand and competitive situation on various operational activities of the enterprise can be captured, and network model analysis data can be obtained.

[0028] Step 208, using various mathematical analysis models, respectively conduct serial market dynamic analysis on the enterprise project operation data to obtain mathematical model analysis data.

[0029] The mathematical model analysis data may be the results obtained through various mathematical analysis models in sequence, usually expressed as quantitative analysis results, such as predicted values, optimal solutions, risk assessments, etc.

[0030] Specifically, the selected mathematical analysis models are used to quantitatively analyze the enterprise project operation data in the selected model calling order to obtain more accurate predictions and results. According to the nature and business needs of the enterprise project operation data, the mathematical analysis model can use mathematical analysis models such as regression analysis, optimization algorithms, and risk assessment to conduct in-depth mining of the dynamic results of the market in a serial manner. Each mathematical analysis model further predicts possible future operating performance based on historical data and market trends, and evaluates the risks and benefits under different decisions to obtain mathematical model analysis data.

[0031] Step 210, using the target information of each enterprise project and the constraint conditions of each market project as limiting information, performing resource utilization analysis based on the network model analysis data and the mathematical model analysis data, and obtaining the enterprise operation analysis results.

[0032] Among them, the enterprise project goal information can be the specific goals and expected results clearly set in the planning stage of data analysis. These goals usually cover multiple levels, such as financial goals (such as profitability, cost control, return on investment), market goals (such as market share, brand awareness, customer satisfaction), operational goals (such as improving production efficiency, optimizing resource allocation, reducing risks, etc.) and strategic goals (such as long-term development, improvement of innovation capabilities, etc.).

[0033] Among them, market project constraints can be restrictions imposed by the external market environment or internal factors during the execution of various projects of the enterprise. These constraints usually include external factors such as policies and regulations (such as industry regulations, environmental protection laws, etc.), market competition (such as competitor strategies, market entry barriers), technical restrictions (such as technical feasibility, technology development trends), and resource supply (such as unstable raw material supply and tight labor market).

[0034] Among them, resource utilization analysis can be the evaluation of the utilization efficiency and allocation of existing resources (such as manpower, funds, equipment, etc.) during the operation of enterprise projects.

[0035] Among them, the results of enterprise operation analysis can be a comprehensive interpretation of the enterprise project operation data and its analysis model output, usually including evaluations of operational efficiency, resource utilization, market adaptability, financial status, etc.

[0036] Among them, the enterprise operation analysis strategy can be an optimization plan or action plan formulated based on the results of the enterprise operation analysis, aiming to improve the execution effect of enterprise projects, improve resource utilization efficiency, optimize financial status or achieve higher market competitiveness.

[0037] Specifically, by combining the enterprise project goal information (such as increasing profitability, expanding market share, etc.) and market project constraints (such as resource availability, budget constraints, etc.) as the analysis objectives and analysis constraints, through integrating the network model analysis data corresponding to each network analysis model and the mathematical model analysis data corresponding to each mathematical analysis model, the enterprise's resource utilization is analyzed in detail, and how the enterprise maximizes resource utilization efficiency under existing conditions is evaluated, and potential problems or optimization space in resource allocation are identified to obtain the enterprise operation analysis results.

[0038] Furthermore, based on the above-mentioned enterprise operation analysis results, specific improvement suggestions are put forward, such as optimizing resource allocation, adjusting business processes, changing marketing strategies, etc., and integrated into operation analysis strategies for target enterprises. Through operation analysis strategies, target enterprises can better respond to market changes and improve operational efficiency, thereby achieving predetermined project goals and long-term development.

[0039] In the above-mentioned method for processing enterprise project information data, the enterprise project operation data, enterprise project target information and market project constraints corresponding to the target enterprise are obtained; according to the data type and data complexity information of the enterprise project operation data, the network analysis models and the mathematical analysis models corresponding to the target enterprise are determined; using the network analysis models, the enterprise project operation data are respectively connected to the market dynamics analysis to obtain network model analysis data; using the mathematical analysis models, the enterprise project operation data are respectively connected to the market dynamics analysis to obtain mathematical model analysis data; using the enterprise project target information and the market project constraints as limiting information, according to the network model analysis data and the mathematical model analysis data The analysis data is used to perform resource utilization analysis to obtain enterprise operation analysis results; the enterprise operation analysis results are used to generate enterprise operation analysis strategies; wherein, the target information of each enterprise project and the constraints of each market project are used as limiting information, and resource utilization analysis is performed according to the analysis data of each network model and the analysis data of each mathematical model to obtain enterprise operation analysis results, including: using the target information of each enterprise project and the constraints of each market project as limiting information, constructing a resource analysis objective function corresponding to the target enterprise; solving the resource analysis objective function to obtain each solved operation analysis result corresponding to any resource allocation stage; finding the Pareto frontier in each solved operation analysis result corresponding to any resource allocation stage to obtain the enterprise operation analysis result.

[0040] By using network analysis models and mathematical analysis models in combination, the enterprise project operation data is analyzed in series with market dynamics, which can effectively reveal potential problems and optimization space in enterprise operations; further introducing enterprise project target information and market constraints, it realizes accurate analysis of resource utilization, thus providing enterprises with practical operation analysis strategies. This multi-model fusion analysis method can not only handle dynamic changes and complex relationships, thereby improving the efficiency of enterprise project information data processing, but also enhance the scientificity and accuracy of decision support, improve the ability of enterprises to respond to market changes and optimize resource allocation, and ultimately promote the improvement of enterprise operation efficiency and market competitiveness.

[0041] In an exemplary embodiment, Figure 3 As shown, each network analysis model is used to perform serial market dynamic analysis on the enterprise project operation data to obtain network model analysis data, including steps 302 to 306. Among them: Step 302: Determine the network model analysis sequence corresponding to each network analysis model according to the data type and data complexity information.

[0042] The network model analysis sequence may be to call different network analysis sub-models in a specific sequence during the analysis process, so as to effectively process various types of information in the enterprise project operation data.

[0043] Specifically, the enterprise project operation data is preliminarily analyzed to identify its data type and data complexity information. The data types may include time series data (such as sales data, inventory changes), structured data (such as financial statements, resource allocation), unstructured data (such as customer feedback, social media information), etc. Data complexity information involves the size of the data volume, the complexity of the dimension, the relationship network between the data, the degree of noise, and the dynamic change characteristics of the data. Based on the information obtained from the above identification, the most suitable network analysis models are determined. The image analysis submodel included in the network analysis model is usually suitable for processing visual or spatial information (such as satellite images, production line monitoring videos, etc.), the nonlinear analysis submodel is suitable for processing data with complex nonlinear relationships (such as the nonlinear correlation between market demand and price), and the reinforcement analysis submodel is used to optimize decision-making, especially in the face of market fluctuations and dynamic changes, the strategy is gradually adjusted through the feedback mechanism. Therefore, it is necessary to reasonably select and determine the network model analysis order for calling different analysis models according to the data characteristics to ensure the logic of the analysis process and the efficiency of data processing.

[0044] Step 304, according to the network model analysis sequence, the image analysis sub-model, the nonlinear analysis sub-model and the reinforcement analysis sub-model are called to perform serial market dynamic analysis on the enterprise project operation data respectively to obtain initial network model analysis data.

[0045] Among them, serial market dynamics analysis can be achieved by calling different analysis sub-models in sequence to combine enterprise project operation data with market dynamic factors.

[0046] The initial network model analysis data may be a preliminary analysis result obtained by sequentially processing the enterprise project operation data through a series of network analysis sub-models.

[0047] Specifically, according to the previously determined network model analysis sequence, each sub-model is called in turn for analysis. For the image analysis sub-model, it will process the possible visual or spatial features in the enterprise project operation data, such as using computer vision technology to analyze market trend charts, geographic location data or customer behavior images, and extract potential patterns and trends from them; then the nonlinear analysis sub-model processes the complex nonlinear data in the enterprise project operation data or the output data of the image analysis sub-model, especially those variables that show nonlinear relationships, such as the relationship between resource input and output, market pricing and consumer demand. This part of the model reveals these complex interactive effects through mathematical methods (such as nonlinear regression, chaos theory, etc.); finally, the reinforcement analysis sub-model plays a role in market dynamic analysis. It simulates various market changes and decision feedback based on the enterprise project operation data or the data output by the nonlinear analysis sub-model, evaluates the effects of different strategies, and optimizes the decision-making process of enterprises in different market environments. Through this series of market dynamic analysis, the initial network model analysis data is finally obtained. These data reflect the performance of enterprise operations in a complex market environment and form analysis results that provide a basis for subsequent adjustments and optimizations.

[0048] Step 306: Adjust the initial network model analysis data according to the difference between the initial network model analysis data and the first preset standard value to obtain the network model analysis data.

[0049] Specifically, the initial network model analysis data is compared with a preset first preset standard value, wherein the first preset standard value is usually a reference benchmark set by enterprise goals, historical data, industry best practices or expert forecast values. The identification and measurement of differences can be carried out in a variety of ways, such as calculating errors or deviation values ​​(such as mean square error, absolute error, etc.). If there is a large difference between the initial network model analysis data and the first preset standard value, it means that the model calling sequence causes inaccurate predictions or results, and the model calling sequence may need to be adjusted. After the calling sequence is adjusted, the model parameters also need to be adjusted, including but not limited to the following aspects: optimizing model parameters (such as weights, coefficients, etc.), improving the processing of input data (such as data cleaning, denoising), or adjusting the algorithm structure of the analysis model (such as changing the topological structure of the network analysis model or introducing new variables); if the analysis data shows that certain external market factors (such as policy changes, competitive behavior) have a greater impact on the results, these factors need to be added to the model for more accurate modeling. In addition, if only the calling order of the model is adjusted but the model parameters are not adjusted, the preliminary analysis results can be corrected through multiple iterative optimizations, and it can be ensured that the regained initial network model analysis data is closer to the first preset standard value, thereby improving the credibility and effectiveness of the analysis results. Through the feedback mechanism, continuous iterations are performed until the difference between the initial network model analysis data and the first preset standard value reaches the expected range, and the network model analysis data is obtained.

[0050] In this embodiment, by determining the analysis order of each network analysis model according to the data type and complexity information, and using the image analysis sub-model, nonlinear analysis sub-model and reinforcement analysis sub-model to conduct serial market dynamic analysis on the enterprise project operation data, more accurate and efficient resource allocation and operation optimization can be achieved. In this process, the generation of initial network model analysis data and the adjustment of data according to the difference from the preset standard value can ensure that the analysis results are continuously optimized and further improve the accuracy and applicability of the model. This dynamic adjustment mechanism enables enterprises to monitor market dynamics and operating conditions in real time and respond in a timely manner, thereby providing strong data support for enterprise decision-making and promoting enterprises to achieve optimal resource allocation and operation strategies in a complex market environment.

[0051] In an exemplary embodiment, Figure 4 As shown, according to the network model analysis sequence, the image analysis sub-model, the nonlinear analysis sub-model and the reinforcement analysis sub-model are called to perform serial market dynamic analysis on the enterprise project operation data respectively to obtain the initial network model analysis data, including steps 402 to 406. Among them: Step 402, when the network model analysis sequence representation uses the image analysis sub-model, the nonlinear analysis sub-model and the reinforcement analysis sub-model in sequence, the graph structure dependency relationship corresponding to the enterprise project operation data is identified to obtain node-edge embedded data.

[0052] Among them, the image analysis sub-model, nonlinear analysis sub-model and reinforcement analysis sub-model can be three different analysis methods used to optimize enterprise project operation data. The image analysis sub-model processes the visual features of the data (such as graphics and spatial structure) to reveal potential patterns such as market trends and customer behavior; the nonlinear analysis sub-model can capture the complex nonlinear relationships in the data and provide more accurate results than traditional linear models, especially suitable for the analysis of complex interactive effects, such as the nonlinear relationship between market demand and supply chain; the reinforcement analysis sub-model is based on the principle of reinforcement learning, simulates different decision paths, and repeatedly tries and fails to dynamically adjust strategies to maximize long-term rewards.

[0053] The graph structure dependency can be the dependency relationship established between nodes (such as projects, resources, departments, etc.) in the enterprise project operation data through edges (representing relationships or interactions). In the graph structure, nodes represent the elements in the system, while edges represent the mutual connection or influence between these elements.

[0054] The node-edge embedded data may be a data form generated by graph structure analysis, in which the feature information of nodes and edges is embedded into a low-dimensional space to form a vector representation.

[0055] Specifically, the image analysis sub-model, nonlinear analysis sub-model, and reinforcement analysis sub-model are applied in sequence through the network model analysis sequence, where the image analysis sub-model first processes the visual or spatial features that may exist in the enterprise project operation data, such as market trend graphs, spatial distribution of resource allocation, etc. These features can be converted into a graph structure (for example, nodes represent different projects or resources, and edges represent the relationship between them). The dependency structure between nodes (projects or resources) and edges (interactions between them) in the graph structure is further identified, and this information is converted into "node-edge embedded data".

[0056] Step 404 , performing nonlinear transformation on the node-edge embedding data to obtain nonlinear operation analysis results.

[0057] The nonlinear operation analysis result may be output data on the enterprise project operation obtained through the nonlinear analysis model.

[0058] Specifically, since the relationship between various factors in enterprise project operations is often not linear, nonlinear analysis methods must be used to reveal these complex interactive effects. Nonlinear transformation is applied to node-edge embedded data. This nonlinear transformation can use nonlinear optimization algorithms, deep learning models and other methods to model the relationship between nodes and edges to capture the complex dependencies and interactions. Through this nonlinear transformation, the nonlinear operation analysis results obtained can accurately reflect the operation effects of enterprise projects under various nonlinear constraints and factors, providing more accurate analysis data for subsequent decision-making and adjustments.

[0059] Step 406 , based on the industry environment data corresponding to the target enterprise, the nonlinear operation analysis results are adjusted to maximize the long-term reward, and the initial network model analysis data is obtained.

[0060] Among them, industry environment data can be external factors and background information that reflect the industry in which the enterprise is located, including information on market trends, regulations and policies, technological development, competitive situation, consumer behavior, social culture, etc.

[0061] Among them, maximizing long-term reward adjustment can be a strategy adjustment applied to decision-making processes such as reinforcement learning.

[0062] Specifically, according to the industry environment data of the target enterprise, the previously obtained nonlinear operation analysis results are further adjusted to optimize the enterprise's long-term development strategy. The industry environment data usually includes information such as market trends, policies and regulations, and competitive situations. These external factors have an important impact on the long-term goals and operation strategies of the enterprise. By combining these environmental data with the nonlinear operation analysis results and using the maximum long-term reward adjustment method (for example, the reward mechanism in reinforcement learning), the enterprise's operation strategy can be adjusted to maximize the final operation effect, ensuring that the analysis results not only meet the current operation needs, but also adapt to the market changes and industry development trends that may occur in the future, thereby obtaining the initial network model analysis data that meets the long-term goals of the enterprise.

[0063] In this embodiment, by sequentially using the image analysis sub-model, the nonlinear analysis sub-model, and the reinforcement analysis sub-model to perform serial analysis on the enterprise project operation data, the graph structure dependencies in the data can be deeply mined to identify the node-edge embedded data. This process can reveal the complex relationships and potential patterns behind the data, which helps to more accurately understand the inherent dynamics of enterprise operations. Nonlinear transformation of node-edge embedded data can further enhance the flexibility and adaptability of analysis, making the interpretation of operation data more comprehensive and accurate. By combining industry environment data to maximize long-term reward adjustments to the results of nonlinear operation analysis, operation strategies can be optimized to ensure that decisions not only meet current needs, but also provide support for the long-term development of the enterprise. This systematic analysis process can provide efficient and accurate decision support in a dynamic market environment, helping enterprises to gain a favorable position in competition.

[0064] In an exemplary embodiment, Figure 5 As shown, according to the difference between the initial network model analysis data and the first preset standard value, the initial network model analysis data is adjusted to obtain the network model analysis data, including steps 502 to 508. Among them: Step 502, traversing each network model sequence to adjust information according to the difference between the initial network model analysis data and the first preset standard value.

[0065] The network model sequence adjustment information may be a possible and adjustable calling sequence of each network analysis model.

[0066] Specifically, the difference (such as error, deviation, etc.) between the initial network model analysis data and the first preset standard value is calculated, that is, the difference reflects the degree of deviation between the initial analysis result and the expected target, and the possible sequence combinations of each network analysis model are traversed. The possible sequence combination of a network analysis model is used as a network model sequence adjustment information, and each network model sequence adjustment information corresponding to the possible sequence combination of each network analysis model is obtained.

[0067] Step 504: According to the sequence adjustment information of each network model, the sequence of network model analysis is adjusted respectively to obtain the adjustment sequence of each network model.

[0068] The network model adjustment sequence may be to modify the execution sequence of each sub-model according to the aforementioned network model sequence adjustment information to obtain new execution sequence information.

[0069] Specifically, according to the order adjustment information of each network model, the calling order of each network analysis model is adjusted respectively. Specifically, this includes rearranging or recombining the calling order of the image analysis sub-model, the nonlinear analysis sub-model and the enhanced analysis sub-model to obtain the adjustment order of each network model, wherein the purpose of adjusting the order is to optimize the analysis process to reduce errors or deviations and maximize the accuracy of the analysis results. For example, some data may reveal important features in the image analysis stage, while other data may need to first use nonlinear analysis to explore complex relationships, so it is necessary to flexibly adjust the analysis order according to the characteristics of the data.

[0070] Step 506, according to the adjustment sequence of each network model, the image analysis sub-model, the nonlinear analysis sub-model and the reinforcement analysis sub-model are respectively called to perform serial market dynamic analysis on the enterprise project operation data to obtain the analysis data of each adjusted network model.

[0071] The adjusted network model analysis data may be a new analysis result obtained by re-analyzing the serial market dynamics of the enterprise project operation data after applying a new network model adjustment sequence.

[0072] Specifically, according to the adjustment order of each network model, the image analysis sub-model, nonlinear analysis sub-model and reinforcement analysis sub-model are re-called in parallel to analyze the enterprise project operation data in turn. Specifically, based on the adjusted order, each sub-model is called in series to conduct a step-by-step in-depth analysis of the data in turn. Through the adjusted analysis, each new "adjusted network model analysis data" is obtained, which reflects the operation of the enterprise project and its relationship with market dynamics under the new analysis order.

[0073] Step 508 , respectively comparing the differences between the initial network model analysis data and each adjusted network model analysis data and the first preset standard value, and selecting the analysis data with the smallest difference as the network model analysis data.

[0074] Specifically, an error or deviation measurement method (such as mean square error, absolute error, etc.) is used to compare the difference between each adjusted network model analysis data and the first preset standard value, forming a difference value set including the difference between the initial network model analysis data and the first preset standard value. The analysis data with the smallest difference value from the first preset standard value is selected from the difference value set as the final network model analysis data. The purpose of the selection is to ensure that the final analysis result best meets the expected goal, minimizes the analysis error, and provides the most accurate and reliable data support for subsequent decision-making.

[0075] In this embodiment, by traversing the order adjustment information of each network model and performing serial market dynamic analysis according to the adjusted analysis order, the accuracy and adaptability of the network model analysis can be significantly improved. In this process, by comparing and adjusting the difference between the initial network model analysis data and the first preset standard value, the model output can be optimized. By continuously adjusting the order of the network model and analyzing the adjusted data, the analysis results that best meet the preset standards can be identified, thereby avoiding the accumulation of model deviations or errors. This dynamic adjustment mechanism not only improves the accuracy of data analysis, but also ensures that the model has higher adaptability when facing a complex and changing market environment, providing more reliable and efficient data support for corporate decision-making, and helping to achieve the optimal allocation of resources and the achievement of strategic goals.

[0076] In an exemplary embodiment, Figure 6 As shown, using various mathematical analysis models, the enterprise project operation data is respectively subjected to serial market dynamic analysis to obtain mathematical model analysis data, including steps 602 to 606. Among them: Step 602: Determine the mathematical model analysis sequence corresponding to each mathematical analysis model according to the data type and data complexity information.

[0077] Among them, the order of mathematical model analysis can be between multiple mathematical analysis models (such as grey theory model, time series model, multivariate linear regression model, variational method model), and the order of their use in the analysis process is determined according to the data type, complexity and analysis objectives.

[0078] Specifically, evaluate the data type (such as time series data, spatial data, discrete data, continuous data, etc.) and data complexity information (such as data dimension, noise level, missing values, etc.). For example, for time series data, the time series model should be used first because it can effectively capture the time dependence of the data; for systems with incomplete information or fuzziness, the grey theory model can provide better processing capabilities; the multivariate linear regression model is suitable for data with linear relationships between variables, while the variational method model is more suitable for solving optimization problems. Through a comprehensive evaluation of the data type and data complexity information, determine the calling order of each mathematical analysis model, so as to ensure that the use of each model can maximize the accuracy and efficiency of data analysis, and obtain the mathematical model analysis order.

[0079] Step 604, according to the mathematical model analysis sequence, call the grey theory model, time series model, multivariate linear regression model and variational method model to perform serial market dynamic analysis on the enterprise project operation data respectively to obtain initial mathematical model analysis data.

[0080] The initial mathematical model analysis data may be the preliminary analysis results obtained after calling various mathematical analysis models (such as grey theory model, time series model, etc.) in sequence for analysis according to a predetermined mathematical model analysis sequence.

[0081] Specifically, according to the mathematical model analysis sequence determined previously, each sub-model is called in turn for analysis. For images or time series data, a preliminary analysis will be performed through the time series model to capture the time dependence and trend of the data; the gray theory model is used to process the data in the enterprise project operation data or the output data of the time series model that has uncertainty, partial information loss or missing, which is particularly effective for dealing with fuzzy or incomplete situations; the multivariate linear regression model is used to analyze the linear relationship between different factors in the enterprise project operation data or the output data of the gray theory model to find out the degree of influence and interaction of each factor; the variational method model is used to calculate the optimal solution or constrained optimization of the output data of the enterprise project operation data or the multivariate linear regression model to help analyze how to maximize certain goals (such as profit, output, etc.) under specific constraints. The serial use of these models can gradually and deeply analyze the different dimensions of the data and finally obtain the initial mathematical model analysis data.

[0082] Step 606: When the error information of the mathematical model analysis data exceeds the second preset standard value, the initial mathematical model analysis data is adjusted to obtain the mathematical model analysis data.

[0083] The second preset standard value may be a threshold used to measure whether the initial mathematical model analysis data meets the expected results or quality requirements during the model analysis process.

[0084] Specifically, the error between the initial mathematical model analysis data and the second preset standard value composed of the actual observed data or the expected standard is calculated. The error can be measured in a variety of ways, such as using the mean square error (MSE), absolute error (AE) and other methods to quantify the data deviation. If the error exceeds the second preset standard value, the model calling order needs to be adjusted. After the calling order is adjusted, the model parameters also need to be adjusted, including resetting the model parameters and optimizing the algorithm (such as adjusting the regularization term, learning rate, etc.). If the parameters cannot meet the analysis requirements after adjustment, a more suitable model type is selected to process the data. For example, if the model overfits the data, it is necessary to reduce the error by changing the complexity of the model; if the model is underfitting, it may be necessary to add more variables or change the data preprocessing method. In addition, if only the calling order of the model is adjusted but the model parameters are not adjusted, the preliminary analysis results can also be corrected through multiple iterative optimizations, and the re-obtained initial mathematical model analysis data is ensured to be closer to the second preset standard value. In this process, methods such as cross-validation are used to verify the effect of the adjusted model, ensure that the error has been reduced to a predetermined range, and determine the target calling order to be used. The mathematical model analysis data output after analyzing each model in sequence using the adjusted target calling order will provide a more accurate and reliable basis for the decision-making of enterprise projects.

[0085] In this embodiment, by determining the analysis order of the mathematical analysis model according to the data type and complexity information, and calling the gray theory model, time series model, multivariate linear regression model and variational method model in sequence to perform serial market dynamic analysis, it is possible to ensure a comprehensive and detailed interpretation of the enterprise project operation data under different analysis dimensions and time frames. This process can provide enterprises with multi-angle market insights and help capture potential market trends and changing laws. During the analysis process, if the error information exceeds the preset standard value, the accuracy and stability of the model can be further optimized by adjusting the initial analysis data, thereby improving the reliability of the analysis results. This adjustment mechanism ensures the adaptability and flexibility of the model in a complex market environment, provides accurate and efficient support for corporate decision-making, and helps it make more scientific strategic choices in a changing market.

[0086] In an exemplary embodiment, Figure 7 As shown, according to the mathematical model analysis sequence, the grey theory model, time series model, multivariate linear regression model and variational method model are called to perform serial market dynamic analysis on the enterprise project operation data respectively to obtain the initial mathematical model analysis data, including steps 702 to 708. Among them: Step 702, in which the mathematical model analysis sequentially characterizes the use of the grey theory model, the time series model, the multivariate linear regression model and the variational method model, the basic development trend corresponding to the enterprise project operation data is identified to obtain the enterprise operation development trend data.

[0087] The enterprise operation development trend data may be data obtained by using a grey theory model to identify the basic change direction or pattern of the enterprise operation over a period of time based on the enterprise project operation data.

[0088] Specifically, when the mathematical model analysis sequential characterization uses the gray theory model, time series model, multivariate linear regression model and variational method model in turn, the enterprise project operation data is processed by the gray theory model. Among them, the gray theory model is particularly suitable for processing small amounts of fuzzy, incomplete or uncertain data. It can mine the implicit laws in the data by establishing a gray system. In actual operation, the enterprise project operation data is grayed by the gray generation algorithm to obtain a relatively clear system trend. The processed enterprise project operation data is analyzed using the gray prediction model to deduce future trend changes. In this process, the gray theory model can not only extract potential laws from the existing data, but also provide more accurate future trend predictions. Enterprise operation development trend data identified by the gray model.

[0089] Step 704, analyzing the seasonal fluctuations of the enterprise operation development trend data to obtain the enterprise operation development fluctuation data.

[0090] Among them, the enterprise operation and development fluctuation data can be data that analyzes the short-term fluctuations or volatility caused by external factors such as market environment, policy changes, and customer demand fluctuations during the enterprise operation process.

[0091] Specifically, a detailed seasonal fluctuation analysis is conducted on the enterprise operation development trend data through a time series model. Seasonal fluctuation analysis refers to analyzing the regular fluctuations in the enterprise operation development trend data within certain cycles (such as quarters or months), which are usually greatly affected by external environmental factors (such as market demand, weather changes, etc.). To this end, the seasonal decomposition method is used to decompose the enterprise operation development trend data into trend components, seasonal components, and residual components. For example, by using the classic seasonal decomposition method (such as STL decomposition), the fluctuation amplitude in each seasonal cycle can be extracted to help enterprises understand which months or quarters have the most significant fluctuations. The enterprise operation development fluctuation data obtained after fluctuation analysis can reveal the impact of seasonal fluctuations on enterprise operations, and further help enterprises predict possible fluctuation trends in the future.

[0092] Step 706, introduce the necessary influencing variables and accidental influencing variables corresponding to the target enterprise, perform regression analysis on the enterprise operation and development fluctuation data, and obtain the enterprise operation and development regression data.

[0093] Among them, the enterprise operation and development regression data can be the enterprise operation results obtained by regression analysis method when analyzing the enterprise operation and development fluctuation data, combining inevitable influencing variables (such as industry trends, policy changes, etc.) and accidental influencing variables (such as market emergencies, competitive situation, etc.).

[0094] Specifically, the necessary influencing variables (such as production capacity, market demand, number of employees, supply chain efficiency, etc.) and accidental influencing variables (such as policy changes, emergencies, natural disasters, etc.) corresponding to the target enterprise are used as independent variables of the multiple regression analysis model, and the enterprise operation development fluctuation data is used as the dependent variable of the multiple regression analysis model to construct a multiple regression analysis model. Through multiple regression analysis, the relationship between each variable and the enterprise operation fluctuation is determined, and the regression coefficients are estimated. These coefficients reflect the intensity and direction of the influence of each variable on the dependent variable. During the analysis process, the multiple regression analysis model can fit the best regression equation through the least squares method (OLS) or other optimization algorithms to help identify which factors have a significant impact on the enterprise operation fluctuation. The final multiple regression analysis results will generate enterprise operation development regression data.

[0095] Step 708, using the enterprise project target information and market project constraints as limiting information, optimizing the enterprise operation and development regression data to obtain initial mathematical model analysis data.

[0096] Specifically, the limited information is set according to the enterprise project target information (such as profit maximization, cost minimization, etc.) and market project constraints (such as resource allocation constraints, production capacity constraints, capital budget, etc.). In the specific analysis, the enterprise operation regression data is first used as the input of the variational model, and the objective function (such as maximizing revenue or minimizing cost) is defined, and the enterprise's limited information is used as a constraint. Then, through the variational solution process, the optimal solution that maximizes or minimizes the objective function is calculated. These solutions represent the best strategy for enterprise operation under specific constraints. The variational model can handle complex and nonlinear problems and find the optimal solution. Finally, the result after variational optimization will be used as the initial mathematical model analysis data to formulate the best operation strategy that meets the enterprise's goals and market environment.

[0097] Among them, the mathematical formula for analyzing seasonal fluctuations corresponding to the time series model is:

[0098] in, is the result of the uncorrected seasonal fluctuation analysis, The historical data of enterprise operation and development trend data is traversed to obtain the previous The data at each moment is obtained. is the autoregressive coefficient, estimated by the least squares method or maximum likelihood estimation method, usually obtained by data fitting during modeling. is the sliding average coefficient, estimated by the least squares method or maximum likelihood estimation method, and usually obtained by data fitting during modeling. is the white noise error, which is obtained by the difference between the actual value of the historical data of the enterprise operation development trend data and the historical data calculated by the model. External influencing parameters are collected from external data sources (such as policies, market activities, weather, etc.) and integrated into the model. is the external influence weighting coefficient, which is determined based on the error at the previous time point and the intensity of the current external factors. is the seasonal correction factor, which is calculated from the seasonal pattern in the historical data. is the trend adjustment value of the previous moment. The data at each moment is calculated using an exponential smoothing algorithm. is the smoothing coefficient, which is determined by cross-validation or minimization of error, and usually ranges from 0 to 1.

[0099] In this embodiment, by using the gray theory model, time series model, multivariate linear regression model and variational method model in sequence, the enterprise project operation data is deeply analyzed, which can comprehensively identify and reveal the basic development trend, seasonal fluctuations and key influencing factors of the enterprise operation. First, identifying the enterprise operation development trend data helps to reveal the long-term development direction and help enterprises foresee future trends; secondly, through the analysis of operation fluctuation data, seasonal fluctuations can be accurately captured, providing enterprises with flexible response strategies in uncertain market environments; further introduce inevitable and accidental influencing variables, accurately quantify the specific impact of external factors on operations through regression analysis, and optimize the decision-making process of enterprises. Finally, combined with the enterprise project target information and market constraints for optimization and adjustment, it can ensure that the model analysis results are more in line with actual needs, and provide enterprises with practical strategic suggestions and resource allocation plans, thereby enhancing their competitiveness and decision-making efficiency in a complex market environment.

[0100] In an exemplary embodiment, Figure 8 As shown, when the error information of the mathematical model analysis data exceeds the second preset standard value, the initial mathematical model analysis data is adjusted to obtain the mathematical model analysis data, including steps 802 to 808. Among them: Step 802, traversing each mathematical model sequence to adjust information according to the difference between the initial mathematical model analysis data and the second preset standard value.

[0101] The mathematical model sequence adjustment information can be used to adjust the order of model application or execution priority according to the performance, applicability and interrelationship of each mathematical model during the analysis process. Such adjustment information is usually evaluated based on the feedback of model errors, the efficiency of each model in processing data and its impact on the results.

[0102] Specifically, the difference (such as error, deviation, etc.) between the initial mathematical model analysis data and the preset second standard value is calculated, that is, the difference reflects the degree of deviation between the initial mathematical model analysis data and the expected target, wherein the second preset standard value can be the industry average, historical performance or other benchmark data. If the error exceeds the set threshold (that is, the error exceeds the second preset standard value), it indicates that the prediction result of the initial model may not meet expectations. Traverse the possible sequential combinations of each mathematical analysis model. The possible sequential combination of a mathematical analysis model is used as a mathematical model sequence adjustment information, and the mathematical model sequence adjustment information corresponding to the possible sequential combination of each mathematical analysis model is obtained.

[0103] Step 804, adjusting the mathematical model analysis order according to the order adjustment information of each mathematical model to obtain the adjustment order of each mathematical model.

[0104] The mathematical model adjustment order may be the order after the model application order is actually adjusted based on the evaluation of the “mathematical model order adjustment information”.

[0105] Specifically, according to the order adjustment information of each mathematical model, the calling order of each mathematical analysis model is adjusted respectively. Specifically, this includes rearranging or recombining the calling order of the grey theory model, time series model, multivariate linear regression model and variational method model to obtain the adjustment order of each mathematical model, wherein the purpose of adjusting the order is to optimize the analysis process to reduce errors or deviations and maximize the accuracy of the analysis results. For example, some models may be more sensitive to data changes in the early steps, while other models may be more suitable for application in the later stages of data processing, so it is necessary to flexibly adjust the analysis order according to the characteristics of the data.

[0106] Step 806, according to the mathematical model analysis sequence, respectively call the image analysis sub-model, the nonlinear analysis sub-model and the reinforcement analysis sub-model to perform serial market dynamic analysis on the enterprise project operation data to obtain the analysis data of each adjusted mathematical model.

[0107] The adjustment of the mathematical model analysis data may be to re-execute the model and generate new analysis data after the mathematical model sequence is adjusted and optimized. By adjusting the execution sequence or parameter configuration of the model, the obtained analysis data will be corrected and optimized according to the new model combination and sequence.

[0108] Specifically, according to the adjustment order of each mathematical model, the grey theory model, time series model, multivariate linear regression model and variational method model are re-called in parallel to analyze the enterprise project operation data in turn. Specifically, based on the adjusted order, each model is called in series to conduct a step-by-step in-depth analysis of the data in turn. Through the adjusted analysis, each new "adjusted mathematical model analysis data" is obtained. These data will present their own perspectives under different models, helping decision makers to fully understand market dynamics and operation trends.

[0109] Step 808 , respectively comparing the differences between the initial mathematical model analysis data and each adjusted mathematical model analysis data and the second preset standard value, and selecting the analysis data with the smallest difference as the mathematical model analysis data.

[0110] Specifically, an error or deviation measurement method (such as mean square error, absolute error, etc.) is used to compare the size of the difference between each adjusted mathematical model analysis data and the second preset standard value, forming a difference value set including the size of the difference between the initial mathematical model analysis data and the second preset standard value. The analysis data with the smallest difference value from the second preset standard value is selected from the difference value set as the final mathematical model analysis data. The purpose of the selection is to ensure that the final analysis result best meets the expected goal, minimize analysis errors, and provide the most accurate and reliable data support for subsequent decision-making.

[0111] In this embodiment, by traversing the difference between the mathematical model analysis data and the second preset standard value, and optimizing the model analysis process according to the adjustment order, the accuracy and adaptability of the mathematical model analysis results can be significantly improved. The adjusted analysis order effectively reduces errors and deviations and improves the accuracy of data analysis by refining and optimizing the role of each model. This process enables each model to better play its strengths in serial market dynamic analysis, fully capturing and explaining the changing trends in the data. Finally, by comparing the differences between the adjusted model analysis data and the preset standard values, and selecting the analysis results with the smallest differences, the accuracy of the enterprise's decision-making basis is ensured, thereby providing enterprises with more accurate operational insights, optimizing resource allocation and strategic decisions, and thus improving competitiveness and stability in a complex market environment.

[0112] In an exemplary embodiment, Fig. 9As shown, the target information of each enterprise project and the constraint conditions of each market project are used as limiting information, and resource utilization analysis is performed according to each network model analysis data and each mathematical model analysis data to obtain the enterprise operation analysis results, including steps 902 to 906. Among them: Step 902, using the project target information of each enterprise and the constraint conditions of each market project as limiting information, construct a resource analysis objective function corresponding to the target enterprise.

[0113] The resource analysis objective function may be a mathematical model used to quantify the resource allocation objectives of an enterprise under specific operating conditions.

[0114] Specifically, a resource analysis objective function is constructed based on the enterprise project goal information and market project constraints. Enterprise project goal information may include goals such as cost control, profit maximization, and market share expansion, while market project constraints may involve budget constraints, resource availability, time constraints, etc. This information will be used as the constraints and optimization goals of the objective function to define a resource analysis objective function that can be quantified and solved. The purpose of the resource analysis objective function is to find the best solution for resource allocation within a framework that meets various conditions and goals. When constructing a resource analysis objective function, it is necessary to ensure that it can comprehensively consider multiple factors and constraints and accurately reflect the resource needs and goals of the enterprise in actual operations.

[0115] Step 904, solving the resource analysis objective function, and obtaining each solved operation analysis result corresponding to any resource allocation stage.

[0116] Among them, the resource allocation stage can be a number of time periods or decision-making stages divided according to different needs and goals during the operation of the enterprise.

[0117] The operational analysis results may be solved by an optimization algorithm or a mathematical model solving process to obtain the resource allocation status and operational performance data of each resource allocation stage.

[0118] Specifically, the resource analysis objective function is solved, where the solution process usually uses numerical optimization methods (such as linear programming, nonlinear programming or other mathematical optimization techniques) to find the optimal solution or approximate optimal solution. By solving the resource analysis objective function, the operational analysis results corresponding to each resource allocation stage can be obtained. These results reflect the best resource allocation strategy that the enterprise should adopt at each stage under given resource constraints and target conditions. For example, one stage may need to optimize the allocation of production resources, while another stage may focus on the effective configuration of marketing resources.

[0119] Step 906, finding the Pareto front in each solved operation analysis result corresponding to any resource allocation stage to obtain the enterprise operation analysis result.

[0120] Specifically, after obtaining the operational analysis results corresponding to each resource allocation stage, the next step is to find the Pareto front among these results. The Pareto front refers to the situation where no solution among multiple optimization objectives is superior to other solutions in all objectives at the same time. By analyzing the relative advantages and disadvantages of each solution, a set of Pareto optimal solutions can be found, representing the most balanced and irreplaceable resource allocation solutions under different objectives. At each stage of resource allocation, finding the Pareto front can help enterprises determine the optimal solution under multi-objective optimization, and ultimately obtain the results of enterprise operation analysis, providing enterprises with feasible resource allocation strategies to maximize their comprehensive benefits or achieve the best operational performance under multiple constraints.

[0121] In this embodiment, by defining the enterprise project target information and market project constraints, a resource analysis objective function is constructed, which can provide the enterprise with a clear resource allocation framework to ensure the optimal allocation of resources. By solving the objective function, operational analysis results can be obtained at different stages of resource allocation, thereby providing support for the enterprise's decision-making in specific operational links. Furthermore, finding the Pareto frontier in the analysis results of each stage helps to identify the optimal balance point between resource utilization and effect, avoiding waste of resources or inefficient effects. This process not only improves the efficiency of resource allocation, but also enhances the enterprise's operational decision-making ability under multi-objective and multi-constraint conditions, and promotes the enterprise to achieve sustained growth and long-term success in a highly competitive market environment.

[0122] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0123] Based on the same inventive concept, the embodiment of the present application also provides a device for processing enterprise project information data for implementing the above-mentioned method for processing enterprise project information data. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiments of one or more device for processing enterprise project information data provided below can refer to the limitations of the method for processing enterprise project information data above, and will not be repeated here.

[0124] In an exemplary embodiment, Fig.10 As shown, a device for processing enterprise project information data is provided, including: a data acquisition module 1002, a model determination module 1004, a data analysis module 1006, and a strategy generation module 1008, wherein: The data acquisition module 1002 is used to acquire enterprise project operation data, enterprise project target information and market project constraints corresponding to the target enterprise; Model determination module 1004, used to determine each network analysis model and each mathematical analysis model corresponding to the target enterprise according to the data type and data complexity information of the enterprise project operation data; The data analysis module 1006 is used to use each network analysis model to perform serial market dynamic analysis on the enterprise project operation data to obtain network model analysis data; The data analysis module 1006 is also used to use various mathematical analysis models to perform serial market dynamic analysis on the enterprise project operation data to obtain mathematical model analysis data; The strategy generation module 1008 is used to use the target information of each enterprise project and the constraints of each market project as limiting information, perform resource utilization analysis based on the network model analysis data and the mathematical model analysis data, and obtain the enterprise operation analysis results; the enterprise operation analysis results are used to generate the enterprise operation analysis strategy; wherein, using the target information of each enterprise project and the constraints of each market project as limiting information, perform resource utilization analysis based on the network model analysis data and the mathematical model analysis data to obtain the enterprise operation analysis results, including: using the target information of each enterprise project and the constraints of each market project as limiting information, constructing the resource analysis objective function corresponding to the target enterprise; solving the resource analysis objective function to obtain the solved operation analysis results corresponding to any resource allocation stage; finding the Pareto front in the solved operation analysis results corresponding to any resource allocation stage to obtain the enterprise operation analysis results.

[0125] In one embodiment, the data analysis module 1006 is also used to determine the network model analysis order corresponding to each network analysis model according to the data type and data complexity information; according to the network model analysis order, call the image analysis sub-model, the nonlinear analysis sub-model and the reinforcement analysis sub-model to perform serial market dynamics analysis on the enterprise project operation data respectively to obtain initial network model analysis data; according to the difference between the initial network model analysis data and the first preset standard value, adjust the initial network model analysis data to obtain network model analysis data.

[0126] In one embodiment, the data analysis module 1006 is also used to identify the graph structure dependency relationship corresponding to the enterprise project operation data when the network model analysis sequential representation uses the image analysis sub-model, the nonlinear analysis sub-model and the reinforcement analysis sub-model in sequence to obtain node-edge embedding data; perform nonlinear transformation on the node-edge embedding data to obtain nonlinear operation analysis results; and maximize long-term reward adjustments to the nonlinear operation analysis results based on the industry environment data corresponding to the target enterprise to obtain initial network model analysis data.

[0127] In one embodiment, the data analysis module 1006 is also used to traverse each network model sequence adjustment information according to the difference between the initial network model analysis data and the first preset standard value; according to each network model sequence adjustment information, the network model analysis sequence is adjusted respectively to obtain each network model adjustment sequence; according to each network model adjustment sequence, the image analysis sub-model, the nonlinear analysis sub-model and the reinforcement analysis sub-model are called respectively to perform a serial market dynamic analysis on the enterprise project operation data to obtain each adjusted network model analysis data; the initial network model analysis data and each adjusted network model analysis data are compared with the first preset standard value respectively, and the analysis data with the smallest difference is selected as the network model analysis data.

[0128] In one embodiment, the data analysis module 1006 is also used to determine the mathematical model analysis order corresponding to each mathematical analysis model according to the data type and data complexity information; according to the mathematical model analysis order, call the grey theory model, time series model, multivariate linear regression model and variational method model to perform serial market dynamics analysis on the enterprise project operation data respectively to obtain initial mathematical model analysis data; when the error information of the mathematical model analysis data exceeds the second preset standard value, adjust the initial mathematical model analysis data to obtain mathematical model analysis data.

[0129] In one embodiment, the data analysis module 1006 is also used to identify the basic development trends corresponding to the enterprise project operation data when the mathematical model analysis sequence is represented by using the grey theory model, time series model, multivariate linear regression model and variational method model in sequence, so as to obtain the enterprise operation development trend data; analyze the seasonal fluctuations of the enterprise operation development trend data to obtain the enterprise operation development fluctuation data; introduce the necessary influencing variables and accidental influencing variables corresponding to the target enterprise, and perform regression analysis on the enterprise operation development fluctuation data to obtain the enterprise operation development regression data; use the enterprise project target information and market project constraints as limiting information, optimize the enterprise operation development regression data, and obtain the initial mathematical model analysis data.

[0130] In one embodiment, the data analysis module 1006 is also used to traverse the order adjustment information of each mathematical model according to the difference between the initial mathematical model analysis data and the second preset standard value; according to the order adjustment information of each mathematical model, the mathematical model analysis order is adjusted respectively to obtain the adjustment order of each mathematical model; according to the mathematical model analysis order, the grey theory model, the time series model, the multivariate linear regression model and the variational method model are called respectively to perform a series market dynamic analysis on the enterprise project operation data to obtain each adjusted mathematical model analysis data; respectively compare the initial mathematical model analysis data and the differences between each adjusted mathematical model analysis data and the second preset standard value, and select the analysis data with the smallest difference as the mathematical model analysis data.

[0131] Each module in the above-mentioned device for processing enterprise project information data can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0132] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.11 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store server data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for processing enterprise project information data is implemented.

[0133] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0134] A system for processing enterprise project information data includes: a computer device, wherein the computer device includes a memory and a processor, the memory includes a storage medium, the storage medium stores a computer program, and the processor implements any one of the enterprise project information data processing methods when executing the computer program.

[0135] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0136] In one embodiment, a storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0137] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a storage medium. A processor of a computer device reads the computer instructions from the storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0138] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0139] 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 the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0140] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0141] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for processing enterprise project information data, characterized in that: The method comprises: Obtain enterprise project operation data, enterprise project target information and market project constraints corresponding to the target enterprise; Determine each network analysis model and each mathematical analysis model corresponding to the target enterprise according to the data type and data complexity information of the enterprise project operation data; Using each of the network analysis models, respectively conduct serial market dynamic analysis on the enterprise project operation data to obtain network model analysis data; Using each of the mathematical analysis models, respectively perform the series market dynamic analysis on the enterprise project operation data to obtain mathematical model analysis data; Using the target information of each enterprise project and the constraint conditions of each market project as limiting information, performing resource utilization analysis according to the network model analysis data and the mathematical model analysis data, and obtaining enterprise operation analysis results; the enterprise operation analysis results are used to generate enterprise operation analysis strategies; The target information of each enterprise project and the constraint conditions of each market project are used as limiting information, and resource utilization analysis is performed according to each network model analysis data and each mathematical model analysis data to obtain enterprise operation analysis results, including: Using the target information of each enterprise project and the constraint conditions of each market project as limiting information, constructing a resource analysis target function corresponding to the target enterprise; Solving the resource analysis objective function to obtain various solved operation analysis results corresponding to any resource allocation stage; The Pareto front is found in each of the solved operation analysis results corresponding to any resource allocation stage to obtain the enterprise operation analysis result.

2. The method according to claim 1, characterized in that Each of the network analysis models includes an image analysis sub-model, a nonlinear analysis sub-model and an enhanced analysis sub-model; Using each of the network analysis models, the enterprise project operation data is respectively subjected to serial market dynamic analysis to obtain network model analysis data, including: Determining a network model analysis order corresponding to each network analysis model according to the data type and the data complexity information; According to the network model analysis sequence, the image analysis sub-model, the nonlinear analysis sub-model and the reinforcement analysis sub-model are called to respectively perform serial market dynamic analysis on the enterprise project operation data to obtain initial network model analysis data; According to the difference between the initial network model analysis data and the first preset standard value, the initial network model analysis data is adjusted to obtain the network model analysis data.

3. The method according to claim 2, characterized in that According to the network model analysis sequence, the image analysis sub-model, the nonlinear analysis sub-model and the reinforcement analysis sub-model are called to respectively perform serial market dynamic analysis on the enterprise project operation data to obtain initial network model analysis data, including: In the case where the network model analysis sequence representation sequentially uses the image analysis sub-model, the nonlinear analysis sub-model, and the reinforcement analysis sub-model, the graph structure dependency relationship corresponding to the enterprise project operation data is identified to obtain node-edge embedding data; Performing a nonlinear transformation on the node-edge embedding data to obtain a nonlinear operation analysis result; According to the industry environment data corresponding to the target enterprise, the nonlinear operation analysis result is adjusted to maximize the long-term reward to obtain the initial network model analysis data.

4. The method according to claim 2, characterized in that: The step of adjusting the initial network model analysis data according to the difference between the initial network model analysis data and the first preset standard value to obtain the network model analysis data includes: According to the difference between the initial network model analysis data and the first preset standard value, traversing each network model sequence adjustment information; According to the network model sequence adjustment information, the network model analysis sequence is adjusted respectively to obtain the adjustment sequence of each network model; According to the adjustment order of each of the network models, the image analysis sub-model, the nonlinear analysis sub-model and the reinforcement analysis sub-model are respectively called to perform the series market dynamic analysis on the enterprise project operation data to obtain analysis data of each adjusted network model; The differences between the initial network model analysis data and each of the adjusted network model analysis data and the first preset standard value are respectively compared, and the analysis data with the smallest difference is selected as the network model analysis data.

5. The method according to claim 1, characterized in that Each of the mathematical analysis models includes a grey theory model, a time series model, a multivariate linear regression model and a variational method model; each of the mathematical analysis models is used to perform the serial market dynamic analysis on the enterprise project operation data to obtain mathematical model analysis data, including: Determining a mathematical model analysis order corresponding to each of the mathematical analysis models according to the data type and the data complexity information; According to the mathematical model analysis sequence, the grey theory model, the time series model, the multivariate linear regression model and the variational method model are called to respectively perform the series market dynamic analysis on the enterprise project operation data to obtain initial mathematical model analysis data; When the error information of the mathematical model analysis data exceeds a second preset standard value, the initial mathematical model analysis data is adjusted to obtain the mathematical model analysis data.

6. The method according to claim 5, characterized in that According to the mathematical model analysis sequence, the grey theory model, the time series model, the multivariate linear regression model and the variational method model are called to respectively perform serial market dynamic analysis on the enterprise project operation data to obtain initial mathematical model analysis data, including: In the case where the mathematical model analysis sequence characterization uses the grey theory model, the time series model, the multivariate linear regression model and the variational method model in sequence, the development basic trend corresponding to the enterprise project operation data is identified to obtain enterprise operation development trend data; Analyze the seasonal fluctuations of the enterprise operation development trend data to obtain enterprise operation development fluctuation data; Introducing the necessary influencing variables and accidental influencing variables corresponding to the target enterprise, performing regression analysis on the enterprise operation and development fluctuation data, and obtaining the enterprise operation and development regression data; Taking the enterprise project target information and the market project constraint conditions as limiting information, optimizing the enterprise operation and development regression data to obtain the initial mathematical model analysis data; Among them, the mathematical formula for analyzing the seasonal fluctuations corresponding to the time series model is: ， in, is the result of the uncorrected seasonal fluctuation analysis, Provide historical data of enterprise operation development trend data, is the autoregression coefficient, is the sliding average coefficient, is the white noise error, is the external influencing parameter, is the external impact weighting coefficient, is the seasonal correction factor, is the trend adjustment value of the previous moment, is the smoothing coefficient.

7. The method according to claim 5, characterized in that When the error information of the mathematical model analysis data exceeds a second preset standard value, adjusting the initial mathematical model analysis data to obtain the mathematical model analysis data includes: According to the difference between the initial mathematical model analysis data and the second preset standard value, traversing each mathematical model sequence to adjust the information; According to the mathematical model sequence adjustment information, the mathematical model analysis sequence is adjusted respectively to obtain the mathematical model adjustment sequence; According to the mathematical model analysis sequence, the grey theory model, the time series model, the multivariate linear regression model and the variational method model are respectively called to perform a series market dynamic analysis on the enterprise project operation data to obtain the analysis data of each adjusted mathematical model; The differences between the initial mathematical model analysis data and each of the adjusted mathematical model analysis data and the second preset standard value are compared respectively, and the analysis data with the smallest difference is selected as the mathematical model analysis data.

8. A device for processing enterprise project information data, characterized in that: The device comprises: The data acquisition module is used to obtain the enterprise project operation data, enterprise project target information and market project constraints corresponding to the target enterprise; A model determination module, used to determine each network analysis model and each mathematical analysis model corresponding to the target enterprise according to the data type and data complexity information of the enterprise project operation data; A data analysis module, used to use each of the network analysis models to perform serial market dynamic analysis on the enterprise project operation data to obtain network model analysis data; The data analysis module is further used to use each of the mathematical analysis models to perform the series market dynamic analysis on the enterprise project operation data to obtain mathematical model analysis data; A strategy generation module is used to use the target information of each enterprise project and the constraint conditions of each market project as limiting information, perform resource utilization analysis according to the network model analysis data and the mathematical model analysis data, and obtain enterprise operation analysis results; the enterprise operation analysis results are used to generate enterprise operation analysis strategies; The target information of each enterprise project and the constraint conditions of each market project are used as limiting information, and resource utilization analysis is performed according to each network model analysis data and each mathematical model analysis data to obtain enterprise operation analysis results, including: Using the target information of each enterprise project and the constraint conditions of each market project as limiting information, constructing a resource analysis target function corresponding to the target enterprise; Solving the resource analysis objective function to obtain various solved operation analysis results corresponding to any resource allocation stage; The Pareto front is found in each of the solved operation analysis results corresponding to any resource allocation stage to obtain the enterprise operation analysis result.

9. A system for processing enterprise project information data, characterized in that: The system comprises: a computer device, wherein the computer device comprises a memory and a processor, the memory comprises a storage medium, the storage medium stores a computer program, and is characterized in that when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

Images