Enterprise project management system based on response feedback

Abstract

The present invention relates to the technical field of enterprise project management, specifically to an enterprise project management system based on response feedback, including a real-time dynamic resource allocation module, an intelligent task priority adjustment module, an adaptive risk warning module and a visual analysis module; the real-time dynamic resource allocation module is used to dynamically adjust resource allocation based on real-time feedback; the intelligent task priority adjustment module is used to dynamically adjust task priority according to task completion status and resource status; the adaptive risk warning module is used to monitor project data in real time and predict potential risks of the project; the visual analysis module is used to integrate data of various modules and visualize the integrated results; the present invention can achieve flexible and precise control of enterprise project management through the joint collaboration of various modules; by constructing linear programming equations, it can adaptively plan the allocation of resources to improve the overall progress and quality of the project.

Description

Technical Field

[0001] This invention relates to the technical field of enterprise project management, specifically to an enterprise project management system based on response feedback. Background Art

[0002] Enterprise project management is a systematic approach to planning, organizing, coordinating, and controlling resources to achieve specific project objectives; it typically involves project planning, resource management, task management, schedule management, quality management, and risk management.

[0003] Current enterprise management faces the following challenges:

[0004] 1. Traditional project management systems typically lack the ability to monitor and adjust resource allocation in real time, leading to resource waste or shortages, which affects project progress and quality;

[0005] 2. The prioritization and allocation of tasks in projects are often based on the initial plan, lacking a dynamic adjustment mechanism, and unable to adapt to changes in actual progress, resulting in low efficiency;

[0006] 3. Existing risk management systems typically only take countermeasures after a risk occurs, lacking the ability to provide early warnings and rapid responses, which can easily lead to project interruptions or failures;

[0007] 4. Project quality issues are often discovered after the fact, lacking prediction and prevention mechanisms, which affects the quality of the final deliverables and customer satisfaction. Summary of the Invention

[0008] In view of the above-mentioned problems, the present invention is proposed.

[0009] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an enterprise project management system based on response feedback, including a real-time dynamic resource allocation module, an intelligent task priority adjustment module, an adaptive risk warning module, and a visualization analysis module;

[0010] The real-time dynamic resource allocation module is used to dynamically adjust resource allocation based on real-time feedback;

[0011] The intelligent task priority adjustment module is used to dynamically adjust task priority based on task completion status and resource status.

[0012] The adaptive risk warning module is used to monitor project data in real time and predict potential risks to the project.

[0013] The visualization analysis module is used to integrate data from various modules and display the integration results in a data visualization format.

[0014] As a preferred embodiment of the enterprise project management system based on response feedback described in this invention, the real-time dynamic resource allocation module monitors project progress and resource status in real time, and uses machine learning algorithms to predict future investment needs. Based on the predicted investment needs, it automatically adjusts resource allocation and simultaneously feeds back the monitored resource status to the intelligent task priority adjustment module and the adaptive risk warning module. The prediction of future investment needs using machine learning algorithms involves constructing a future investment demand model based on a linear regression algorithm, as detailed below:

[0015] y t =β0+β1x 1t +β2x 2t +...+β n x nt +ε t

[0016] Among them, y t This represents the resource requirement of the project at time t, and β0 represents the intercept term of the linear regression, which is calculated by substituting historical data. it This represents the i-th characteristic value of the project at time t, including the project completion rate, current resource usage, human resource workload, equipment failure rate, and equipment usage status, ε. t Represents the error term, β i Represent each feature x it The regression coefficients, error term, and regression coefficients are calculated by training the future investment demand model, as follows:

[0017] The model is trained using historical data as the training dataset, and compared with the current project.

[0018] Select similar projects from historical data. The similar projects are matched according to the current project's scheduled construction period, project objectives, construction team, and acceptance unit, and the number of matches is no less than 2.

[0019] Based on the current project schedule, select data corresponding to the time schedule from historical data, including historical resource requirements (y). t ′ and historical eigenvalues ​​x i ′ t ;

[0020] Finally, the selected data is used to train the constructed model, and the regression coefficient β corresponding to each feature value can be calculated. i The calculated regression coefficients are then mapped to the current project to predict resource requirements at future points in time.

[0021] As a preferred embodiment of the enterprise project management system based on response feedback described in this invention, the automatic adjustment of resource allocation according to predicted investment demand is achieved by constructing a linear programming equation and using dynamic adjustment constraints to constrain the constructed equation, thereby realizing the automatic adjustment of resource allocation according to predicted investment demand. The specific implementation is as follows:

[0022] Construct linear programming equations,

[0023] Constraints are applied using dynamically adjusted constraints.

[0024]

[0025]

[0026]

[0027] Among them, X ij a represents the number of resources allocated to the i-th item in task j. ij This represents the contribution coefficient of the i-th resource to the j-th task. Before the current project starts, historical data will be used as reference data to set the contribution coefficient according to the importance of the resource to the task. j w represents the predicted demand for the j-th task. j Y represents the priority weight of task j, which is a priority weight pre-assigned to each task based on historical data before the current project starts. Y represents the total resource investment of the current project. ij This represents the priority weight of the i-th resource and the j-th task. It is a priority weight pre-assigned to each resource based on historical data before the current project starts. ij This represents the predicted demand for the i-th resource in the j-th task.

[0028] As a preferred embodiment of the enterprise project management system based on response feedback described in this invention, the method of using dynamically adjusted constraints to constrain the constructed equations involves constraining the linear programming equations by ensuring the fulfillment of the constraints, thereby achieving adaptive resource allocation, as detailed below:

[0029] For different tasks, the resource allocation is determined by X. ij The constraint ≥0 means that when allocating resources according to the linear programming equation, it is necessary to ensure that the resource allocation quantity for the task is greater than 0.

[0030] For task priority weights, through The constraint indicates that the actual resource allocation for the current task is greater than the predicted resource allocation based on the priority weight of the current task.

[0031] For adaptive resource allocation, the allocation is performed using the calculation result f of the linear programming equation, y ij w ij This represents a comprehensive score for the current task, derived through a combined analysis of the predicted resource quantity and priority weights for that task. Y represents the total comprehensive score of all tasks in the current project, Y represents the total resource input of the current project, and f represents the allocation quantity of the i-th resource assigned to task j, which is adaptively allocated based on the proportion of the comprehensive score of the current task in the entire project.

[0032] As a preferred embodiment of the enterprise project management system based on response feedback described in this invention, the intelligent task priority adjustment module resets the task priority weight of the current project according to the task completion rate and the amount of resources allocated, and feeds the adjustment result back to the real-time dynamic resource allocation module to perform secondary regulation on the resource allocation of tasks in the real-time dynamic resource allocation module.

[0033] The repriority weighting of tasks in the current project is determined by comprehensively considering task completion rate and resource allocation results. The specific calculation formula is as follows:

[0034]

[0035]

[0036] Where λ represents the completion rate of the current task, t represents the time the current task has been performed, T represents the scheduled duration of the entire project, and w j This represents the priority weight assigned to tasks before the project starts, f represents the amount of resources allocated to the current project, and w′ represents the priority weight assigned to tasks before the project starts. j This indicates the priority weight for adaptive allocation of tasks to the current task. The specific adaptive allocation is as follows:

[0037] The task completion rates λ are sorted in descending order, and the current project's completion rate is compared with the historical project completion rates λ′ within the same duration. Based on the comparison results, the task priority weights are adaptively adjusted. Specifically,

[0038] When the comparison result satisfies the formula λ≤λ′, it means that the completion rate of the current task is lower than the historical task completion rate. The priority weight of the current task is increased, and the increased priority weight is fed back to the real-time dynamic resource allocation module to increase the amount of resources allocated to the current task, thus completing the secondary adjustment of the resource allocation of the task.

[0039] When the comparison result satisfies the formula λ>λ′, it means that the completion rate of the current task is higher than the historical task completion rate. The priority weight of the current task is reduced, and the reduced priority weight is fed back to the real-time dynamic resource allocation module to reduce the amount of resources allocated to the current task, thus completing the secondary adjustment of the resource allocation of the task.

[0040] As a preferred embodiment of the enterprise project management system based on response feedback described in this invention, the adaptive risk early warning module identifies potential risks in the project by real-time monitoring of project data and based on the monitoring results, specifically implemented as follows:

[0041] The monitored project data is constructed into a dataset R = [r1, r2, r3, ..., r n ], where each feature vector r i It includes multiple feature values, and the feature vector includes project progress data, resource usage data, quality data, and environmental data. The feature values ​​included in the project progress data are task completion time and task delay status.

[0042] The probability of a risk occurring using a feature vector is calculated using a Bayesian network. The specific calculation formula is as follows:

[0043]

[0044] Where P(R|r) represents the eigenvector r i Given the occurrence of [something], the probability of project risk, P(r) i ) represents the eigenvector r i The probability of occurrence, P(R) represents the initial probability of the project risk occurring, P(r) i |R) represents the feature vector r when a risk occurs in the project. i The probability of its occurrence.

[0045] As a preferred embodiment of the enterprise project management system based on response feedback described in this invention, the step of identifying potential project risks based on monitoring results involves predicting the risk type using a support vector machine model based on the calculated probability of risk occurrence. The specific prediction is as follows:

[0046] The calculated probability of the risk occurring P(R|r) i Using r1, r2, r3, ..., r4 as new feature vectors, construct a new feature set R′, satisfying the formula R′ = [r1, r2, r3, ..., r4]. n ,P(R1|r i ),P(R2|r i ),...,P(R m |r i ]], where n represents the total number of original features and m represents the total number of project risk types, which are set based on historical data;

[0047] A support vector machine model is constructed to predict risk types. The specific model is as follows:

[0048]

[0049] Among them, R T Let W represent the risk type prediction result, W represent the weight vector that controls the accuracy of risk classification, b represent the bias term, and R represent the risk type prediction result. i ′ represents the true risk type of the i-th feature vector.

[0050] As a preferred embodiment of the enterprise project management system based on response feedback described in this invention, the visualization analysis module integrates feedback data from the real-time dynamic resource allocation module, the intelligent task priority adjustment module, and the adaptive risk warning module, and uses data technology to display the data in a page-interactive form on the visualization terminal.

[0051] The integration of feedback data from the real-time dynamic resource allocation module, the intelligent task priority adjustment module, and the adaptive risk warning module utilizes a comprehensive scoring method to evaluate the data from each module. The evaluation results then serve as the data basis for subsequent page interactions. The specific implementation is as follows:

[0052] For any task j in the current project, the data from the real-time dynamic resource allocation model is f. j This indicates the amount of resources allocated to the current task; the data from the intelligent task priority adjustment module is w. j , indicating the priority of the current task, and the data from the adaptive risk warning module is R. Tj This indicates the type of risk arising from the current task;

[0053] The data for each module are evaluated using a weighted average method, as detailed below:

[0054]

[0055] Among them, f j This represents data from a real-time dynamic resource allocation model, w j This indicates data from the intelligent task priority adjustment module, R Tj This indicates data from the adaptive risk warning module;

[0056] The weighted average data was then comprehensively evaluated, and the specific evaluation is as follows:

[0057] E=W f ·f J +W w ·w J +WR ·R Tj

[0058] Among them, W f 、W w 、W R These represent the weights of the data in each module, set based on the contribution of the current task to the project in historical data. E represents the calculated comprehensive score, which is used as the basis for the vertical axis display on the visualization terminal.

[0059] Finally, the calculated comprehensive score is used as the vertical axis in the visualization terminal display, and the time progress is used as the horizontal axis in the visualization terminal display, so that relevant staff can make quick decisions based on the visualization terminal display results.

[0060] The beneficial effects of this invention are as follows: Through the joint collaboration of various modules, the results of the front-end modules affect the output of the back-end modules, and the feedback from the front-end modules triggers the real-time response of the back-end modules, enabling flexible and precise control of enterprise project management; by constructing linear programming equations, adaptive planning of resource allocation can be achieved, improving the overall progress and quality of the project; through real-time monitoring and prediction of project risks, project risks can be predicted in advance, and targeted measures can be taken against the predicted risks. Attached Figure Description

[0061] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0062] Figure 1 This is a schematic diagram of the overall structure of the enterprise project management system based on response feedback according to the present invention. Detailed Implementation

[0063] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0064] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0065] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0066] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0067] Furthermore, it should be noted in the description of this invention that the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0068] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0069] Example 1

[0070] Reference Figure 1 The first embodiment of the present invention provides an enterprise project management system based on response feedback, including a real-time dynamic resource allocation module, an intelligent task priority adjustment module, an adaptive risk warning module, and a visualization analysis module.

[0071] Furthermore, the real-time dynamic resource allocation module is used to dynamically adjust resource allocation based on real-time feedback, the intelligent task priority adjustment module is used to dynamically adjust task priority according to task completion status and resource status, the adaptive risk warning module is used to monitor project data in real time and predict potential project risks, and the visualization analysis module is used to integrate data from various modules and display the integration results in data visualization.

[0072] It should be noted that the real-time dynamic resource allocation module feeds back the monitored resource status to the intelligent task priority adjustment module and the adaptive risk warning module. The intelligent task priority adjustment module receives the resource status feedback from the real-time dynamic resource allocation module, adjusts task allocation, and feeds back the task completion status to the adaptive risk warning module and the visualization analysis module. The adaptive risk warning module receives task progress feedback from the intelligent task priority adjustment module and resource status feedback from the real-time dynamic resource allocation module, identifies risks, and adjusts countermeasures. The visualization analysis module integrates the feedback data from the real-time dynamic resource allocation module, the intelligent task priority adjustment module, and the adaptive risk warning module, and uses data technology to display the data in an interactive page format on a visualization terminal, enabling relevant personnel to supervise the project and make rapid decisions.

[0073] It should be noted that through the joint collaboration of various modules, the modules are closely connected to each other, and the front-end modules have an effect on the back-end modules. The results of the front-end modules affect the output of the back-end modules, and the feedback of the front-end modules affects the real-time response of the back-end modules, thereby achieving flexible and precise control of enterprise project management.

[0074] Furthermore, the real-time dynamic resource allocation module monitors project progress and resource status in real time, uses machine learning algorithms to predict future investment needs, automatically adjusts resource allocation based on the predicted investment needs, and feeds back the monitored resource status to the intelligent task priority adjustment module and the adaptive risk warning module.

[0075] Specifically, the real-time monitoring of project progress and resource status is achieved by using data acquisition equipment to retrieve enterprise data from the enterprise database in real time. The enterprise data includes project progress data, resource usage data, and historical project data.

[0076] The method of predicting future investment demand using machine learning algorithms involves constructing a future investment demand model based on a linear regression algorithm. The specific construction of this model is as follows:

[0077] y t =β0+β1x 1t +β2x 2t +...+β n x nt +ε t

[0078] Among them, y t This represents the resource requirement of the project at time t, and β0 represents the intercept term of the linear regression, which is calculated by substituting historical data. itThis represents the i-th characteristic value of the project at time t, including the project completion rate, current resource usage, human resource workload, equipment failure rate, and equipment usage status, ε. t Represents the error term, β i Represent each feature x it The regression coefficients, error term, and regression coefficients are calculated by training the future investment demand model, as follows:

[0079] The model is trained using historical data as the training dataset, and compared with the current project.

[0080] Select similar projects from historical data. The similar projects are matched according to the current project's scheduled construction period, project objectives, construction team, and acceptance unit, and the number of matches is no less than 2.

[0081] Based on the current project schedule, select data corresponding to the time schedule from historical data, including historical resource requirements (y). t ′ and historical eigenvalues ​​x i ′ t ;

[0082] Finally, the selected data is used to train the constructed model, and the regression coefficient β corresponding to each feature value can be calculated. i The calculated regression coefficients are then mapped to the current project to predict resource requirements at future points in time.

[0083] Furthermore, the automatic adjustment of resource allocation based on predicted investment demand is achieved by constructing a linear programming equation and applying dynamic adjustment constraints to the constructed equation, thereby realizing the automatic adjustment of resource allocation based on predicted investment demand. The specific implementation is as follows:

[0084] Construct linear programming equations,

[0085] Constraints are applied using dynamically adjusted constraints.

[0086]

[0087]

[0088]

[0089] Among them, X ij a represents the number of resources allocated to the i-th item in task j. ij This represents the contribution coefficient of the i-th resource to the j-th task. Before the current project starts, historical data will be used as reference data to set the contribution coefficient according to the importance of the resource to the task.j w represents the predicted demand for the j-th task. j Y represents the priority weight of task j, which is a priority weight pre-assigned to each task based on historical data before the current project starts. Y represents the total resource investment of the current project. ij This represents the priority weight of the i-th resource and the j-th task. It is a priority weight pre-assigned to each resource based on historical data before the current project starts. ij This represents the predicted demand for the i-th resource in the j-th task.

[0090] It should be noted that the use of dynamically adjusted constraints to constrain the constructed equations involves applying constraints to the linear programming equations to achieve adaptive resource allocation, as detailed below:

[0091] For different tasks, the resource allocation is determined by X. ij The constraint ≥0 means that when allocating resources according to the linear programming equation, it is necessary to ensure that the resource allocation quantity for the task is greater than 0.

[0092] For task priority weights, through The constraint indicates that the actual resource allocation for the current task is greater than the predicted resource allocation based on the priority weight of the current task.

[0093] For adaptive resource allocation, the allocation is performed using the calculation result f of the linear programming equation, y ij w ij This represents a comprehensive score for the current task, derived through a combined analysis of the predicted resource quantity and priority weights for that task. Y represents the total comprehensive score of all tasks in the current project, Y represents the total resource input of the current project, and f represents the allocation quantity of the i-th resource assigned to task j, which is adaptively allocated based on the proportion of the comprehensive score of the current task in the entire project.

[0094] Furthermore, the intelligent task priority adjustment module resets the task priority weights of the current project based on the task completion rate and the amount of resources allocated, thereby completing the adaptive adjustment of the priority of the current project tasks and feeding the adjustment results back to the real-time dynamic resource allocation module for secondary control of the resource allocation of tasks in the real-time dynamic resource allocation module.

[0095] Specifically, the repriority weighting of tasks in the current project is determined by comprehensively considering task completion rate and resource allocation results, and the specific calculation formula is as follows:

[0096]

[0097]

[0098] Where λ represents the completion rate of the current task, t represents the time the current task has been performed, T represents the scheduled duration of the entire project, and w j This represents the priority weight assigned to tasks before the project starts, f represents the amount of resources allocated to the current project, and w′ represents the priority weight assigned to tasks before the project starts. j This indicates the priority weight for adaptive allocation of tasks to the current task. The specific adaptive allocation is as follows:

[0099] The task completion rates λ are sorted in descending order, and the current project's completion rate is compared with the historical project completion rates λ′ within the same duration. Based on the comparison results, the task priority weights are adaptively adjusted. Specifically,

[0100] When the comparison result satisfies the formula λ≤λ′, it means that the completion rate of the current task is lower than the historical task completion rate. The priority weight of the current task is increased, and the increased priority weight is fed back to the real-time dynamic resource allocation module to increase the amount of resources allocated to the current task, thus completing the secondary adjustment of the resource allocation of the task.

[0101] When the comparison result satisfies the formula λ>λ′, it means that the completion rate of the current task is higher than the historical task completion rate. The priority weight of the current task is reduced, and the reduced priority weight is fed back to the real-time dynamic resource allocation module to reduce the amount of resources allocated to the current task, thus completing the secondary adjustment of the resource allocation of the task.

[0102] Furthermore, the adaptive risk warning module identifies potential risks in the project by monitoring project data in real time and based on the monitoring results, as specifically implemented as follows:

[0103] The monitored project data is constructed into a dataset R = [r1, r2, r3, ..., r n ], where each feature vector r i It includes multiple feature values, and the feature vector includes project progress data, resource usage data, quality data, and environmental data. The feature values ​​included in the project progress data are task completion time and task delay status.

[0104] The probability of a risk occurring using a feature vector is calculated using a Bayesian network. The specific calculation formula is as follows:

[0105]

[0106] Where P(R|r) represents the eigenvector r i Given the occurrence of [something], the probability of project risk, P(r) i ) represents the eigenvector r iThe probability of occurrence, P(R) represents the initial probability of the project risk occurring, P(r) i |R) represents the feature vector r when a risk occurs in the project. i The probability of its occurrence.

[0107] Furthermore, the identification of potential risks in a project based on monitoring results involves calculating the probability of risk occurrence and using a support vector machine model to predict the risk type. The specific prediction is as follows:

[0108] The calculated probability of the risk occurring P(R|r) i Using r1, r2, r3, ..., r4 as new feature vectors, construct a new feature set R′, satisfying the formula R′ = [r1, r2, r3, ..., r4]. n ,P(R1|r i ),P(R2|r i ),...,P(R m |r i ]], where n represents the total number of original features and m represents the total number of project risk types, which are set based on historical data;

[0109] A support vector machine model is constructed to predict risk types. The specific model is as follows:

[0110]

[0111] Among them, R T Let W represent the risk type prediction result, W represent the weight vector that controls the accuracy of risk classification, b represent the bias term, and R represent the risk type prediction result. i ′ represents the true risk type of the i-th feature vector.

[0112] It should be noted that the values ​​of the weight vectors and bias terms in the support vector machine model are obtained through training using historical data, as detailed below:

[0113] The feature vectors r from the historical data that are the same as those in the current feature set R′ are... i And the corresponding probability of risk occurrence P′(R|r) i The weight vector W and the bias term b are input into the constructed support vector machine model. After inputting multiple sets of inputs, the values ​​of the weight vector W and the bias term b in the model can be obtained.

[0114] The calculated weight vector W and the bias term b are substituted into the constructed support vector machine model to complete the prediction of risk type.

[0115] Furthermore, the visualization analysis module integrates feedback data from the real-time dynamic resource allocation module, the intelligent task priority adjustment module, and the adaptive risk warning module, and uses data technology to display the data in an interactive page format on the visualization terminal, so that relevant staff can supervise the project and make quick decisions.

[0116] Specifically, the integration of feedback data from the real-time dynamic resource allocation module, the intelligent task priority adjustment module, and the adaptive risk warning module involves evaluating the data from each module using a comprehensive scoring method, and using the evaluation results as the data basis for subsequent page interactions. The specific implementation is as follows:

[0117] For any task j in the current project, the data from the real-time dynamic resource allocation model is f. j This indicates the amount of resources allocated to the current task; the data from the intelligent task priority adjustment module is w. j , indicating the priority of the current task, and the data from the adaptive risk warning module is R. Tj This indicates the type of risk arising from the current task;

[0118] The data for each module are evaluated using a weighted average method, as detailed below:

[0119]

[0120] Among them, f j This represents data from a real-time dynamic resource allocation model, w j This indicates data from the intelligent task priority adjustment module, R Tj This indicates data from the adaptive risk warning module;

[0121] The weighted average data will then be comprehensively evaluated to assess the stability of the current project progress. The specific evaluation is as follows:

[0122] E=W f ·f J +W w ·w J +W R ·R Tj

[0123] Among them, W f 、W w 、W R The weights of each module's data are set based on the contribution of the current task to the project in historical data. E represents the calculated comprehensive score, which is used as the basis for the vertical axis display on the visualization terminal.

[0124] Finally, the calculated comprehensive score is used as the vertical axis in the visualization terminal display, and the time progress is used as the horizontal axis in the visualization terminal display, so that relevant staff can make quick decisions based on the visualization terminal display results.

[0125] It should be noted that when staff make quick decisions based on the results displayed on the visualization terminal, they first analyze the main factors affecting the project's progress, as detailed below:

[0126] For data with abnormal overall project scores, a secondary analysis should be conducted;

[0127] Secondary analysis involves a detailed analysis of the nodes exhibiting anomalies in the overall score, examining the data from each module within the overall score.

[0128] When data from the real-time dynamic resource allocation module is abnormal, the cause of the project abnormality is uneven allocation of task resources. The task resource allocation should be readjusted immediately so that the project can return to normal operation.

[0129] When an abnormal data block is received from the intelligent task priority adjustment module, the reason for the project abnormality is that the task priority adjustment is improper, resulting in uneven allocation of task resources. The priority needs to be readjusted according to the urgency of the tasks so that the project can return to normal working status.

[0130] When data from the adaptive risk warning module is abnormal, the cause of the project abnormality is that the project risk type assessment is incorrect, which leads to the implementation of incorrect preventive measures, and thus the project abnormality. It is necessary to reassess the entire project risk type in order to formulate the correct implementation plan and restore the project to normal operation.

[0131] Example 2

[0132] The second embodiment of the present invention provides a practical application case of an enterprise project management system based on response feedback, as detailed below:

[0133] The project team first conducted a detailed requirements analysis, identified the key objectives and resource requirements of the project, and deployed the response-based enterprise project management system into the enterprise's existing IT infrastructure, including servers and cloud services.

[0134] Based on project needs and existing resources, a preliminary resource allocation will be conducted.

[0135] During the project, the system monitors project progress and resource usage in real time, uses machine learning algorithms to predict future resource needs, and dynamically adjusts resource allocation based on the prediction results to ensure efficient resource utilization.

[0136] The system adjusts task priority in real time based on task completion status and resource status;

[0137] The task completion status will be fed back to the system in real time. The system will then dynamically adjust the task priority based on the feedback data to ensure that critical tasks can be completed first, thereby improving the overall progress and quality of the project.

[0138] The system monitors project data in real time and predicts potential risks through data analysis;

[0139] When a potential risk is detected, the system will immediately issue an alert and provide corresponding countermeasure suggestions. The project team can then quickly adjust project plans and resource allocation based on the alert information to mitigate the impact of the risk on the project.

[0140] Finally, visualization technology is used to display the integrated data on a visual terminal in an interactive page format, making it convenient for project managers to monitor the project in real time and make quick decisions.

[0141] To further highlight the beneficial effects of the technical solution of the present invention, the technical features of the present invention are compared with the prior art, as shown in the table below:

[0142]

[0143] The comparison table above clearly shows that the response-based enterprise project management system demonstrates significant improvements across all key indicators, particularly in resource utilization efficiency, task completion rate, and project risk reduction rate, showcasing its remarkable superiority. The data comparison also provides a clear view of the substantial improvements that the system's implementation has brought to enterprise project management.

[0144] Furthermore, if the aforementioned function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0145] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, instruction execution methods, apparatus, or devices (such as computer-based methods, processor-based methods, or other methods that can fetch and execute instructions from or in conjunction with such methods, apparatus, or devices). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by or in conjunction with instruction execution methods, apparatus, or devices.

[0146] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0147] Furthermore, in order to provide a concise description of exemplary embodiments, not all features of actual embodiments (i.e., those features that are not relevant to the currently considered best mode for carrying out the invention, or those features that are not relevant to implementing the invention) may be omitted.

[0148] It should be understood that numerous specific implementation decisions can be made during the development of any practical implementation, such as in any engineering or design project. Such development efforts may be complex and time-consuming, but for those skilled in the art who benefit from this disclosure, the development effort will be a routine work of design, manufacturing, and production without requiring much experimentation.

[0149] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An enterprise project management system based on response feedback, characterized by: include, Real-time dynamic resource allocation module, intelligent task priority adjustment module, adaptive risk warning module and visual analysis module; The real-time dynamic resource allocation module is used to dynamically adjust resource allocation based on real-time feedback; Automatically adjusting resource allocation according to predicted investment needs is achieved by constructing the calculation results of a linear programming equation and constraining the constructed equation using dynamic adjustment constraints to achieve automatic adjustment of resource allocation according to predicted investment needs. The specific implementation is as follows: Construct the linear programming equation, Use dynamic adjustment constraints to constrain, Among them, X ij represents the number of resources assigned to task j, a ij The contribution coefficient of the jth task of the i-th resource is set based on the historical data as reference data before the current project is launched, according to the importance of the resource to the task. j represents the predicted demand for the jth task, w j represents the priority weight of the jth task. It is the priority weight set for each task in advance based on historical data as reference data before the current project starts. Y represents the total resource investment of the current project, and w ij represents the priority weight of the jth task of the i-th resource. It is the priority weight set for each resource in advance based on historical data as reference data before the current project starts. ij represents the predicted demand for the i-th resource of the j-th task; The method of constraining the constructed equation by dynamically adjusting the constraint condition is to constrain the linear programming equation by the establishment of the constraint condition to complete the adaptive allocation of resources, as follows: For different task resource allocations, ij ≥0 is used as a constraint, which means that when allocating resources according to the linear programming equation, it is necessary to ensure that the number of resources allocated to the task is greater than 0; For the priority weight of the task, A constraint is imposed, indicating that the actual resource allocation for the current task is greater than the predicted resource quantity predicted based on the current task priority weight; For adaptive allocation of resources, the calculation result f of the linear programming equation is used for allocation, y ij w ij It represents the comprehensive score for the current task, which is obtained through comprehensive analysis of the predicted resource volume and priority weight of the current task. represents the sum of the comprehensive scores of all tasks in the current project, Y represents the total resource input of the current project, and f represents the allocation quantity of the i-th resource allocated to task j, which is adaptively allocated according to the proportion of the comprehensive score of the current task in the entire project; The intelligent task priority adjustment module is used to dynamically adjust the task priority according to the task completion status and resource status; The intelligent task priority adjustment module resets the task priority weight of the current project according to the task completion rate and the amount of resource allocation, and feeds back the adjustment result to the real-time dynamic resource allocation module to perform secondary regulation on the resource allocation of tasks in the real-time dynamic resource allocation module; The resetting of the task priority weight of the current project is carried out by comprehensively considering the task completion rate and resource allocation results. The specific calculation formula is as follows: Among them, λ represents the completion rate of the current task, t represents the time of the current task, T represents the specified duration of the entire project, and w j represents the priority weight set for the task before the project starts, f represents the number of resources allocated to the current project, and w′ j Indicates the priority weight of the current task's adaptive allocation. The specific adaptive allocation is as follows: Sort the task completion rates λ in descending order, and compare the task completion rate of the current project with the completion rate λ′ of the historical projects in the same duration. Adaptively adjust the task priority weights based on the comparison results. Specifically, When the comparison result satisfies the formula λ≤λ′, it means that the completion rate of the current task is lower than the completion rate of the historical tasks. The priority weight of the current task is increased, and the increased priority weight is fed back to the real-time dynamic resource allocation module to increase the resource allocation quantity of the current task, thus completing the secondary regulation of the resource allocation of the task. When the comparison result satisfies the formula λ>λ′, it means that the completion rate of the current task is higher than the completion rate of the historical tasks. The priority weight of the current task is reduced, and the reduced priority weight is fed back to the real-time dynamic resource allocation module to reduce the number of resources allocated to the current task, thus completing the secondary regulation of the resource allocation of the task. The adaptive risk warning module is used to monitor project data in real time and predict potential risks of the project; The adaptive risk warning module monitors project data in real time and identifies potential risks of the project based on the monitoring results. The specific implementation is as follows: The monitored project data is constructed into a data set R = [r1, r2, r3, ..., r n ], where each eigenvector r i It includes multiple feature values, and the feature vector includes project progress data, resource usage data, quality data, and environmental data. The feature values ​​of the project progress data include task completion time and task extension status; The Bayesian network is used to calculate the probability of risk of the feature vector. The specific calculation formula is as follows: Among them, P(R|r) represents the feature vector r i The probability of project risk occurring under the appearance of i ) represents the feature vector r i The probability of occurrence of the risk, P(R) represents the initial probability of the project risk, P(r i |R) indicates that when a project encounters risk, the eigenvector r i The probability of occurrence; The identification of potential risks of the project based on the monitoring results is based on the calculation of the probability of risk occurrence and the use of the support vector machine model to predict the risk type. The specific prediction is as follows: The calculated risk probability P(R|r i ) as a new feature vector, construct a new feature set R′, and satisfy the formula R′=[r1,r2,r3,..,r n ,P(R1|r i ),P(R2|r i ),...,P(R m |r i )], where n represents the total number of original features and m represents the total number of project risk types, which are set based on historical data; Construct a support vector machine model to predict risk types. The specific model is as follows: Among them, R T represents the risk type prediction result, W represents the weight vector, which controls the accuracy of risk classification, b represents the bias term, and R i ′ represents the true risk type of the i-th eigenvector; The visualization analysis module is used to integrate the data of each module and visualize the integration results.

2. The enterprise project management system based on response feedback as claimed in claim 1, characterized in that: The real-time dynamic resource allocation module monitors the project progress and resource status in real time, and uses machine learning algorithms to predict future investment needs, automatically adjusts resource allocation according to the predicted investment needs, and feeds back the monitored resource status to the intelligent task priority adjustment module and the adaptive risk warning module; the use of machine learning algorithms to predict future investment needs is to use machine learning algorithms to build a future investment demand model, and the future investment demand model is built based on a linear regression algorithm, and the specific construction is as follows: y t =β0+β1x 1t +β2x 2t +...+b n x nt +e t Among them, y t represents the resource demand of the project at time t, β0 represents the intercept term of linear regression, which is calculated by substituting historical data, x it represents the i-th eigenvalue of the project at time t, including the project completion rate, current resource usage, human resource workload, equipment damage rate, and equipment usage status, ε t represents the error term, β i Represents each feature x it The regression coefficient, error term and regression coefficient are calculated by training the future investment demand model, as follows: Use historical data as training data sets to train the constructed model and compare it with the current ongoing project. Select similar projects from historical data, where the similar projects are matched according to the scheduled construction period, project objectives, construction team and acceptance unit of the current project, and the number of matches is not less than 2; According to the schedule date of the current project, select the corresponding time schedule data from the historical data, including the historical resource demand y t ′ and historical eigenvalue x i ' t ; Finally, the constructed model is trained with the selected data, and the regression coefficient β corresponding to each eigenvalue can be calculated. i , and maps the calculated regression coefficients to the current project to predict resource requirements at future time points.

3. The enterprise project management system based on response feedback as claimed in claim 2, characterized in that: The visualization analysis module integrates the feedback data from the real-time dynamic resource allocation module, the intelligent task priority adjustment module and the adaptive risk warning module, and uses data technology to display the data in the form of page interaction to the visualization terminal; The integration of feedback data from the real-time dynamic resource allocation module, the intelligent task priority adjustment module, and the adaptive risk warning module is to evaluate the data of each module in a comprehensive scoring manner, and use the evaluation results as the data basis for subsequent page interactions. The specific implementation is as follows: For any task j in the current project, the data from the real-time dynamic resource allocation model is f j , represents the number of resources allocated to the current task, and the data from the intelligent task priority adjustment module is w j , indicating the priority of the current task, and the data from the adaptive risk warning module is R Tj , indicating the risk type caused by the current task; The data of each module is evaluated by weighted average, as follows: Among them, f j represents the data from the real-time dynamic resource allocation model, w j represents the data from the intelligent task priority adjustment module, R Tj Represents data from the adaptive risk early warning module; The weighted average data will be evaluated comprehensively, and the specific evaluation is as follows: E=W f ·f J +W w ·w J +W R ·R TJ Among them, W f , W w , W R Respectively represent the weight of each module data, which is set according to the contribution of the current task to the project in the historical data. E represents the calculated comprehensive score, which is used as the ordinate basis for the visualization terminal display; Finally, the calculated comprehensive score is used as the basis for the vertical axis in the visualization terminal display, and the time progress is used as the basis for the horizontal axis in the visualization terminal display, so that relevant staff can make quick decisions based on the visualization terminal display results.

Images