Operation information prediction method and device based on enterprise project informatization data

Abstract

The invention relates to an operation information prediction method and device based on enterprise project informatization data. The method comprises the steps of obtaining project structured data, project unstructured data and project field standard data of an enterprise project; taking the project field standard data as a causal relationship constraint condition, and constructing a project causal graph of the enterprise project according to the project structured data and the project unstructured data; reasoning the operation information of the enterprise project according to a causal relationship among variables in the project causal graph to obtain operation information reasoning data; and performing causal intervention analysis on the operation information reasoning data to obtain operation information prediction data of the enterprise project. By adopting the method, the adaptive capacity of sudden changes and complex market environments can be effectively improved, so that refinement and intelligentization of project management are realized, and enterprises are promoted to improve the overall operation efficiency and market competitiveness.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for predicting business information based on enterprise project information data. Background Art

[0002] In traditional technology, the future business conditions of enterprises are mainly predicted by analyzing historical data and market trends. The analysis process usually relies on statistics and mathematical models, such as time series analysis and regression analysis. Through detailed analysis of records of past business activities, the trend of changes in key indicators such as future sales, costs, and profits is inferred. The core is to assume that past trends and patterns will continue to a certain extent in the future, so it can help enterprises to make resource allocation, risk management and decision-making plans in advance. However, traditional methods rely more on linear assumptions and the stability of past data, and are not able to adapt to sudden changes and complex market environments. Summary of the invention

[0003] Based on this, it is necessary to provide a business information forecasting method, device and computer equipment based on enterprise project information data that can effectively improve the ability to adapt to sudden changes and complex market environments in order to address the above technical problems.

[0004] In a first aspect, the present application provides a method for predicting business information based on enterprise project information data, comprising: Acquire project structured data, project unstructured data, and project domain standard data of enterprise projects; Using the project domain standard data as causal relationship constraints, and constructing a project causal graph of the enterprise project according to the project structured data and the project unstructured data; Inferring the business information of the enterprise project according to the causal relationship between the variables in the project causal graph to obtain business information inference data; Performing causal intervention analysis on the business information inference data to obtain business information forecast data of the enterprise project; The step of performing causal intervention analysis on the business information inference data to obtain the business information forecast data of the enterprise project includes: According to the project structured data, the project unstructured data and the project field standard data, setting various decision optimization goals of the enterprise project; According to each of the decision optimization goals, causal intervention analysis is performed on the business information reasoning data to obtain each business decision intervention data; Analyze the resources of the enterprise project according to each of the business decision intervention data to generate the business information forecast data; The mobilization analysis of the resources of the enterprise project according to each of the business decision intervention data to generate the business information forecast data includes: Using an intervention data optimization algorithm to optimize the business decision intervention data, to obtain the optimal intervention data combination; According to the optimal intervention data combination, virtually scheduling the resources of the enterprise project to obtain resource virtual scheduling data; When the resource virtual scheduling data indicates that the enterprise project still has a project resource output value lower than the set resource output value, adjusting each of the decision optimization targets based on the project field standard data to obtain each adjusted optimization target; Taking each of the adjustment optimization targets as each of the decision optimization targets, returning to the step of performing causal intervention analysis on the business information inference data according to each of the decision optimization targets to obtain each of the business decision intervention data; Until the resource virtual scheduling data indicates that the enterprise project has a resource output value that is higher than the set resource output value, the current resource scheduling efficiency is calculated according to the current physical resource scheduling capacity data and the current virtual resource scheduling capacity data of the enterprise project; The business information forecast data is generated according to the resource virtual scheduling data and the current resource scheduling efficiency.

[0005] In a second aspect, the present application also provides a business information prediction device based on enterprise project information data, comprising: Project data acquisition module, used to acquire project structured data, project unstructured data and project field standard data of enterprise projects; A cause-effect diagram construction module, used to construct a project cause-effect diagram of the enterprise project based on the project structured data and the project unstructured data, using the project domain standard data as cause-effect constraint conditions; An operating information prediction module is used to infer the operating information of the enterprise project according to the causal relationship between the variables in the project causal diagram to obtain operating information inference data; An operating information intervention module, used to perform causal intervention analysis on the operating information inference data to obtain operating information forecast data of the enterprise project; The step of performing causal intervention analysis on the business information inference data to obtain the business information forecast data of the enterprise project includes: According to the project structured data, the project unstructured data and the project field standard data, setting various decision optimization goals of the enterprise project; According to each of the decision optimization goals, causal intervention analysis is performed on the business information reasoning data to obtain each business decision intervention data; Analyze the resources of the enterprise project according to each of the business decision intervention data to generate the business information forecast data; The mobilization analysis of the resources of the enterprise project according to each of the business decision intervention data to generate the business information forecast data includes: Using an intervention data optimization algorithm to optimize the business decision intervention data, to obtain the optimal intervention data combination; According to the optimal intervention data combination, virtually scheduling the resources of the enterprise project to obtain resource virtual scheduling data; When the resource virtual scheduling data indicates that the enterprise project still has a project resource output value lower than the set resource output value, adjusting each of the decision optimization targets based on the project field standard data to obtain each adjusted optimization target; Taking each of the adjustment optimization targets as each of the decision optimization targets, returning to the step of performing causal intervention analysis on the business information inference data according to each of the decision optimization targets to obtain each of the business decision intervention data; Until the resource virtual scheduling data indicates that the enterprise project has a resource output value that is higher than the set resource output value, the current resource scheduling efficiency is calculated according to the current physical resource scheduling capacity data and the current virtual resource scheduling capacity data of the enterprise project; The business information forecast data is generated according to the resource virtual scheduling data and the current resource scheduling efficiency.

[0006] In a third aspect, the present application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements any step of a method for predicting business information based on enterprise project information data.

[0007] The above-mentioned method, device and computer equipment for predicting business information based on enterprise project information data obtains project structured data, project unstructured data and project field standard data of the enterprise project; uses the project field standard data as the causal relationship constraint condition, and constructs the project causal graph of the enterprise project according to the project structured data and the project unstructured data; infers the business information of the enterprise project according to the causal relationship between the variables in the project causal graph to obtain the business information inference data; performs causal intervention analysis on the business information inference data to obtain the business information prediction data of the enterprise project; wherein, performing causal intervention analysis on the business information inference data to obtain the business information prediction data of the enterprise project includes: setting each decision optimization target of the enterprise project according to the project structured data, the project unstructured data and the project field standard data; performing causal intervention analysis on the business information inference data according to each decision optimization target to obtain each business decision intervention data; performing resource mobilization analysis on the enterprise project according to each business decision intervention data to generate business information prediction data; wherein, The resources of the enterprise project are mobilized and analyzed according to each business decision intervention data to generate business information prediction data, including: using an intervention data optimization algorithm to optimize from each business decision intervention data to obtain the optimal intervention data combination; based on the optimal intervention data combination, the resources of the enterprise project are virtually scheduled to obtain resource virtual scheduling data; when the resource virtual scheduling data indicates that the enterprise project still has a project resource output value lower than the set resource output value, based on the project field standard data, each decision optimization target is adjusted to obtain each adjusted optimization target; each adjusted optimization target is used as each decision optimization target, and the execution is returned to perform causal intervention analysis on the business information reasoning data according to each decision optimization target to obtain each business decision intervention data; until the resource virtual scheduling data indicates that the enterprise project has a project resource output value higher than the set resource output value, the current resource scheduling efficiency is calculated according to the current physical resource scheduling capacity data and the current virtual resource scheduling capacity data of the enterprise project; and the business information prediction data is generated according to the resource virtual scheduling data and the current resource scheduling efficiency.

[0008] By acquiring and integrating the structured data, unstructured data and domain standard data of enterprise projects, a project causal diagram is constructed to systematically reveal the causal relationship between the variables in the project; further combining causal relationships and causal reasoning to conduct in-depth analysis of project management information helps to identify the key factors that affect project results, thereby providing enterprises with more accurate business insights and decision support; finally, causal intervention analysis of business information can simulate the impact of different intervention measures on project performance and foresee possible business risks and opportunities in advance. This data-driven causal reasoning and intervention analysis improves the accuracy of predictions, provides scientific basis for enterprises in resource allocation, risk control, etc., and can effectively improve the ability to adapt to sudden changes and complex market environments, thereby realizing the refinement and intelligence of project management and promoting enterprises to improve overall operational efficiency and market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] 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.

[0010] Figure 1 An application environment diagram of a method for predicting business information based on enterprise project information data in one embodiment; Figure 2 It is a flowchart of a method for predicting business information based on enterprise project information data in one embodiment; Figure 3 A schematic diagram of a flow chart of a method for obtaining business information inference data in one embodiment; Figure 4 A schematic diagram of a flow chart of a method for optimizing causal relationship data in one embodiment; Figure 5 A schematic diagram of a process for obtaining causal relationship reasoning data in one embodiment; Figure 6 A schematic diagram of a process of constructing a project cause-effect diagram in one embodiment; Figure 7 A schematic diagram of a process of constructing a project cause-effect diagram in another embodiment; Figure 8 A schematic diagram of a flow chart of a method for obtaining business information prediction data in one embodiment; Fig. 9 A schematic diagram of a flow chart of a method for generating business information forecast data in one embodiment; Fig.10It is a structural block diagram of a business information prediction device based on 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

[0011] 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.

[0012] The present application provides a method for predicting business information based on enterprise project information data, which can be applied to Figure 1 In 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 project structured data, project unstructured data and project domain standard data of the enterprise project through the terminal 102; using the project domain standard data as the causal constraint condition, according to the project structured data and the project unstructured data, construct the project causal graph of the enterprise project; according to the causal relationship between the variables in the project causal graph, the business information of the enterprise project is inferred to obtain the business information inference data; the business information inference data is subjected to causal intervention analysis to obtain the business information prediction data of the enterprise project. Among them, the server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0013] In an exemplary embodiment, Figure 2 As shown in the figure, a business information forecasting method based on enterprise project information data is provided. Figure 1 The server in the example is used to illustrate, including the following steps 202 to 208. Among them: Step 202: Acquire project structured data, project unstructured data, and project domain standard data of the enterprise project.

[0014] Among them, an enterprise project can be a series of activities carried out by an enterprise to achieve a specific goal or task, usually with a clear time frame, budget constraints and specific resource allocation.

[0015] Among them, project structured data can be data stored in a standardized and well-organized format, usually in the form of tables, databases or electronic forms. Such data has clear fields and attributes, such as project budget, schedule, personnel allocation, progress status, cost, etc., which is easy to calculate, count and analyze.

[0016] Among them, project unstructured data can be data that cannot be stored and processed in traditional tables, usually in the form of text, images, audio, video, etc. These data include project reports, meeting minutes, emails, contract documents, design drawings, project team discussions, etc., and usually contain rich background information and situation descriptions.

[0017] Among them, project field standard data can be standards, specifications, laws and regulations, and best practices that are generally recognized and followed in a specific industry or field.

[0018] Specifically, three different types of data are obtained from enterprise projects. The first type is structured data, such as project financial data (budget, expenditure, income, etc.), time data (project plan, progress, duration, etc.), resource data (manpower, equipment, materials, etc.) and results data (project deliverables, quality control, etc.); these data usually exist in the form of tables or databases and can be directly used for analysis and modeling. The second type is unstructured data, such as project-related documents, meeting minutes, emails, design drawings, reports, etc.; these data contain detailed information on discussions, decisions and actions of all parties in the project, which can provide important background and context for subsequent analysis. Finally, the third type of project field standard data, which includes industry standards, laws and regulations, technical specifications, etc., is used as a constraint when analyzing causal relationships to ensure that the constructed causal model is consistent with the actual industry environment. For example, projects in the construction industry may be subject to safety standards, relevant regulations on building materials, etc., while IT projects may be limited by technical standards for software development and project management methodology.

[0019] Step 204 , using the project domain standard data as causal relationship constraints, and based on the project structured data and the project unstructured data, construct a project causal graph of the enterprise project.

[0020] Among them, causal constraints can be restrictions and specifications on the causal relationship between different variables based on domain standard data and practical experience.

[0021] Among them, the project causal diagram can be a graphical representation constructed by causal reasoning methods to describe the causal relationship between various factors in the project. The nodes in the causal diagram represent the variables of the project (such as budget, schedule, quality, risk, etc.), and the edges connecting these nodes represent the causal relationship between the variables (such as budget increase leads to faster schedule).

[0022] Specifically, the structured data and unstructured data of enterprise projects are integrated and transformed, and the structured data is directly mapped to the nodes in the initial causal graph (such as budget, progress, resources, etc.). Among them, the unstructured data is extracted through text analysis technology (such as natural language processing, topic modeling, etc.) to extract potential factors (such as team collaboration, project risks, external interference, etc.), and this information is converted into quantifiable variables and then mapped to the nodes in the initial causal graph. Then, based on the standard data in the project field, the constraints of the causal relationship are set to clarify which variables have direct causal relationships, which are indirect, and which are constrained by external factors. For example, an increase in project budget may directly affect the allocation of resources and the improvement of project quality, but it is restricted by industry budget control standards. Using causal discovery algorithms, such as Bayesian networks or structural equation models, a project causal graph is established to reveal the influence paths and interdependencies between variables, thereby providing a clear framework for subsequent reasoning analysis.

[0023] Step 206, based on the causal relationship between the variables in the project causal diagram, the business information of the enterprise project is inferred to obtain business information inference data.

[0024] A causal relationship is a relationship in which one variable affects another variable. In project management, a causal relationship describes the interaction between various factors in a project. For example, increasing the project budget may directly affect the allocation of resources, thereby accelerating the project schedule, or a shortage of human resources may cause project delays.

[0025] Among them, operating information can be data and information about the operating status of an enterprise or project, usually involving the project's financial status, progress, resource utilization, risk assessment and other aspects.

[0026] Among them, the business information reasoning data can be data obtained through causal reasoning analysis, reflecting how the future operating conditions of a project or enterprise will change with changes in different variables under given conditions.

[0027] Specifically, according to the causal relationship between the variables in the causal graph, the causal reasoning analysis algorithm is used to infer the project's operating information, which can simulate the various future operating conditions of the enterprise project under the current conditions or given additional conditions, so as to predict the future operating performance of the project under the current conditions or given additional conditions (one or more). For example, in the reasoning process of the causal reasoning analysis algorithm, the system will consider the changes in various factors, the possible driving effect of budget increase on progress, or the potential impact of resource shortage on quality, and will also include the impact of external factors, such as changes in the market environment or technological progress. Through causal reasoning, it is possible to predict the future project operating indicators (such as cost, time, quality, etc.) or the changing trends of project operating indicators under different scenarios. For example, assuming that a certain resource is insufficient, the reasoning model can predict how the change will lead to project delays or cost increases. Since the reasoning process of the causal reasoning analysis algorithm not only considers direct causal relationships, but also indirect influences and feedback effects, it can provide more accurate future enterprise project operating estimates and obtain operating information reasoning data.

[0028] Step 208, performing causal intervention analysis on the business information inference data to obtain business information forecast data for the enterprise project.

[0029] Among them, causal intervention analysis can be achieved by changing the values ​​of certain variables and observing the impact on other related variables, thereby analyzing the potential impact of different intervention measures on the operating results of projects or enterprises.

[0030] Among them, the business information forecast data can be the prediction results of future business conditions based on causal intervention analysis, for example, predicting the completion time of a project under different conditions, the probability of budget overruns, or the probability of quality problems.

[0031] Specifically, causal intervention analysis is performed based on the inference data of business information obtained by reasoning, that is, targeted intervention simulation is performed on different business factors of the project to check the impact of different intervention measures on project results. For example, the effects of measures such as increasing resource input, adjusting work plans or changing management strategies when the project schedule is delayed can be simulated to predict how these intervention measures will change the project's cost, schedule, quality and other business indicators. Intervention analysis usually includes multiple experiments in different scenarios to find the most optimized intervention plan, and further generates business information prediction data based on the most optimized intervention plan.

[0032] In the above-mentioned business information prediction method based on enterprise project information data, by obtaining project structured data, project unstructured data and project field standard data of the enterprise project; taking the project field standard data as the causal relationship constraint condition, according to the project structured data and the project unstructured data, constructing the project causal graph of the enterprise project; according to the causal relationship between the variables in the project causal graph, reasoning the business information of the enterprise project to obtain the business information reasoning data; performing causal intervention analysis on the business information reasoning data to obtain the business information prediction data of the enterprise project; wherein, performing causal intervention analysis on the business information reasoning data to obtain the business information prediction data of the enterprise project includes: setting each decision optimization target of the enterprise project according to the project structured data, the project unstructured data and the project field standard data; according to each decision optimization target, performing causal intervention analysis on the business information reasoning data respectively to obtain each business decision intervention data; performing mobilization analysis on the resources of the enterprise project according to each business decision intervention data to generate business information prediction data; wherein, according to each business The method uses the business decision intervention data to mobilize and analyze the resources of the enterprise project and generate business information prediction data, including: using an intervention data optimization algorithm to optimize from each business decision intervention data to obtain the optimal intervention data combination; based on the optimal intervention data combination, virtually scheduling the resources of the enterprise project to obtain resource virtual scheduling data; when the resource virtual scheduling data indicates that the enterprise project still has a project resource output value lower than the set resource output value, based on the project field standard data, adjusting each decision optimization target to obtain each adjusted optimization target; using each adjusted optimization target as each decision optimization target, returning to execute the step of performing causal intervention analysis on the business information reasoning data according to each decision optimization target to obtain each business decision intervention data; until the resource virtual scheduling data indicates that the enterprise project has a project resource output value higher than the set resource output value, the current resource scheduling efficiency is calculated according to the current physical resource scheduling capacity data and the current virtual resource scheduling capacity data of the enterprise project; and generating business information prediction data according to the resource virtual scheduling data and the current resource scheduling efficiency.

[0033] By acquiring and integrating the structured data, unstructured data and domain standard data of enterprise projects, a project causal diagram is constructed to systematically reveal the causal relationship between the variables in the project; further combining causal relationships and causal reasoning to conduct in-depth analysis of project management information helps to identify the key factors that affect project results, thereby providing enterprises with more accurate business insights and decision support; finally, causal intervention analysis of business information can simulate the impact of different intervention measures on project performance and foresee possible business risks and opportunities in advance. This data-driven causal reasoning and intervention analysis improves the accuracy of predictions, provides scientific basis for enterprises in resource allocation, risk control, etc., and can effectively improve the ability to adapt to sudden changes and complex market environments, thereby realizing the refinement and intelligence of project management and promoting enterprises to improve overall operational efficiency and market competitiveness.

[0034] In an exemplary embodiment, Figure 3 As shown, according to the causal relationship between the variables in the project causal diagram, the business information of the enterprise project is inferred to obtain the business information inference data, including steps 302 to 306. Among them: Step 302, using a causal reasoning analysis algorithm, removes direct causal relationships between variables in the project causal diagram and false associations in indirect causal relationships to obtain optimized causal relationship data.

[0035] Among them, causal reasoning analysis algorithms can be tools used to infer and verify causal relationships between variables through mathematical and statistical methods. They can identify which variables have direct or indirect impacts on other variables based on historical data or simulation data, and help predict how changes in a certain factor affect other factors in different scenarios.

[0036] Among them, direct causality can be in causal reasoning analysis, the influence between two variables is direct, that is, the change of one variable directly leads to the change of another variable. For example, in project management, increasing the budget may directly lead to the acceleration of the project schedule, and this relationship does not have any mediating variables or indirect paths.

[0037] Among them, indirect causality can be in causal reasoning, where the impact of one variable on another variable does not occur directly, but is transmitted through one or more mediating variables. For example, an increase in project budget may not directly accelerate the progress, but may ultimately promote the improvement of project progress through indirect channels such as improving resource allocation and increasing personnel input.

[0038] Among them, a false correlation can be a seemingly causal relationship, but in fact this relationship is caused by other hidden factors or external interference, rather than a true causal relationship. For example, under certain conditions, there may be a strong correlation between an increase in project budget and an acceleration of project schedule, but this correlation may only be due to the combined effect of other common external factors (such as team capabilities, market environment, etc.), rather than the budget directly affecting the schedule.

[0039] The optimized causal relationship data may be data obtained by eliminating false associations, data noise or irrelevant variables in causal reasoning analysis.

[0040] Specifically, causal reasoning analysis algorithms (such as Bayesian networks, Granger causal analysis or structural equation models, etc.) are applied to conduct in-depth analysis of the relationship between the variables in the project causal diagram. Different causal reasoning analysis algorithms will calculate the direct causal relationship between each variable and the causal relationship strength in the indirect causal relationship (including the causal relationship strength of the direct causal relationship between each variable and the causal relationship strength of the indirect causal relationship between each variable), and identify the false associations. For example, some seemingly related variables may not really have a causal relationship, but are only caused by the joint influence of other hidden factors. By eliminating these false associations, optimizing causal relationship data can more accurately reflect the true causal path between the variables in the project, thereby providing a more reliable and accurate basis for subsequent reasoning analysis. The optimization process usually includes multiple iterative verifications of the model, data cleaning, outlier identification, and correction of the causal path using domain knowledge.

[0041] Step 304, based on the optimized causal relationship data, the business information of the enterprise project is inferred to obtain causal relationship inference data.

[0042] The causal relationship reasoning data may be the result obtained through causal reasoning analysis, which reflects the reasoning result of how various variables affect each other in the optimized causal relationship network.

[0043] Specifically, based on the optimized causal relationship data after eliminating false associations, the causal reasoning model is used to further reason and analyze the business information of the enterprise project. The causal reasoning analysis algorithm simulates the relationship between variables in the optimized causal relationship data, evaluates how various factors interact with each other, and then derives the business performance of the enterprise project under different conditions in the future, and obtains causal reasoning data. For example, reasoning may reveal the accelerated impact of increasing budget input on project progress, or the improvement of quality control by resource reallocation.

[0044] Step 306, interpreting and processing the causal relationship reasoning data according to the causal interpretation rules of the project domain standard data to obtain the business information reasoning data.

[0045] Among them, causal interpretation rules can be standardized rules or guidelines used to interpret causal reasoning results in a specific industry or field.

[0046] Among them, the interpretation processing can be to combine the causal reasoning results with the causal interpretation rules in the standard data of the project field to ensure the rationality and operability of the reasoning results in the industry context.

[0047] Specifically, the inference results are reasonably interpreted and processed according to the causal interpretation rules of the standard data in the project field; the causal interpretation rules usually include industry regulations, technical standards, best practices, and empirical rules, which provide a framework for interpreting and understanding the inference results. For example, in a construction project, the inference results may show the impact of a certain resource input on the project progress, but it needs to be interpreted in conjunction with the specific regulations of the construction industry, such as construction safety specifications may limit the flexibility of resource use; in IT projects, the inference results may reveal the impact of technology investment on the development cycle, but the rules of the agile development method must be referred to. After the causal interpretation rules reasonably interpret and process the inference results, the text model is used to transform them into business information inference data that the enterprise can understand and apply.

[0048] In this embodiment, by using a causal reasoning analysis algorithm to eliminate false direct and indirect causal relationships in the project causal graph, the optimized causal relationship data can more accurately reflect the true influence relationship between the variables of the project, thereby improving the accuracy of reasoning about the enterprise project business information. By reasoning on the optimized causal relationship data, more reliable business information reasoning data can be generated to provide a scientific basis for decision-making. Further combined with the causal interpretation rules of standard data in the project field, the reasoning data is reasonably interpreted and processed to ensure that the reasoning results meet industry standards and actual business needs, thereby providing easy-to-understand and actionable business insights for enterprise management. It can help enterprises more accurately predict project trends, optimize resource allocation, and improve decision-making efficiency and the scientific nature of project management.

[0049] In an exemplary embodiment, Figure 4 As shown, using a causal reasoning analysis algorithm, the direct causal relationship between the variables in the project causal graph and the false associations in the indirect causal relationship are eliminated to obtain optimized causal relationship data, including steps 402 to 408. Among them: Step 402, causal effect calculation is performed on the direct causal relationship and indirect causal relationship between the variables in the project causal diagram to obtain causal effect calculation data.

[0050] The causal effect calculation may be a calculation that uses a causal inference algorithm to quantify the degree of influence of a certain variable on another variable.

[0051] Among them, the causal effect calculation data can be the quantitative results obtained through causal reasoning analysis, which represents the strength and direction of the causal relationship between the variables.

[0052] Specifically, causal reasoning analysis algorithms (such as Bayesian networks, Granger causal analysis, etc.) are used to quantitatively evaluate the direct and indirect causal relationships between all variables in the project causal graph. Specifically, causal effect calculation is used to measure how a variable affects other variables when it changes. In causal effect calculation, the causal reasoning analysis algorithm will quantify the degree of influence of each path based on the direct causal relationship between variables and the causal path corresponding to the indirect causal relationship. This is not just a statistical correlation, but the direction and strength of the causal effect are determined through modeling. For example, Bayesian networks use conditional probability and graphical models to represent and calculate the causal relationship between different variables. It can handle the interdependence of multiple variables at the same time and represent the strength and direction of the causal effect through the directionality and weight of the edge; Granger causal analysis uses time series data to analyze whether the historical value of a variable can effectively predict the future changes of another variable, helping to reveal the causal influence in the time dimension and ultimately obtaining causal effect calculation data.

[0053] Step 404 , decompose each initial causal path of the project causal diagram according to the causal effect calculation data to obtain causal path decomposition data.

[0054] The initial causal path may be a preliminary causal relationship network constructed based on structured data and unstructured data of the project in the preliminary stage of causal reasoning analysis.

[0055] Among them, the causal path decomposition data can be the data obtained by disassembling and refining the initial causal path, clarifying the specific role and influence mechanism of each causal path.

[0056] Specifically, the initial causal path in the project causal diagram is decomposed in detail according to the causal effect calculation data, including disassembling the complex causal relationship network into simpler causal paths that can be analyzed separately. Specifically, according to the strength and direction of the causal relationship between each variable provided by the causal effect calculation data, the initial causal path in the project causal diagram is disassembled, that is, the overall causal chain is decomposed into multiple independent causal paths that can be analyzed separately. For example, assuming that the progress of the project is affected by multiple factors such as budget, resource allocation, and personnel efficiency, the causal path decomposition extracts each influencing path separately, such as "budget increase → progress acceleration", "resource increase → progress acceleration", and "personnel efficiency improvement → progress acceleration", and obtains causal path decomposition data, where the causal path decomposition data can identify which paths play the most critical role in the entire causal chain and which paths may be redundant or have less impact, so as to better understand how each variable interacts with each other through different causal chains.

[0057] Step 406 , performing a counterfactual analysis on the project causal graph based on the causal effect calculation data and the causal path decomposition data to obtain counterfactual analysis data.

[0058] Among them, counterfactual analysis can be a simulation analysis method used to assume the impact of changes in variables on results under different scenarios, thereby verifying and evaluating the accuracy of causal reasoning.

[0059] Among them, counterfactual analysis data can be the simulation results obtained through counterfactual analysis, reflecting the changes in causal paths and causal effects under different hypothetical scenarios.

[0060] Specifically, since the key to counterfactual analysis is to verify the reliability and validity of data by simulating different "hypothetical scenarios", in specific operations, the data is decomposed according to the causal path to understand the mechanism and impact path of each causal path. On this basis, counterfactual analysis will propose different hypothetical scenarios, such as assuming that a certain variable (such as budget, resources, staffing, etc.) changes, and observe the potential impact of these changes on other variables. For example, if the budget of the project increases by 10%, counterfactual analysis will predict whether this change can accelerate the project progress as expected, or whether it is affected by other mediating variables (such as resource allocation, team collaboration, etc.). By simulating these hypothetical scenarios, counterfactual analysis verifies the accuracy of the data and identifies those causal relationships that are theoretically valid but may not be effective in practice. For example, counterfactual analysis may show that the expected effect of accelerating the progress is not achieved in the case of an increased budget, which may be due to other constraints (such as staff shortages, technical problems, etc.) affecting the final result, clearly identifying and excluding those causal paths that cannot be established or effective in the real environment, and obtaining counterfactual analysis data.

[0061] Step 408, based on the causal effect calculation data, the causal path decomposition data and the counterfactual analysis data, the false associations in the direct causal relationship and the indirect causal relationship are eliminated to obtain optimized causal relationship data.

[0062] Specifically, the causal effect calculation data, causal path decomposition data and counterfactual analysis data are integrated to eliminate possible false associations in the project causal diagram through multi-dimensional analysis. In the specific implementation, the causal effect strength between each variable has been quantified in the causal effect calculation data, and the causal relationships that have the most significant impact on the project results are identified. Then, combined with the causal path decomposition data, each small segment in each causal path is further refined to understand how each variable affects the project results through different mediating variables; however, there may be some false associations in the causal path, that is, those seemingly existing causal relationships are actually not real due to data noise, omitted variables or external factors. Using counterfactual analysis, different hypothetical scenarios are simulated to further verify which causal relationships cannot work as expected in reality, and identify those causal paths that may be established in theory but do not produce the expected effects in practice. Finally, the above data are combined to eliminate the false causal relationships that meet any of the data, and the causal diagram is updated and optimized according to the real and effective causal paths.

[0063] In this embodiment, by calculating the causal effect of the direct and indirect causal relationships between the variables in the project causal diagram, the actual degree of influence of each variable on other variables can be clarified, providing a quantitative basis for the subsequent causal path decomposition. After combining the causal effect calculation data with the causal path decomposition data, further counterfactual analysis is performed to help identify and evaluate possible changes under different decisions or scenarios, providing project managers with deeper insights. Ultimately, by eliminating false associations and optimizing causal relationship data, untrue or irrelevant influencing factors can be eliminated to ensure the accuracy and effectiveness of the causal diagram. Overall, it can improve the accuracy of causal reasoning, help companies identify key influencing factors, optimize decisions, predict project results, and effectively reduce uncertainty and risk in decision-making.

[0064] In an exemplary embodiment, Figure 5 As shown, according to the optimized causal relationship data, the business information of the enterprise project is inferred to obtain the causal relationship inference data, including steps 502 to 506. Among them: Step 502, according to each optimized causal path in the optimized causal relationship data, identifying each business causal direct path and each business causal indirect path from the optimized causal relationship data.

[0065] Among them, the optimized causal path can be the most accurate and effective causal relationship path retained after eliminating false associations and invalid paths in the project causal diagram.

[0066] Specifically, since the optimized causal relationship data is obtained by eliminating false associations and invalid paths to obtain each optimized causal path, and includes direct causal paths and indirect causal paths. According to the optimized causal relationship data, identify which causal paths directly affect the project's operating information, and which paths indirectly affect the operating information through intermediary factors. Among them, the direct operating causal path refers to those paths in which when one variable changes, another variable is directly affected, such as an increase in the budget directly leading to an acceleration of the project progress. The indirect operating causal path is a path that is indirectly affected through one or more intermediary variables. For example, after the budget increases, it may affect the project progress and quality through intermediary variables such as resource allocation and personnel arrangements.

[0067] Step 504 , causal impact decomposition is performed on each business causal direct path and each business causal indirect path, respectively, to obtain each business causal direct decomposition data and each business causal indirect decomposition data.

[0068] Among them, causal impact decomposition can be to break down complex causal relationships into multiple separate influencing factors and gradually quantify the contribution of each factor to the result.

[0069] Among them, the direct decomposition data of operating causality can be the specific data obtained after causal impact decomposition of the direct operating causal path, reflecting the direct contribution of each variable in the direct causal path to the project operating results.

[0070] Among them, the indirect decomposition data of business causality can be the specific data obtained after causal impact decomposition of the indirect path of business causality, revealing the data that affects the business through one or more mediating variables.

[0071] Specifically, the causal impact of each identified direct path of business cause and effect and each indirect path of business cause and effect are decomposed in depth. For the decomposition of direct paths of business cause and effect, the key is to quantify the specific contribution of each variable in each path. For example, an increase in budget may directly affect the acceleration of progress. At this time, it is necessary to calculate the specific impact value of the budget increase on the progress, and further deduce the impact of this impact on the overall quality, cost and other business information of the project. For the decomposition of indirect paths, it is necessary to identify the mechanism of action of each mediating variable in the path. For example, an increase in budget indirectly affects the progress by optimizing resource allocation, and the change in progress is fed back to the cost through project quality. The direct decomposition data of each business cause and effect (including the quantitative data of contribution) and the indirect decomposition data of each business cause and effect (including the data of the mechanism of action) are obtained.

[0072] Step 506, predicting the business information of the enterprise project based on the direct decomposition data of each business cause and effect and the indirect decomposition data of each business cause and effect, and obtaining the cause and effect reasoning data.

[0073] Specifically, the direct decomposition data of each business cause and effect and the indirect decomposition data of each business cause and effect are input into the prediction sub-algorithm in the causal reasoning analysis algorithm, such as Bayesian network, regression analysis model, system dynamics model or deep learning model. Specifically, the prediction sub-algorithm quantifies the causal influence between each variable according to the direct decomposition data of each business cause and effect and the indirect decomposition data of each business cause and effect, and then establishes a multivariate prediction framework for prediction through these causal influences. For the Bayesian network, it uses a graph model to represent the conditional dependency between variables and predicts the possible values ​​of different variables through probabilistic reasoning; the regression analysis model uses statistical methods to establish the numerical relationship between the causal variable and the target variable (such as project schedule, cost, etc.), and predicts the output through known input; the system dynamics model simulates the interaction of different factors in the system by establishing a model based on causal feedback loop, which is suitable for dynamic long-term prediction; if a deep learning model is used, a large amount of historical data is usually trained through a neural network to automatically capture complex causal relationships and make future predictions, and finally obtain causal relationship reasoning data through one prediction or weighted fusion of multiple model predictions. For example, assuming that a key variable (such as the budget) changes, the forecasting sub-model will calculate the impact of the budget change on project progress, quality, cost and other factors based on the optimized causal path and decomposition data, and give expectations for future operating results.

[0074] In this embodiment, by identifying the direct and indirect paths of business causality based on the optimized causal relationship data, it is possible to deeply analyze the influence relationship between the key factors in the enterprise project and provide an accurate causal basis for subsequent decision-making. The causal impact decomposition of the direct and indirect paths of business causality helps to quantify the specific contribution of different paths to project business information and reveal the interactive effects between various factors, thereby providing a scientific basis for resource allocation and strategy adjustment. Ultimately, business information forecasting based on these causal decomposition data can not only improve the accuracy of project business decisions, but also effectively predict the possible business performance of the project, help enterprises to promptly discover potential problems, optimize management strategies, and thus improve the overall success probability and benefits of the project.

[0075] In an exemplary embodiment, Figure 6 As shown, the project domain standard data is used as the causal relationship constraint condition, and the project structured data and the project unstructured data are used to construct the project causal graph of the enterprise project, including steps 602 to 606. Among them: Step 602, setting the key project variables of the enterprise project according to the project domain standard data.

[0076] Among them, key project variables can be variables that have a significant impact on project objectives (such as progress, cost, quality, resource utilization, etc.) during project management and execution.

[0077] Specifically, the standard data in the project field is analyzed. Since the standard data in the project field comes from industry specifications, industry reports, project management best practices, etc., by combining the specific needs and goals of the project, determine which variables are critical to the success of the project. For example, in a construction project, the key variables of the project may include cost, time, resource allocation, construction quality, etc.; in a software development project, the key variables may include development progress, code quality, personnel capabilities, demand changes, etc. Based on the results of the combination of the two, the variables that are critical to the success of the project are set as the key variables of the project.

[0078] Step 604 , identifying project exogenous variables and project endogenous variables from the project key variables.

[0079] Among them, project exogenous variables can be external factors that are not directly affected by project control or internal decisions, but have a significant impact on the project, such as market trends, natural disasters, supply chain disruptions, etc.

[0080] Among them, project endogenous variables can be variables generated by the interaction between various factors within the project. These variables are controllable by the project, and their values ​​can be directly affected by the management, decision-making and optimization of the project team, such as the allocation of project resources, the work efficiency of the team, the priority arrangement of tasks, etc.

[0081] Specifically, since project exogenous variables are those factors that are uncontrollable or not controlled by the project, they play the role of "given conditions" in the project and cannot be directly controlled or changed by variables within the project. For example, market demand fluctuations, natural disasters, etc. are all exogenous variables. Project endogenous variables are the result variables within the project, which are affected by internal factors of the project, such as project progress, cost, quality, team performance, etc. By classifying each key project variable, each key project variable is marked as a project exogenous variable and a project endogenous variable.

[0082] Step 606, constructing a project cause-and-effect diagram according to the project structured data, the project unstructured data, the project exogenous variables and the project endogenous variables.

[0083] Specifically, quantitative information is provided based on structured data, so that causal relationships can be expressed through numerical relationships, and unstructured data can be used to extract potential association patterns through text analysis to help identify those implicit but critical causal paths; combined with the causal relationship mapping data obtained by mapping the exogenous variables and endogenous variables of the project, a project causal graph is constructed. The causal graph expresses the network of interactions among various factors in the project by describing the causal relationship between various variables (such as "budget increase leads to faster progress").

[0084] In this embodiment, by setting the key variables of the enterprise project according to the standard data of the project field, it can be ensured that the selected variables comprehensively cover the decisive factors for the success of the project, thereby laying the foundation for the in-depth analysis of the project. By identifying exogenous variables and endogenous variables from these key variables, it is possible to more clearly understand which factors are controllable by the project (endogenous variables) and which factors are externally uncontrollable (exogenous variables), thereby providing clear guidance for subsequent risk management and resource allocation. Finally, by combining project structured data, unstructured data, and exogenous and endogenous variables, a project cause-and-effect diagram is constructed, which can effectively reveal the cause-and-effect relationship between the various factors of the project, help the project team identify key driving factors and potential risks, provide a scientific basis for accurate decision-making and efficient management, and enhance the predictability and controllability of project success.

[0085] In an exemplary embodiment, Figure 7 As shown, a project cause-effect diagram is constructed according to project structured data, project unstructured data, project exogenous variables and project endogenous variables, including steps 702 to 706. Among them: Step 702: Determine the cause-effect diagram display style and the cause-effect diagram system dynamics data according to the project structured data and the project unstructured data.

[0086] Among them, the causal diagram display style can be to visually present the various variables in the causal diagram and the causal relationship between them, which includes the layout of the causal diagram, the representation of nodes, the connection method of edges, the direction of arrows, and the color and shape of nodes and edges.

[0087] Among them, the causal diagram system dynamics data can be used to describe the dynamic relationship between the variables in the project causal diagram, emphasizing the changes of variables in time series and their interactions.

[0088] Specifically, the clear numerical values ​​and time series of the total structured data of the project are analyzed, and the key indicators such as the budget, cost, progress, and staffing of the project are analyzed to identify the main variables in the project and their interrelationships, such as how budget changes affect the project progress or cost fluctuations; at the same time, unstructured data such as project reports, meeting minutes, and emails contain rich text information, which may imply the relationship between different factors in the project and potential causal relationships. Analyze and extract the potential relationship between key topics, decision points, and variables. Since the causal graph display style refers to how to present the causal relationship of the project in the form of a graph, it usually includes the layout of nodes and edges, the display style of the relationship between variables, etc., the data obtained by analyzing the structured data and unstructured data of the project will be combined with the specific requirements of the project to determine the hierarchical structure and complexity of the causal graph, such as whether to use a simple linear graph or a more complex dynamic system model, and finally obtain the causal graph display style. At the same time, according to the causal graph display style and the analysis of the changing trends of project variables, the dynamic characteristics of the interaction between the variables are determined, and the system dynamics data is further calculated.

[0089] Step 704 , using a causal discovery algorithm, identifies project causal relationships from project structured data, project unstructured data, project exogenous variables, and project endogenous variables.

[0090] Among them, the project causal relationship can be the causal influence relationship between different variables, that is, how the change of one variable causes the change of another variable.

[0091] Specifically, causal discovery algorithms (such as Granger causal analysis, Bayesian network, mutual information analysis, etc.) are used to analyze the correlation between different variables from project structured data, project unstructured data, project exogenous variables, and project endogenous variables, and derive the project causal relationship between variables. For example, structured data provides the numerical relationship between variables, and unstructured data reveals potential causal relationships through technologies such as natural language processing. The algorithm can automatically identify which variables have direct or indirect causal relationships and determine the causal direction. In a specific example, an increase in the project budget may affect the project progress through multiple channels (such as resource allocation and staffing), thereby revealing the causal relationship between budget and progress.

[0092] Step 706 , constructing a project cause-effect diagram according to the project cause-effect relationship, the cause-effect diagram display style, and the cause-effect diagram system dynamics data.

[0093] Specifically, based on the identified project causal relationships, relevant variables are used as nodes, and these nodes are connected by edges to represent the causal relationship between the variables; then, based on the causal diagram display style, the visual representation of each node and edge is determined, such as color, size, arrow direction, etc., so as to clearly express the strength, direction and type of the causal relationship; in addition, system dynamics data is used to describe the dynamic change characteristics of each variable and the temporal relationship of their mutual influence, ensuring that the causal diagram not only represents the static relationship, but also reflects the changing trend of the project at different time nodes and situations. The final constructed project causal diagram shows the complex relationship between the variables in the project.

[0094] In this embodiment, by determining the display style and system dynamics data of the causal diagram based on the project structured data and unstructured data, it can be ensured that the causal diagram has both clear visualization effects and can accurately reflect the dynamic relationship between various factors of the project, providing intuitive support for project analysis. Using causal discovery algorithms to identify causal relationships from various types of project data helps to reveal the true impact path between various factors in the project and avoid misleading data bias and incompleteness. Finally, combining causal relationships, display styles, and system dynamics data to construct a project causal diagram can systematically display the internal mechanisms and key driving factors of project operations, provide project managers with deeper insights, optimize decision-making processes, and improve the controllability and transparency of project execution.

[0095] In an exemplary embodiment, Figure 8 As shown, the causal intervention analysis is performed on the business information reasoning data to obtain the business information forecast data of the enterprise project, including steps 802 to 806. Among them: Step 802, setting various decision optimization goals of the enterprise project based on the project structured data, the project unstructured data and the project field standard data.

[0096] Among them, the decision optimization goal can be a specific goal set during project operation to improve project performance based on project needs, resource constraints and external environment. It usually involves multiple aspects, such as improving project benefits, reducing costs, shortening construction period, improving quality, and enhancing customer satisfaction.

[0097] Specifically, feature extraction is performed on project structured data, project unstructured data, and project field standard data. The three different feature data after feature extraction are used to evaluate the current status of the project, external environment, and industry requirements, so as to formulate various decision optimization goals. The decision optimization goals include improving project benefits, reducing costs, shortening construction period, improving quality, and enhancing customer satisfaction.

[0098] Step 804, according to each decision optimization goal, causal intervention analysis is performed on the business information inference data to obtain each business decision intervention data.

[0099] Among them, the operational decision intervention data can be data obtained through causal intervention analysis methods, reflecting the changes in project operational information (such as cost, progress, quality, etc.) under different decision interventions.

[0100] Specifically, using the causal reasoning model, according to the set optimization goals of each decision, the key variables related to the decision are identified, and further analysis is conducted on how the project's operating information will change when these variables are adjusted. For example, if the goal is to reduce costs, then improving resource utilization efficiency or reducing redundant resources may have an impact on the overall cost of the project, and the intervention data of each operating decision can be obtained.

[0101] Step 806, analyzing the mobilization of resources for enterprise projects based on each operational decision intervention data, and generating operational information forecast data.

[0102] Among them, mobilization analysis can be a process of evaluating and simulating the impact of different resource allocation plans on project performance based on business decision intervention.

[0103] Specifically, since mobilization analysis involves evaluating how to optimize resource allocation to achieve decision-making goals under different intervention measures based on data obtained from causal intervention analysis, and these resources may include funds, personnel, materials, etc., the intervention data optimization algorithm is used to calculate the optimal resource allocation plan in each business decision intervention data, and further predict the changes in business information after the implementation of these plans, as the generation of business information prediction data.

[0104] In this embodiment, by setting decision optimization goals based on project structured data, unstructured data, and domain standard data, it is possible to ensure that the goal setting of the enterprise project is accurate and meets actual needs, providing a clear direction for subsequent decision-making. By performing causal intervention analysis on business information reasoning data, the impact of different decision intervention measures on various aspects of the project can be identified, thereby providing management with an operational decision-making basis. Further resource mobilization analysis based on business decision intervention data will help optimize resource allocation, improve resource utilization efficiency, and ensure the achievement of project goals. The business information forecast data finally generated can help companies identify potential problems in advance, optimize resource allocation and decision-making, and improve the overall benefits and success rate of the project.

[0105] In an exemplary embodiment, Fig. 9 As shown, the resources of the enterprise project are mobilized and analyzed according to each business decision intervention data to generate business information forecast data, including steps 902 to 912. Among them: Step 902, using an intervention data optimization algorithm, optimizes each business decision intervention data to obtain the optimal intervention data combination.

[0106] Among them, the intervention data optimization algorithm can be an algorithm used to optimize decision-making intervention measures and to identify the most effective combination from multiple intervention plans.

[0107] Among them, the optimal intervention data combination can be the best decision-making intervention plan screened out by the intervention data optimization algorithm, which can maximize the project benefits based on project goals and resource constraints.

[0108] Specifically, intervention data optimization algorithms (such as genetic algorithms, simulated annealing, particle swarm optimization, etc.) are used to optimize and analyze the intervention data of various business decisions. The goal is to find the most effective combination from multiple intervention plans to maximize the realization of project goals. The intervention data optimization algorithm evaluates the impact of different intervention measures on project operating indicators (such as cost, progress, quality, etc.), comprehensively considers all possible variables and intervention methods, and obtains an optimal combination of intervention data. This combination can minimize resource waste and risks while meeting project goals, ensuring that the project can achieve the best results under given resources and constraints.

[0109] Step 904: Virtually schedule the resources of the enterprise project according to the optimal intervention data combination to obtain resource virtual scheduling data.

[0110] Among them, resource virtual scheduling data can be data generated by simulation and emulation technology, which is used to show how resources are optimally configured under ideal conditions.

[0111] Specifically, based on the optimal intervention data combination, the resources in the enterprise project are virtually scheduled. Virtual scheduling is to evaluate the impact of different resource allocation schemes on the project without actually adjusting the resources through simulation and simulation technology. By calculating indicators such as project progress, cost control and quality management under different resource configurations, resource virtual scheduling data is obtained. These data can reveal how resources are optimally configured under ideal intervention conditions to achieve project goals and provide decision support for subsequent actual operations.

[0112] Step 906, when the resource virtual scheduling data indicates that the enterprise project still has a project resource output value lower than the set resource output value, each decision optimization target is adjusted based on the project field standard data to obtain each adjusted optimization target.

[0113] Among them, the project resource output value can be the output or effect generated by the project under the actual resource input, which is usually closely related to the project's operating indicators (such as the amount of tasks completed, cost savings, progress achieved, etc.).

[0114] The set resource output value may be an ideal resource output level set in advance according to project objectives, resource allocation and external environment requirements.

[0115] Among them, the adjusted optimization target can be a target for resetting the original target according to the actual situation during the resource scheduling and intervention analysis process.

[0116] Specifically, if in the virtual scheduling process, it is found that the output value of the project resources of the enterprise project is still lower than the preset resource output value, it means that the existing resource allocation plan is not enough to meet the profit target of the project production. In this case, it is necessary to adjust the decision optimization target based on the standard data in the project field (such as industry regulations, best practices, project goals, etc.). For example, it may be necessary to re-evaluate the allocation ratio of resources, increase the investment of certain key resources, or extend the project time. Through this adjustment, the optimization target will be reset to ensure that the resource allocation and project goals are more in line with the actual situation and obtain various adjusted optimization targets.

[0117] Step 908, taking each adjustment optimization target as each decision optimization target, returning to execute the step of performing causal intervention analysis on the business information inference data according to each decision optimization target, and obtaining each business decision intervention data.

[0118] Specifically, after adjusting the optimization target, each new adjusted optimization target replaces the original decision optimization target as the optimization basis, and performs causal intervention analysis on the business information reasoning data. This step is similar to the causal intervention analysis step mentioned above, but the target used this time has been adjusted to reflect the new resource allocation and expected results. On this basis, further causal analysis is performed to obtain updated business decision intervention data.

[0119] Step 910, until the resource virtual scheduling data indicates that the enterprise project has a project resource output value higher than the set resource output value, calculate the current resource scheduling efficiency according to the current physical resource scheduling capacity data and the current virtual resource scheduling capacity data of the enterprise project.

[0120] Among them, the current entity resource scheduling capability data can be the configuration and scheduling capability data of tangible resources in the enterprise project, including the allocation and use of personnel, funds, equipment, etc.

[0121] Among them, the current virtual resource scheduling capability data can be the configuration and scheduling capability data of invisible resources in the enterprise project.

[0122] Among them, the current resource scheduling efficiency can be a quantitative assessment of the gap between the actual resource usage in the project and the ideal resource configuration.

[0123] Specifically, the intervention and optimization steps are repeated until the resource virtual scheduling data shows that the project resource output value exceeds the set resource output value. When this goal is achieved, it means that the resource allocation is sufficient to meet the project requirements. On this basis, the current resource scheduling efficiency can be calculated by combining the current physical resource scheduling capability data (such as the actual resource allocation) and the virtual resource scheduling capability data (such as the ideal resource scheduling in the virtual environment). In the calculation process, by analyzing the physical resource scheduling capability data, the allocation and use effect of actual resources (such as personnel, equipment, funds, etc.) are evaluated to determine whether each resource is reasonably allocated and fully utilized. On this basis, combined with the virtual resource scheduling capability data, the resource allocation under ideal conditions is simulated through the simulation model, and the optimal resource allocation scheme is considered without external interference and restrictions. Next, multiple levels of factors should be considered in the calculation, such as the use time of resources, the interdependence between resources, the priority of tasks, and the relationship between resource input and project goals (such as cost, progress, quality, etc.). In the evaluation process, it is also necessary to pay attention to the gap between actual resource use and virtual scheduling schemes, analyze the impact of these gaps on project execution, and convert them into indicators of resource scheduling efficiency.

[0124] Step 912, generating business information forecast data based on the resource virtual scheduling data and the current resource scheduling efficiency.

[0125] Specifically, the current resource scheduling efficiency is used to adjust the resource virtual scheduling data to predict the operating results (such as cost, progress, quality, etc.) that may be achieved during the actual execution of the enterprise project and obtain operating information prediction data.

[0126] In this embodiment, by using the intervention data optimization algorithm to optimize the optimal intervention data combination from the business decision intervention data, it can ensure that the intervention measures for project decisions are more scientific and effective, thereby maximizing the positive impact of the decision on the project. Based on the optimal intervention data combination, virtual resource scheduling can test and evaluate the effect of resource allocation under different decisions without interfering with the actual resource allocation, and discover potential resource bottlenecks or waste in advance. When the resource virtual scheduling data represents that the project resource output value is lower than the set standard, the decision optimization target is adjusted to make the resource scheduling more in line with the project needs and ensure the maximization of resource output value. By continuously iteratively adjusting the target and optimizing the decision until the project resource output value is higher than the set standard, the current resource scheduling efficiency can be accurately calculated, thereby providing a quantitative basis for resource allocation. Finally, the business information forecasting data generated by combining the resource virtual scheduling data and the scheduling efficiency can help enterprises understand the resource usage and project progress in real time, optimize decisions, improve the possibility of project success, and enhance the flexibility and accuracy of overall business management.

[0127] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned 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 does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can 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 to be 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.

[0128] Based on the same inventive concept, the embodiment of the present application also provides a business information prediction device based on enterprise project information data for implementing the business information prediction method based on enterprise project information data involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the business information prediction device based on enterprise project information data provided below can refer to the above limitations on a business information prediction method based on enterprise project information data, and will not be repeated here.

[0129] In an exemplary embodiment, Fig.10 As shown, a business information prediction device based on enterprise project information data is provided, including: a project data acquisition module 1002, a cause-effect diagram construction module 1004, a business information prediction module 1006 and a business information intervention module 1008, wherein: 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 The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface.

[0130] 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.

[0131] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0132] 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 computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0133] 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.

[0134] 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.

[0135] 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 understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations 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 predicting business information based on enterprise project information data, characterized in that: The method comprises: Acquire project structured data, project unstructured data, and project domain standard data of enterprise projects; Using the project domain standard data as causal relationship constraints, and constructing a project causal graph of the enterprise project according to the project structured data and the project unstructured data; Inferring the business information of the enterprise project according to the causal relationship between the variables in the project causal graph to obtain business information inference data; Performing causal intervention analysis on the business information inference data to obtain business information forecast data of the enterprise project; The step of performing causal intervention analysis on the business information inference data to obtain the business information forecast data of the enterprise project includes: According to the project structured data, the project unstructured data and the project field standard data, setting various decision optimization goals of the enterprise project; According to each of the decision optimization goals, causal intervention analysis is performed on the business information reasoning data to obtain each business decision intervention data; Analyze the resources of the enterprise project according to each of the business decision intervention data to generate the business information forecast data; The mobilization analysis of the resources of the enterprise project according to each of the business decision intervention data to generate the business information forecast data includes: Using an intervention data optimization algorithm to optimize the business decision intervention data, to obtain the optimal intervention data combination; According to the optimal intervention data combination, virtually scheduling the resources of the enterprise project to obtain resource virtual scheduling data; When the resource virtual scheduling data indicates that the enterprise project still has a project resource output value lower than the set resource output value, adjusting each of the decision optimization targets based on the project field standard data to obtain each adjusted optimization target; Taking each of the adjustment optimization targets as each of the decision optimization targets, returning to the step of performing causal intervention analysis on the business information inference data according to each of the decision optimization targets to obtain each of the business decision intervention data; Until the resource virtual scheduling data indicates that the enterprise project has a resource output value that is higher than the set resource output value, the current resource scheduling efficiency is calculated according to the current physical resource scheduling capacity data and the current virtual resource scheduling capacity data of the enterprise project; The business information forecast data is generated according to the resource virtual scheduling data and the current resource scheduling efficiency.

2. The method according to claim 1, characterized in that The inference of the business information of the enterprise project based on the causal relationship between the variables in the project causal diagram to obtain the business information inference data includes: Using a causal reasoning analysis algorithm, the direct causal relationship between the variables in the causal diagram of the project and the false associations in the indirect causal relationship are eliminated to obtain optimized causal relationship data; Reasoning the business information of the enterprise project based on the optimized causal relationship data to obtain causal relationship reasoning data; The causal relationship reasoning data is interpreted and processed according to the causal interpretation rules of the project field standard data to obtain the business information reasoning data.

3. The method according to claim 2, characterized in that The causal reasoning analysis algorithm is used to eliminate the direct causal relationship between the variables in the project causal diagram and the false associations in the indirect causal relationship to obtain optimized causal relationship data, including: Perform causal effect calculation on the direct causal relationship and indirect causal relationship between the variables in the project causal diagram to obtain causal effect calculation data; Decomposing each initial causal path of the project causal diagram according to the causal effect calculation data to obtain causal path decomposition data; Performing a counterfactual analysis on the project causal graph according to the causal effect calculation data and the causal path decomposition data to obtain counterfactual analysis data; According to the causal effect calculation data, the causal path decomposition data and the counterfactual analysis data, false associations in the direct causal relationship and the indirect causal relationship are eliminated to obtain the optimized causal relationship data.

4. The method according to claim 2, characterized in that: The step of inferring the business information of the enterprise project based on the optimized causal relationship data to obtain causal relationship inference data includes: According to each optimized causal path in the optimized causal relationship data, identifying each operating causal direct path and each operating causal indirect path from the optimized causal relationship data; Performing causal impact decomposition on each of the direct paths of the business cause and effect and each of the indirect paths of the business cause and effect to obtain direct decomposition data of each business cause and effect and indirect decomposition data of each business cause and effect; Based on the direct decomposition data of each operating cause and effect and the indirect decomposition data of each operating cause and effect, the operating information of the enterprise project is predicted to obtain the cause and effect reasoning data.

5. The method according to claim 1, characterized in that The project cause-effect diagram of the enterprise project is constructed based on the project structured data and the project unstructured data using the project domain standard data as the cause-effect constraint condition, including: According to the project field standard data, set the key project variables of the enterprise project; Identify project exogenous variables and project endogenous variables from the key project variables; The project cause-effect diagram is constructed according to the project structured data, the project unstructured data, the project exogenous variables and the project endogenous variables.

6. The method according to claim 5, characterized in that The step of constructing the project cause-effect diagram according to the project structured data, the project unstructured data, the project exogenous variables and the project endogenous variables includes: Determine a cause-effect diagram display style and cause-effect diagram system dynamics data according to the project structured data and the project unstructured data; Using a causal discovery algorithm, identifying project causal relationships from the project structured data, the project unstructured data, the project exogenous variables, and the project endogenous variables; The project cause-effect diagram is constructed according to the project cause-effect relationship, the cause-effect diagram display style and the cause-effect diagram system dynamics data.

7. A business information prediction device based on enterprise project information data, characterized in that: The device comprises: Project data acquisition module, used to acquire project structured data, project unstructured data and project field standard data of enterprise projects; A cause-effect diagram construction module, used to construct a project cause-effect diagram of the enterprise project based on the project structured data and the project unstructured data, using the project domain standard data as cause-effect constraint conditions; An operating information prediction module is used to infer the operating information of the enterprise project according to the causal relationship between the variables in the project causal diagram to obtain operating information inference data; An operating information intervention module, used to perform causal intervention analysis on the operating information inference data to obtain operating information forecast data of the enterprise project; The step of performing causal intervention analysis on the business information inference data to obtain the business information forecast data of the enterprise project includes: According to the project structured data, the project unstructured data and the project field standard data, setting various decision optimization goals of the enterprise project; According to each of the decision optimization goals, causal intervention analysis is performed on the business information reasoning data to obtain each business decision intervention data; Analyze the resources of the enterprise project according to each of the business decision intervention data to generate the business information forecast data; The mobilization analysis of the resources of the enterprise project according to each of the business decision intervention data to generate the business information forecast data includes: Using an intervention data optimization algorithm to optimize the business decision intervention data, to obtain the optimal intervention data combination; According to the optimal intervention data combination, virtually scheduling the resources of the enterprise project to obtain resource virtual scheduling data; When the resource virtual scheduling data indicates that the enterprise project still has a project resource output value lower than the set resource output value, adjusting each of the decision optimization targets based on the project field standard data to obtain each adjusted optimization target; Taking each of the adjustment optimization targets as each of the decision optimization targets, returning to the step of performing causal intervention analysis on the business information inference data according to each of the decision optimization targets to obtain each of the business decision intervention data; Until the resource virtual scheduling data indicates that the enterprise project has a resource output value that is higher than the set resource output value, the current resource scheduling efficiency is calculated according to the current physical resource scheduling capacity data and the current virtual resource scheduling capacity data of the enterprise project; The business information forecast data is generated according to the resource virtual scheduling data and the current resource scheduling efficiency.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

Images