Project task progress display system, progress generation method and related equipment

Abstract

The invention discloses a project task progress display system, a progress generation method and related equipment, and the system can effectively integrate various types of information such as real-time progress data, team member biological rhythm data and environmental parameter data of a project task through a multi-source data collection module and a data fusion processing module. Project management decisions can be established on the basis of richer and more reliable data, the progress exception processing module integrated in the system can detect progress deviation in real time, and corresponding processing measures are automatically taken according to the deviation degree. By means of the intelligent exception handling mechanism, the response speed and the handling efficiency of the system to project risks are remarkably improved, and the risks of project delay and hyper-cost are effectively reduced. And the most suitable visualization mode can be automatically selected according to project characteristics, user preferences and data characteristics.

Description

Technical Field

[0001] This invention relates to the field of project management technology, specifically to a project task progress display system, a progress generation method, and related equipment. Background Technology

[0002] As project management becomes increasingly complex, traditional project schedule management and display systems have been widely adopted across various industries. These systems typically include modules for data acquisition, schedule calculation, risk assessment, and visualization. Currently, common project schedule display systems primarily rely on methods such as Gantt charts, Critical Path Method (CPM), and Project Evaluation and Review Technique (PERT) to track and display project progress. Meanwhile, some advanced systems also integrate resource management, cost control, and quality monitoring functions, providing project managers with comprehensive decision support.

[0003] However, existing project task progress display systems still have some significant shortcomings. First, most systems lack the ability to effectively integrate multi-source heterogeneous data, making it difficult to fully utilize various data resources within the project environment. Second, traditional systems often employ static or semi-static methods for progress calculation and risk assessment, failing to adapt to rapidly changing project environments. Third, the visualization functions of existing systems are typically fixed, making it difficult to dynamically adjust the display method according to different user needs and preferences. Finally, these systems often react slowly to anomaly detection and handling, lacking intelligent decision support capabilities.

[0004] In light of the aforementioned issues, improvements to the project task progress display system primarily focus on the following aspects: enhancing the fusion and processing capabilities of multi-source data, improving the system's dynamic adaptability and intelligence level, enhancing the flexibility and personalization of visualization, and strengthening the intelligent handling and decision support capabilities for anomalies. Simultaneously, effectively utilizing advanced technologies such as artificial intelligence and big data analytics to improve the overall performance of the system is also a key research direction. Summary of the Invention

[0005] The purpose of this invention is to provide a project task progress display system, a progress generation method, and related equipment to solve the problems existing in the current project task progress display system mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a project task progress display system, comprising: The multi-source data acquisition module is used to simultaneously collect real-time progress data of project tasks, team member biorhythm data, and environmental parameter data; The data fusion processing module is used to clean, align, and fuse the collected multi-source heterogeneous data to generate multi-dimensional standardized progress information. The dynamic weighted progress calculation module is used to dynamically adjust the weights of data in each dimension according to the project stage and type, and calculate the comprehensive progress index of the project tasks. The adaptive display module can automatically adjust the displayed content and method according to the user's device, network conditions, and personal preferences; The intelligent prediction module based on graph neural networks is used to build a task dependency graph, analyze historical data and current progress, and predict project completion time, resource bottlenecks and potential risks.

[0007] Preferably, the data fusion processing module specifically includes: The data cleaning unit is used to handle missing values, outliers, and duplicate data; Time alignment units unify data from different sources and sampling frequencies to the same time scale; The feature extraction unit extracts meaningful features from the raw data; The multimodal fusion unit uses attention mechanisms and transfer learning techniques to fuse data features from different modalities. The data quality assessment unit performs consistency and reliability checks on the merged data and determines, based on preset thresholds, whether to adopt the current merged result or trigger a process of re-collecting or processing a specific data source.

[0008] Preferably, it also includes a progress anomaly handling module, specifically comprising: The schedule deviation detection unit is used to compare the actual progress with the planned progress in real time. The deviation classification unit categorizes schedule anomalies into three levels: minor, moderate, and severe, based on the degree of deviation. The cause analysis unit uses data mining and pattern recognition techniques to identify possible causes of schedule anomalies. The response strategy generation unit generates corresponding response strategies based on the anomaly level and cause. in: When a slight deviation is detected, the system automatically adjusts the task priority and sends optimization suggestions to the task execution module; When a moderate deviation is detected, the system triggers a resource reallocation process and sends an alarm message to the decision support system. When a serious deviation is detected, the system automatically suspends the affected tasks, activates the emergency response mechanism, and generates a detailed problem report. If no abnormalities are found within three consecutive detection cycles, the system will appropriately increase the monitoring frequency to optimize system resource utilization.

[0009] Preferably, the system integrates an intelligent risk assessment module, including: The risk factor identification unit identifies potential risk factors by analyzing historical data and current project characteristics; The risk probability calculation unit uses a Bayesian network model to calculate the probability of each risk occurring. The impact assessment unit evaluates the potential impact of each risk factor on the project schedule. The risk level assessment unit, taking into account both the probability and the degree of impact of the risk, divides the risk into three levels: low, medium, and high. The response recommendation unit recommends corresponding response measures based on the risk level. in: When a low-level risk is identified, the system adds the risk information to the project risk log and focuses on it during the next routine system check. When a medium-level risk is identified, the system immediately pushes the risk information to the risk management subsystem and initiates an automated risk response plan generation program. When a high-level risk is identified, the system automatically adjusts the affected task schedule and triggers a cross-departmental collaboration mechanism to initiate a virtual risk assessment meeting. If an identified risk remains unchanged for three consecutive assessment periods, the system will reassess the relevance of the risk and consider whether to move it from the active monitoring list to the potential risk pool.

[0010] Preferably, the adaptive display module includes: The multidimensional data analysis unit is used to process and analyze project progress data from different dimensions; The dynamic weight calculation unit dynamically adjusts the weights of data in each dimension based on project stage, data reliability, and user concerns. An adaptive visualization engine can automatically select the most suitable visualization method based on data characteristics and display requirements; An interactive data exploration interface that allows users to conduct in-depth analysis of specific data through custom queries; Personalized recommendation systems recommend the most relevant data views based on users' historical behavior and preferences; in: The dynamic weight calculation employs a modified analytic hierarchy process (AHP), considering factors including but not limited to: a) Data timeliness weight Wt, which reflects the data update frequency and real-time performance; b) Data reliability weight Wr, based on historical accuracy assessment of the data source; c) Task criticality weight Wc, which reflects the importance of the task to the overall project; d) User attention weight Wu, dynamically adjusted based on user interaction behavior; The formula for calculating the overall weight is: W = α × Wt + β × Wr + γ × Wc + δ × Wu Where α, β, γ, and δ are dynamic adjustment parameters, and α+β+γ+δ=1; The adaptive visualization engine selects from the following visualization methods based on the weighted characteristics of the data: a) When the data shows a clear time trend, prioritize time series plots or Gantt charts; b) When it is necessary to display multidimensional data relationships, use a parallel coordinate graph or a scatter matrix; c) For hierarchical data, use a tree diagram or sunburst diagram; d) When illustrating complex network relationships, use force-directed graphs or Sankey diagrams; The system continuously optimizes weight calculation and visualization selection strategies through machine learning algorithms, specifically including: a) Optimize personalized recommendations using collaborative filtering algorithms; b) Adjust the dynamic weight parameters using reinforcement learning methods; c) Continuously evaluate and improve visualization through A / B testing.

[0011] A method for generating project task schedules. Includes the following steps: S1. Collect multi-source heterogeneous data, including structured data from traditional project management systems, semi-structured data from team collaboration platforms, unstructured text data related to projects, and environmental and equipment operation data collected by IoT devices; S2. Use multimodal deep learning models to process and fuse various types of data; S3. Construct a dynamic knowledge graph to represent the complex relationships between the elements of the project; S4. Calculate multi-dimensional project progress indicators based on the fused data and knowledge graph; S5. Apply graph neural networks and time series analysis to predict future project progress and potential risks; S6. Based on the degree of deviation between the forecast results and the preset target, determine whether to maintain the current project plan, make fine-tuning and optimization, or initiate a large-scale plan adjustment process; S7. Generate visual reports and interactive dashboards to display project progress.

[0012] Preferably, the steps of the multimodal deep learning model in processing and fusing various types of data specifically include: Perform feature engineering and normalization on structured data; Use pre-trained language models to analyze text data and extract key information and sentiment. Apply time series analysis models to process continuous sensor data; Design a multimodal attention mechanism to weightedly fuse information from different sources; Transfer learning techniques are used to adapt models pre-trained on large-scale datasets to specific project scenarios. Based on the historical accuracy of each data source and the characteristics of the current project stage, determine and select the most suitable data fusion strategy.

[0013] Preferably, the steps for constructing the dynamic knowledge graph specifically include: Define the ontology model to describe the concepts and relationships within the project domain; Extract entities and relationships from multi-source data to populate the knowledge graph; Using graph embedding techniques, knowledge graphs are transformed into low-dimensional vector representations; Apply graph convolutional networks to perform information propagation and aggregation on knowledge graphs; Design a knowledge graph update mechanism to dynamically adjust the knowledge graph structure based on new data and user feedback; Based on the project's progress stage and the criticality of the tasks, determine which subgraphs in the knowledge graph require priority updates and optimization.

[0014] A computer-readable storage medium having a computer program stored thereon. When the program is executed by the processor, it implements the steps of any of the project task progress generation methods described above.

[0015] A computer device, including memory and processor, The memory stores a computer program, and when the processor executes the computer program, it implements the steps of any of the project task schedule generation methods described above.

[0016] Compared with the prior art, the beneficial effects of the present invention are: 1) This system, through its multi-source data acquisition and data fusion processing modules, effectively integrates various types of information, including real-time progress data of project tasks, team member biorhythm data, and environmental parameter data. This comprehensive data fusion greatly improves the accuracy and comprehensiveness of progress assessment, enabling project management decisions to be based on a richer and more reliable data foundation. 2) The integrated schedule anomaly handling module of this system can detect schedule deviations in real time and automatically take corresponding measures based on the degree of deviation. This intelligent anomaly handling mechanism significantly improves the system's response speed and processing efficiency to project risks, effectively reducing the risk of project delays and cost overruns; 3) The adaptive display module of this invention employs dynamic weight calculation and adaptive visualization technology, which can automatically select the most suitable visualization method based on project characteristics, user preferences, and data characteristics. This greatly improves the relevance and effectiveness of information display, enabling users with different roles to quickly obtain the project progress information they care about most; 4) This system continuously optimizes weight calculation and visualization selection strategies through machine learning algorithms, and constantly improves its performance using techniques such as collaborative filtering and reinforcement learning. This ability to continuously learn and optimize enables the system to improve its accuracy and applicability with use, providing increasingly precise and personalized support for long-term project management. Attached Figure Description

[0017] Figure 1 This is an overall architecture diagram of a project task progress display system according to the present invention; Figure 2 This is a flowchart of the data fusion processing module of a project task progress display system according to the present invention; Figure 3 This is a flowchart of a project task progress generation method according to the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] In the description of the invention, it should be noted that the terms "upper," "lower," "inner," "outer," "front end," "rear end," "both ends," "one end," and "the other end," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0020] In the description of the invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installed," "equipped with," "connected," etc., should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0021] In the description of the invention, it should be noted that the execution order of the steps is not limited by the sequence number. The possible changes in the order of some steps, the synchronous execution of steps, and the split execution of steps are all within the scope of protection of this application.

[0022] Please see Figure 1 This invention provides a technical solution: a project task progress display system, comprising: The multi-source data acquisition module is used to simultaneously collect real-time progress data of project tasks, team member biorhythm data, and environmental parameter data; The data fusion processing module is used to clean, align, and fuse the collected multi-source heterogeneous data to generate multi-dimensional standardized progress information. The dynamic weighted progress calculation module is used to dynamically adjust the weights of data in each dimension according to the project stage and type, and calculate the comprehensive progress index of the project tasks. The adaptive display module can automatically adjust the displayed content and method according to the user's device, network conditions, and personal preferences; The intelligent prediction module based on graph neural networks is used to build a task dependency graph, analyze historical data and current progress, and predict project completion time, resource bottlenecks and potential risks.

[0023] Therefore, through multi-source data acquisition and fusion, the system provides more comprehensive and accurate project progress information. Dynamic weight calculation and adaptive display functions enable the system to flexibly adapt to the needs of different projects and users. The graph neural network-based prediction module significantly improves risk warning and resource optimization capabilities.

[0024] Specifically, graph neural networks are an emerging deep learning method that is particularly well-suited for processing data with graph structures. In project management, the dependencies between tasks naturally form a graph structure. Therefore, using graph neural networks can better capture the complex relationships between tasks, thereby improving the accuracy of predictions.

[0025] Please see Figure 2 In some embodiments, the data fusion processing module specifically includes: The data cleaning unit is used to handle missing values, outliers, and duplicate data; Time alignment units unify data from different sources and sampling frequencies to the same time scale; The feature extraction unit extracts meaningful features from the raw data; The multimodal fusion unit uses attention mechanisms and transfer learning techniques to fuse data features from different modalities. The data quality assessment unit performs consistency and reliability checks on the merged data and determines, based on preset thresholds, whether to adopt the current merged result or trigger a process of re-collecting or processing a specific data source.

[0026] Therefore, the data fusion processing module ensures the quality and consistency of multi-source heterogeneous data through multi-step data processing, providing a reliable data foundation for subsequent progress calculations and predictions. In particular, the introduction of the data quality assessment unit further improves the stability and reliability of the system.

[0027] Specifically, multimodal fusion refers to the technology of comprehensively analyzing information from different data sources (such as text, images, sensor data, etc.). In this system, this technology can integrate different types of project data to provide a more comprehensive view of the project status.

[0028] In some embodiments, a progress exception handling module is also included, specifically comprising: The schedule deviation detection unit is used to compare the actual progress with the planned progress in real time. The deviation classification unit categorizes schedule anomalies into three levels: minor, moderate, and severe, based on the degree of deviation. The cause analysis unit uses data mining and pattern recognition techniques to identify possible causes of schedule anomalies. The response strategy generation unit generates corresponding response strategies based on the anomaly level and cause. in: When a slight deviation is detected, the system automatically adjusts the task priority and sends optimization suggestions to the task execution module; When a moderate deviation is detected, the system triggers a resource reallocation process and sends an alarm message to the decision support system. When a serious deviation is detected, the system automatically suspends the affected tasks, activates the emergency response mechanism, and generates a detailed problem report. If no abnormalities are found within three consecutive detection cycles, the system will appropriately increase the monitoring frequency to optimize system resource utilization.

[0029] Therefore, the schedule anomaly handling module can promptly detect and resolve project schedule anomalies, significantly reducing project risks. The automated anomaly handling process reduces the need for human intervention and improves project management efficiency. Furthermore, the adaptive monitoring frequency design optimizes system resource utilization.

[0030] Specifically, the schedule deviation classification uses three levels: minor, moderate, and severe. This classification method allows the system to take corresponding measures according to different degrees of deviation, achieving more refined project management.

[0031] In some embodiments, the system integrates an intelligent risk assessment module, including: The risk factor identification unit identifies potential risk factors by analyzing historical data and current project characteristics; The risk probability calculation unit uses a Bayesian network model to calculate the probability of each risk occurring. The impact assessment unit evaluates the potential impact of each risk factor on the project schedule. The risk level assessment unit, taking into account both the probability and the degree of impact of the risk, divides the risk into three levels: low, medium, and high. The response recommendation unit recommends corresponding response measures based on the risk level. in: When a low-level risk is identified, the system adds the risk information to the project risk log and focuses on it during the next routine system check. When a medium-level risk is identified, the system immediately pushes the risk information to the risk management subsystem and initiates an automated risk response plan generation program. When a high-level risk is identified, the system automatically adjusts the affected task schedule and triggers a cross-departmental collaboration mechanism to initiate a virtual risk assessment meeting. If an identified risk remains unchanged for three consecutive assessment periods, the system will reassess the relevance of the risk and consider whether to move it from the active monitoring list to the potential risk pool.

[0032] Therefore, the intelligent risk assessment module provides comprehensive risk management functions, covering the entire risk management process from risk identification to response recommendation. Through automated risk assessment and processing, the efficiency and accuracy of project risk management are greatly improved.

[0033] Specifically, Bayesian networks are probabilistic graphical models particularly well-suited for handling uncertainty and complex dependencies. Using Bayesian networks in risk assessment allows for a better simulation of the interactions between various risk factors, thus providing more accurate risk predictions.

[0034] In some embodiments, the adaptive display module includes: The multidimensional data analysis unit is used to process and analyze project progress data from different dimensions; The dynamic weight calculation unit dynamically adjusts the weights of data in each dimension based on project stage, data reliability, and user concerns. An adaptive visualization engine can automatically select the most suitable visualization method based on data characteristics and display requirements; An interactive data exploration interface that allows users to conduct in-depth analysis of specific data through custom queries; Personalized recommendation systems recommend the most relevant data views based on users' historical behavior and preferences; in: The dynamic weight calculation employs a modified analytic hierarchy process (AHP), considering factors including but not limited to: a) Data timeliness weight Wt, which reflects the data update frequency and real-time performance; b) Data reliability weight Wr, based on historical accuracy assessment of the data source; c) Task criticality weight Wc, which reflects the importance of the task to the overall project; d) User attention weight Wu, dynamically adjusted based on user interaction behavior; The formula for calculating the overall weight is: W = α × Wt + β × Wr + γ × Wc + δ × Wu Where α, β, γ, and δ are dynamic adjustment parameters, and α+β+γ+δ=1; The adaptive visualization engine selects from the following visualization methods based on the weighted characteristics of the data: a) When the data shows a clear time trend, prioritize time series plots or Gantt charts; b) When it is necessary to display multidimensional data relationships, use a parallel coordinate graph or a scatter matrix; c) For hierarchical data, use a tree diagram or sunburst diagram; d) When illustrating complex network relationships, use force-directed graphs or Sankey diagrams; The system continuously optimizes weight calculation and visualization selection strategies through machine learning algorithms, specifically including: a) Optimize personalized recommendations using collaborative filtering algorithms; b) Adjust the dynamic weight parameters using reinforcement learning methods; c) Continuously evaluate and improve visualization through A / B testing.

[0035] Therefore, the adaptive display module, through dynamic weight calculation and adaptive visualization, greatly improves the personalization and effectiveness of data presentation. The introduction of machine learning algorithms enables the system to be continuously optimized and improved, providing users with increasingly accurate data views.

[0036] Specifically, the Analytic Hierarchy Process (AHP) is a decision-making method that systematizes and hierarchically addresses complex decision problems. In this system, an improved version of AHP is used to dynamically calculate the weights of different data dimensions, enabling the system to adapt more flexibly to different project situations and user needs.

[0037] Please see Figure 3 According to another aspect of this application, a method for generating project task schedules is also provided, characterized in that... Includes the following steps: S1. Collect multi-source heterogeneous data, including structured data from traditional project management systems, semi-structured data from team collaboration platforms, unstructured text data related to projects, and environmental and equipment operation data collected by IoT devices; S2. Use multimodal deep learning models to process and fuse various types of data; S3. Construct a dynamic knowledge graph to represent the complex relationships between the elements of the project; S4. Calculate multi-dimensional project progress indicators based on the fused data and knowledge graph; S5. Apply graph neural networks and time series analysis to predict future project progress and potential risks; S6. Based on the degree of deviation between the forecast results and the preset target, determine whether to maintain the current project plan, make fine-tuning and optimization, or initiate a large-scale plan adjustment process; S7. Generate visual reports and interactive dashboards to display project progress.

[0038] Specifically, the project task schedule generation method covers the entire process from data collection and processing to visualization. The advantage of this method lies in its comprehensiveness and flexibility, enabling it to adapt to various complex project management scenarios.

[0039] In some embodiments, the steps of processing and fusing various types of data using a multimodal deep learning model specifically include: Perform feature engineering and normalization on structured data; Use pre-trained language models to analyze text data and extract key information and sentiment. Apply time series analysis models to process continuous sensor data; Design a multimodal attention mechanism to weightedly fuse information from different sources; Transfer learning techniques are used to adapt models pre-trained on large-scale datasets to specific project scenarios. Based on the historical accuracy of each data source and the characteristics of the current project stage, determine and select the most suitable data fusion strategy.

[0040] Therefore, the project task progress generation method achieves efficient processing and fusion of different types of data through a multimodal deep learning model. Feature engineering and normalization improve the quality of structured data; the use of pre-trained language models greatly enhances the effectiveness of text data analysis; time series analysis ensures that the temporal characteristics of continuous data are fully utilized; the multimodal attention mechanism enables effective integration of information from different sources; and transfer learning technology allows the model to quickly adapt to different project scenarios. Furthermore, by dynamically selecting data fusion strategies, this method can optimize the data processing flow according to actual conditions, improving overall accuracy and efficiency.

[0041] In some embodiments, the steps of constructing a dynamic knowledge graph specifically include: Define the ontology model to describe the concepts and relationships within the project domain; Extract entities and relationships from multi-source data to populate the knowledge graph; Using graph embedding techniques, knowledge graphs are transformed into low-dimensional vector representations; Apply graph convolutional networks to perform information propagation and aggregation on knowledge graphs; Design a knowledge graph update mechanism to dynamically adjust the knowledge graph structure based on new data and user feedback; Based on the project's progress stage and the criticality of the tasks, determine which subgraphs in the knowledge graph require priority updates and optimization.

[0042] Therefore, the construction of dynamic knowledge graphs provides a powerful knowledge representation and reasoning framework for project schedule management. The definition of the ontology model ensures the standardization and consistency of knowledge; the extraction of entities and relations enables the system to automatically construct knowledge structures from raw data; and the application of graph embedding techniques and graph convolutional networks significantly improves the efficiency of knowledge processing and analysis. The dynamic update mechanism allows the knowledge graph to reflect the latest state of the project in a timely manner, while the selective update strategy optimizes the use of system resources. This approach not only improves the efficiency of project knowledge management but also provides a powerful tool for the analysis and decision support of complex project relationships.

[0043] Specifically, dynamic knowledge graphs are a knowledge representation method that evolves over time. In project management, dynamic knowledge graphs can better capture the complex relationships between project elements that change over time, providing more comprehensive and dynamic information support for decision-making.

[0044] Example 1 The following example is a specific implementation of a software development project, demonstrating how this system can be applied in actual project management.

[0045] Project Background A medium-sized software development project includes the following main phases: requirements analysis, design, coding, testing, and deployment. The project is expected to last 3 months.

[0046] The system application process is as follows: 1. Multi-source data acquisition Collect task completion information from project management software; Collect code commit frequency from the version control system; Collect meeting minutes and communication data from team collaboration platforms; Collect environmental data (such as temperature and noise level) from the environmental monitoring system.

[0047] 2. Data fusion processing The collected data is cleaned to remove outliers; Align data from different sources to a uniform time scale (e.g., daily). Extract key features, such as daily task completion rate, code submission volume, and team communication frequency.

[0048] 3. Dynamic weighted progress calculation Suppose that at some point in the project, we have the following data: Data timeliness weight Wt=0.3; data reliability weight Wr=0.25; task criticality weight Wc=0.3; user attention weight Wu=0.15; For a specific task (such as "user interface development"), we have the following rating: Timeliness rating: 8 (out of 10, data is very recent); Reliability rating: 7 (out of 10, data source is reliable); Criticality rating: 9 (out of 10, very important to the project); User attention rating: 6 (out of 10, users are quite concerned). Using the formula: W = α × Wt + β × Wr + γ × Wc + δ × Wu Submit specific data: W=0.3×8+0.25×7+0.3×9+0.15×6 =2.4 + 1.75 + 2.7 + 0.9 =7.75 The overall weight of 7.75 (out of 10) indicates that this task is of high importance at the current stage.

[0049] 4. Intelligent Prediction Based on Graph Neural Networks Construct a task dependency graph to connect the "user interface development" task with other related tasks (such as "backend API development" and "database design"); Graph convolutional networks are used to process task dependency graphs and predict task completion times and potential risks.

[0050] 5. Handling of progress anomalies Suppose the system detects that the actual progress of the "user interface development" task is 65%, while the planned progress should be 80%.

[0051] Calculate schedule deviation: Deviation = (Planned Schedule / Actual Schedule) × 100% =(80%-65%) / 80%×100% =18.75% According to the regulations of the progress exception handling module: The deviation is between 10% and 20%, which is considered a moderate deviation. The system automatically triggers a resource reallocation process and sends an alarm message to the decision support system.

[0052] 6. Intelligent Risk Assessment Based on the detected progress anomalies, the system conducts a risk assessment: Risk identification: Project delay risk; Risk probability calculation: Based on historical data and current deviation, the estimate is 65%; Impact Assessment: Considering the importance of the user interface, the impact is assessed as 8 (out of 10). Risk level assessment: High risk (probability > 60% and impact level > 7).

[0053] The system will automatically take the following measures: Adjust the project plan and extend the deadline for the user interface development task by 5 working days; This triggered a cross-departmental collaboration mechanism, arranging an emergency meeting between the UI design team and the development team.

[0054] 7. Adaptive display The system automatically adjusts the displayed content based on different users' roles and devices: Project Manager: Displays a comprehensive dashboard on the desktop, including Gantt charts and risk matrices; Development team members: Push updated task lists and progress charts to mobile devices; Executives: Generate an overall project progress report, highlighting risks and solutions.

[0055] Implementation effect By using this system, the project team is able to: 1. Promptly identify and resolve progress issues in the "User Interface Development" task. 2. Accurately assess project risks and take corresponding mitigation measures. 3. Provide personalized project information displays based on the needs of different roles. Ultimately, despite the delays, the project was successfully completed just three days later than originally planned thanks to the system's intelligent early warning and decision support, greatly reducing the potential for even longer delays.

[0056] According to another aspect of this application, a computer-readable storage medium is also provided, on which a computer program is stored. The steps for implementing a project task progress generation method when the program is executed by the processor.

[0057] Storing the project task schedule generation method as a computer program on a computer-readable storage medium allows for its widespread deployment and use. This implementation significantly improves the method's portability and reusability, enabling different project management teams to easily adopt and integrate this advanced schedule management technology. Furthermore, because the method is encapsulated as a computer program, it can respond quickly and run continuously, improving the automation and efficiency of project schedule management.

[0058] According to another aspect of this application, a computer device is also provided, including a memory and a processor, characterized in that, The memory stores a computer program, and when the processor executes the computer program, it implements the steps of a method for generating the schedule of any project task.

[0059] Integrating project task schedule generation methods into dedicated computer equipment provides a complete hardware solution for project management. This integrated design ensures optimal hardware and software matching, fully leveraging algorithm performance and improving the speed of data processing and analysis. The use of dedicated equipment also enhances system security and stability, making it particularly suitable for handling large-scale, complex project management tasks. Furthermore, as a standalone device, it can be more easily integrated into existing project management infrastructure, offering plug-and-play convenience.

[0060] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A project task progress display system, characterized in that, include: The multi-source data acquisition module is used to simultaneously collect real-time progress data of project tasks, team member biorhythm data, and environmental parameter data; The data fusion processing module is used to clean, align, and fuse the collected multi-source heterogeneous data to generate multi-dimensional standardized progress information. The dynamic weighted progress calculation module is used to dynamically adjust the weights of data in each dimension according to the project stage and type, and calculate the comprehensive progress index of the project tasks. The adaptive display module can automatically adjust the displayed content and method according to the user's device, network conditions, and personal preferences; The intelligent prediction module based on graph neural networks is used to build a task dependency graph, analyze historical data and current progress, and predict project completion time, resource bottlenecks and potential risks.

2. The project task progress display system according to claim 1, characterized in that, The data fusion processing module specifically includes: The data cleaning unit is used to handle missing values, outliers, and duplicate data; Time alignment units unify data from different sources and sampling frequencies to the same time scale; The feature extraction unit extracts meaningful features from the raw data; The multimodal fusion unit uses attention mechanisms and transfer learning techniques to fuse data features from different modalities. The data quality assessment unit performs consistency and reliability checks on the merged data and determines, based on preset thresholds, whether to adopt the current merged result or trigger a process of re-collecting or processing a specific data source.

3. The project task progress display system according to claim 1, characterized in that, It also includes a progress exception handling module, which specifically includes: The schedule deviation detection unit is used to compare the actual progress with the planned progress in real time. The deviation classification unit categorizes schedule anomalies into three levels: minor, moderate, and severe, based on the degree of deviation. The cause analysis unit uses data mining and pattern recognition techniques to identify possible causes of schedule anomalies. The response strategy generation unit generates corresponding response strategies based on the anomaly level and cause. in: When a slight deviation is detected, the system automatically adjusts the task priority and sends optimization suggestions to the task execution module; When a moderate deviation is detected, the system triggers a resource reallocation process and sends an alarm message to the decision support system. When a serious deviation is detected, the system automatically suspends the affected tasks, activates the emergency response mechanism, and generates a detailed problem report. If no abnormalities are found within three consecutive detection cycles, the system will appropriately increase the monitoring frequency to optimize system resource utilization.

4. The project task progress display system according to claim 1, characterized in that, The system integrates an intelligent risk assessment module, including: The risk factor identification unit identifies potential risk factors by analyzing historical data and current project characteristics; The risk probability calculation unit uses a Bayesian network model to calculate the probability of each risk occurring. The impact assessment unit evaluates the potential impact of each risk factor on the project schedule. The risk level assessment unit, taking into account both the probability and the degree of impact of the risk, divides the risk into three levels: low, medium, and high. The response recommendation unit recommends corresponding response measures based on the risk level. in: When a low-level risk is identified, the system adds the risk information to the project risk log and focuses on it during the next routine system check. When a medium-level risk is identified, the system immediately pushes the risk information to the risk management subsystem and initiates an automated risk response plan generation program. When a high-level risk is identified, the system automatically adjusts the affected task schedule and triggers a cross-departmental collaboration mechanism to initiate a virtual risk assessment meeting. If an identified risk remains unchanged for three consecutive assessment periods, the system will reassess the relevance of the risk and consider whether to move it from the active monitoring list to the potential risk pool.

5. The project task progress display system and its progress generation method according to claim 1, characterized in that, The adaptive display module includes: The multidimensional data analysis unit is used to process and analyze project progress data from different dimensions; The dynamic weight calculation unit dynamically adjusts the weights of data in each dimension based on project stage, data reliability, and user concerns. An adaptive visualization engine can automatically select the most suitable visualization method based on data characteristics and display requirements; An interactive data exploration interface that allows users to conduct in-depth analysis of specific data through custom queries; Personalized recommendation systems recommend the most relevant data views based on users' historical behavior and preferences; in: The dynamic weight calculation employs a modified analytic hierarchy process (AHP), considering factors including but not limited to: a) Data timeliness weight Wt, which reflects the data update frequency and real-time performance; b) Data reliability weight Wr, based on historical accuracy assessment of the data source; c) Task criticality weight Wc, which reflects the importance of the task to the overall project; d) User attention weight Wu, dynamically adjusted based on user interaction behavior; The formula for calculating the overall weight is: W = α × Wt + β × Wr + γ × Wc + δ × Wu Where α, β, γ, and δ are dynamic adjustment parameters, and α+β+γ+δ=1; The adaptive visualization engine selects from the following visualization methods based on the weighted characteristics of the data: a) When the data shows a clear time trend, prioritize time series plots or Gantt charts; b) When it is necessary to display multidimensional data relationships, use a parallel coordinate graph or a scatter matrix; c) For hierarchical data, use a tree diagram or sunburst diagram; d) When illustrating complex network relationships, use force-directed graphs or Sankey diagrams; The system continuously optimizes weight calculation and visualization selection strategies through machine learning algorithms, specifically including: a) Optimize personalized recommendations using collaborative filtering algorithms; b) Adjust the dynamic weight parameters using reinforcement learning methods; c) Continuously evaluate and improve visualization through A / B testing.

6. A method for generating project task schedules, characterized in that, Includes the following steps: S1. Collect multi-source heterogeneous data, including structured data from traditional project management systems, semi-structured data from team collaboration platforms, unstructured text data related to projects, and environmental and equipment operation data collected by IoT devices; S2. Use multimodal deep learning models to process and fuse various types of data; S3. Construct a dynamic knowledge graph to represent the complex relationships between the elements of the project; S4. Calculate multi-dimensional project progress indicators based on the fused data and knowledge graph; S5. Apply graph neural networks and time series analysis to predict future project progress and potential risks; S6. Based on the degree of deviation between the forecast results and the preset target, determine whether to maintain the current project plan, make fine-tuning and optimization, or initiate a large-scale plan adjustment process; S7. Generate visual reports and interactive dashboards to display project progress.

7. The project task progress generation method according to claim 6, characterized in that, The steps for processing and fusing various types of data using the multimodal deep learning model specifically include: Perform feature engineering and normalization on structured data; Use pre-trained language models to analyze text data and extract key information and sentiment. Apply time series analysis models to process continuous sensor data; Design a multimodal attention mechanism to weightedly fuse information from different sources; Transfer learning techniques are used to adapt models pre-trained on large-scale datasets to specific project scenarios. Based on the historical accuracy of each data source and the characteristics of the current project stage, determine and select the most suitable data fusion strategy.

8. The project task progress generation method according to claim 6, characterized in that, The specific steps for constructing a dynamic knowledge graph include: Define the ontology model to describe the concepts and relationships within the project domain; Extract entities and relationships from multi-source data to populate the knowledge graph; Using graph embedding techniques, knowledge graphs are transformed into low-dimensional vector representations; Apply graph convolutional networks to perform information propagation and aggregation on knowledge graphs; Design a knowledge graph update mechanism to dynamically adjust the knowledge graph structure based on new data and user feedback; Based on the project's progress stage and the criticality of the tasks, determine which subgraphs in the knowledge graph require priority updates and optimization.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the project task progress generation method as described in any one of claims 6-8.

10. A computer device, comprising a memory and a processor, characterized in that, The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the project task schedule generation method as described in any one of claims 6-8.

Images