Comprehensive monitoring and data integration system for intelligent project management

Abstract

The invention provides a comprehensive monitoring and data integration system for intelligent project management, and the system comprises a data collection module which is used for collecting project data from a plurality of data sources in real time; wherein the data source comprises a database, an external API (Application Program Interface) and a sensor; the project data comprises project progress, resource allocation and environment parameters; the data processing module is used for performing project state prediction and risk assessment on the collected project data by using an adaptive time convolution technology and a machine learning algorithm; the visualization module is used for selecting a specific index to generate an instrument panel according to a user demand, displaying the instrument panel to a user according to a specific data display mode, and updating a project state in real time; and the intelligent early warning module is used for monitoring project risks in real time and providing effective management decision support. The system can adapt to the change of time sequence data, the analysis capability of dynamic data is improved, the automation degree is greatly improved, and meanwhile, managers are helped to quickly respond to risks.

Description

Technical Field

[0001] This application belongs to the technical field of project management, and particularly relates to a comprehensive monitoring and data integration system for intelligent project management. Background Art

[0002] With the increasing complexity of project management, traditional project management methods face numerous challenges. Firstly, project data usually comes from multiple different sources, such as internal databases, external services, and on-site sensors, which makes information integration and real-time analysis difficult. In addition, project management often relies on manual data processing, resulting in lagging information processing, low decision-making efficiency, and difficulty in adapting to rapidly changing project requirements. These problems directly affect the success rate of projects and the rational utilization of resources.

[0003] To address these fundamental issues, past solutions mainly focused on improving data management processes and tools. For example, many enterprises adopted centralized databases and basic project management software, attempting to improve efficiency by standardizing data entry and simplifying processes. However, these methods still cannot fully integrate information from different channels and often require a large amount of manual intervention, unable to achieve true real-time monitoring and decision support.

[0004] In recent years, with the rapid development of artificial intelligence and big data technologies, intelligent solutions have gradually been introduced into the field of project management. More and more enterprises have started to adopt data analysis and machine learning technologies to achieve automated data processing and real-time analysis. In addition, the rise of the Internet of Things (IoT) technology has made real-time monitoring and data collection more convenient, and project managers can obtain more comprehensive information. These emerging technologies not only improve the efficiency of data processing but also enhance the accuracy of decision-making, laying the foundation for the realization of intelligent project management. However, despite the emergence of many solutions, there is still a lack of a comprehensive intelligent project management system in the market that can fully integrate and real-time analyze various data. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide a comprehensive monitoring and data integration system for intelligent project management, which uses an adaptive temporal convolutional unit, can adapt to the changes of time series data, improves the analysis ability of dynamic data, generates intelligent decision-making suggestions based on historical and real-time data, greatly improves the degree of automation, and at the same time helps managers quickly respond to risks and optimize resource allocation.

[0006] This application provides a comprehensive monitoring and data integration system for intelligent project management, including:

[0007] A data collection module for real-time collection of project data from multiple data sources; wherein, the data sources include: databases, external APIs, and sensors; the project data includes: project progress, resource allocation, and environmental parameters;

[0008] A data processing module for predicting project status and assessing risks for the collected project data using adaptive time convolution technology and machine learning algorithms;

[0009] A visualization module for generating dashboards by selecting specific metrics according to user requirements, presenting them to users according to specific data display methods, and updating the project status in real time;

[0010] An intelligent early warning module for real-time monitoring of project risks and providing effective management decision support.

[0011] Furthermore, the data collection module includes:

[0012] A database connection unit for docking with multiple databases MySQL, PostgreSQL, and Oracle within the enterprise;

[0013] An API integration unit for integrating external API interfaces to collect project data in real time from project management tools Jira and Asana;

[0014] A sensor data collection unit for collecting project data in real time at the project site through Internet of Things sensors.

[0015] Furthermore, the data processing module includes:

[0016] A data preprocessing unit for preprocessing and standardizing the collected project data and fusing the project data collected from different data sources;

[0017] An adaptive time convolution unit for capturing features of project data by combining convolution operations and the characteristics of time series;

[0018] A machine learning algorithm unit for predicting project status in real time and identifying anomalies in project data based on the captured features of project data.

[0019] Furthermore, the visualization module includes:

[0020] A visualization option unit for providing multiple visualization charts to suit different types of project data; wherein, the visualization charts include: line charts, bar charts, pie charts, and heat maps;

[0021] A custom design unit for extracting specific metrics from project data according to user requirements, configuring corresponding visual charts, and generating dashboards that meet user needs;

[0022] An interaction design unit for providing interactive icons to enhance the user experience; among them, the interactive icons include: data point hover prompt icons, zoom and drag icons, and click icons.

[0023] Furthermore, the visualization module further includes:

[0024] A real-time data acquisition unit for obtaining real-time updated project data from the data processing module and dynamically refreshing the visual charts to ensure that project managers can always grasp the project status;

[0025] A data update unit for sending a project data update request to the data processing module according to the project data update frequency set by the user;

[0026] A status monitoring and warning unit for monitoring the project status based on the real-time obtained project data, and automatically sending a warning signal on the dashboard when an abnormal situation is detected.

[0027] Furthermore, the intelligent warning module includes:

[0028] A key indicator setting unit for setting corresponding thresholds for key indicators related to the project; among them, the key indicators include: project progress, budget consumption, resource utilization rate, task status;

[0029] A real-time monitoring unit for obtaining key indicator data based on the real-time updated project data obtained from the data processing module and detecting whether the key indicator data exceeds the corresponding threshold;

[0030] A warning trigger unit for sending a warning notice containing detailed abnormal information to project managers by means of email, text message, and interface pop-up window when it is detected that the key indicator data exceeds the corresponding threshold; among them, the detailed abnormal information includes: the name of the key indicator, the current key indicator data, and the threshold corresponding to the key indicator.

[0031] Furthermore, the intelligent warning module further includes:

[0032] A risk prediction unit for performing regression analysis and time series analysis based on historical project data to predict the future risk situation of the project;

[0033] Multi-dimensional risk analysis for aggregating and calculating multiple key indicators to evaluate the overall health status of the project and judge the overall risk trend of the project.

[0034] Furthermore, the intelligent early warning module further includes:

[0035] A decision-making generation unit, configured to automatically generate decision-making suggestions according to the early warning situation, future risk situation, and overall risk trend of the project;

[0036] A decision-making optimization unit, configured to optimize the quality of the decision-making suggestions according to the adoption situation of the decision-making suggestions by the project manager.

[0037] The integrated monitoring and data integration system for intelligent project management provided by this application has the following technical effects: (1) By adopting an adaptive temporal convolutional unit, it can adapt to the changes in time series data and improve the analysis ability of dynamic data. (2) Based on microservices and a cloud computing platform, a highly scalable service deployment and fault tolerance mechanism are realized to meet different project requirements. (3) It can monitor the project status in real time, generate intelligent decision-making suggestions based on historical and real-time data, greatly improving the automation level, helping managers quickly respond to risks and optimize resource allocation. Description of the Drawings

[0038] Figure 1 Shows the framework diagram of the integrated monitoring and data integration system for intelligent project management provided by the embodiments of this application. Detailed Embodiments

[0039] To make the objectives, technical solutions, and advantages of this technical solution clearer and more understandable, the following further details this technical solution in conjunction with specific embodiments. It should be understood that these descriptions are exemplary and not intended to limit the scope of this technical solution.

[0040] Please refer to the Figure 1 framework diagram of the integrated monitoring and data integration system for intelligent project management as shown. As Figure 1 shown, the integrated monitoring and data integration system 10 includes:

[0041] A data collection module 11, configured to collect project data in real time from multiple data sources; wherein, the data sources include: databases, external APIs, and sensors; the project data includes: project progress, resource allocation, and environmental parameters;

[0042] A data processing module 12, configured to perform project status prediction and risk assessment on the collected project data by using adaptive temporal convolutional technology and machine learning algorithms;

[0043] A visualization module 13, configured to generate a dashboard according to user needs by selecting specific metrics, display to the user according to specific data display methods, and update the project status in real time;

[0044] The intelligent early warning module 14 is used to monitor project risks in real time and provide effective management decision-making support.

[0045] Specifically, the data collection module 11 includes:

[0046] The database connection unit 111 is used to interface with various databases MySQL, PostgreSQL, and Oracle within the enterprise.

[0047] The database connection unit 111 is specifically used for: (1) Selecting an appropriate database type and configuring the database connection through JDBC (Java Database Connectivity) or ODBC (Open Database Connectivity) interfaces to ensure the stability of the data channel. (2) Configuring the connection parameters of the database, including the database address, port, username, and password, to ensure a secure and reliable connection. (3) Writing SQL query scripts, regularly extracting project-related data from the database, and setting up automated tasks through a scheduling tool (such as cron) to perform data cycle collection at a predetermined time.

[0048] The API integration unit 112 is used to integrate external API interfaces to collect project data in real time from project management tools Jira and Asana.

[0049] The API integration unit 112 is specifically used for: (1) Determining the external API to be integrated, obtaining the API documentation, and configuring the access authentication information according to the documentation, including the API key or Token. (2) Writing a data acquisition program, using a programming language (such as Python or Java) to call the API, receiving real-time data from the external service through an HTTP request, parsing the JSON or XML format data of the API response, and converting it into a format suitable for storage and subsequent processing. (3) Adding an exception handling mechanism to ensure that in case of network request failures, timeouts, etc., it can automatically retry or perform error handling to ensure the stability and reliability of data collection.

[0050] The sensor data collection unit 113 is used to collect project data in real time at the project site through Internet of Things sensors.

[0051] The sensor data acquisition unit 113 is specifically used for: (1) Selecting appropriate sensor types, such as temperature and humidity sensors, and installing them at the project site to monitor data. (2) Configuring the sampling frequency and working parameters of the sensors to ensure the accuracy of data acquisition. (3) Using communication protocols such as MQTT or HTTP to transmit the data collected by the sensors to the data collection module in real time through the network, and performing preliminary sorting and storage processing on the data through a dedicated receiving program. (4) Setting up a timeout and retry mechanism for data transmission to ensure the continuity and integrity of the data in case of network latency or data transmission failures.

[0052] In addition, in order to ensure the integrity and validity of the collected project data, a temporary storage and monitoring mechanism is also equipped, which is specifically used for: (1) Using tools such as Redis or SQLite to build a temporary storage system to store the data collected from different sources for quick access and processing. (2) Cleaning the collected data to remove duplicate or invalid data to ensure the quality of the data for subsequent processing. (3) Monitoring the data collection process in real time, recording logs and tracking the details of each data extraction, API call, and sensor data reception for subsequent auditing and troubleshooting.

[0053] Specifically, the data processing module 12 includes:

[0054] The data preprocessing unit 121 is used to preprocess and standardize the collected project data and fuse the project data collected from different data sources.

[0055] The data preprocessing unit 121 is specifically used for: (1) Data cleaning and standardization: Before entering the ATC unit, all the collected data is first cleaned and standardized through the data preprocessing step. This step ensures that the data from different sources is processed on the same scale, eliminates noise and outliers, and makes subsequent analysis more accurate. (2) Multi-source data fusion: For the project data from different data sources, a multi-channel convolution method is used for fusion. The specific formula is as follows:

[0056]

[0057] In the formula, Xt,i represents the input feature from the i-th data source, and Wt,i is its corresponding convolution kernel weight.

[0058] Through multi-channel fusion, different types of data features can be integrated together to generate more comprehensive project progress and status information. Specifically, Z_t represents the fusion output at time point t, which is usually used to represent the information integration result of multiple data sources for facilitating the comprehensive analysis of the project status. In the formula, X_t,i is the i-th input feature at time point t, covering data from different data sources, such as sensor data, historical project data, and external market data, to ensure that various aspects of information are considered during the fusion process. W_t,i is the convolution kernel weight corresponding to the i-th feature, responsible for weighting the importance of different data sources to ensure that more relevant information plays a greater role during the fusion process. b_t is the bias term, used to adjust the fusion result to make it more in line with the actual situation. Finally, σ is the activation function, usually a non-linear function (such as ReLU or Sigmoid), used to introduce non-linearity to improve the model's expressive ability.

[0059] The adaptive temporal convolutional unit 122 is used to capture features of project data by combining convolutional operations and the characteristics of time series.

[0060] Specifically, the convolutional operation of the adaptive temporal convolutional unit can be expressed by the following formula:

[0061] T t = ReLU(W t * X t + b t )

[0062] In the formula, W_t represents the convolution kernel weight at time point t, X_t is the input feature sequence at time point t, B_t is the bias term, and ReLU is the non-linear activation function.

[0063] This operation can effectively extract local features in time series data. Specifically, the input feature sequence X_t represents the project management data at time point t. This feature sequence contains data such as project progress, resource allocation, and environmental conditions, serving as the basic data input for model analysis. The convolution kernel weight W changes dynamically at each time point and can make adaptive adjustments according to the local features of the time series. This adjustment mechanism allows the model to more accurately identify patterns and changes in the face of project data fluctuations. The bias term b_t is used to introduce non-linear mapping, mapping the input data into the output result space to provide the convolutional layer with stronger fitting ability. Finally, the output is non-linearly processed through the activation function ReLU (Rectified Linear Unit), suppressing the negative values in the convolutional output T_t to obtain the effective features required by the model. The generated output can not only reflect the project status in real time but also identify potential risk changes in advance.

[0064] In addition, the adaptive weight update formula is as follows:

[0065] W t = W t-1 + α·ΔW t

[0066] Where α is the learning rate that controls the update speed, and ΔWt is the weight update amount calculated by the gradient descent method or other optimization algorithms at time point t:

[0067]

[0068] This weight update mechanism ensures that the convolutional kernel can be automatically adjusted according to the characteristics of the time series to adapt to the dynamic changes of time data in project management. Specifically, the convolutional kernel weight Wt-1 at the previous moment provides a historical parameter basis for the current weight update, enabling the model to maintain a certain degree of smoothness when adjusting the current weight Wt. The learning rate α is used to adjust the amplitude of the weight update to ensure an appropriate update rate, which can not only respond to data changes but also avoid system instability caused by overly rapid updates. The weight update amount ΔWt is the value calculated by the gradient descent or other optimization algorithms, reflecting the learning result of the model on data changes at each moment. Such an adaptive update mechanism enables the ATC unit to better adapt to the complex and dynamic environment in the project management process, being able to smoothly handle the diversity of project data and effectively capture trends and anomalies therein, thereby providing efficient and accurate analysis and prediction for the entire project management system.

[0069] The machine learning algorithm unit 123 is used to predict the project status in real time and identify anomalies in the project data according to the captured characteristics of the project data.

[0070] The machine learning algorithm unit 123 is specifically used for: (1) Combining supervised learning and unsupervised learning methods. Supervised learning is used to train the model through the historical data of the project to predict future project progress; unsupervised learning (such as clustering algorithms like K-Means, DBSCAN, etc.) is used to identify abnormal patterns in the data. (2) Efficient prediction and risk warning: In actual project management, based on the features extracted by the ATC unit and combined with machine learning algorithms, the project status can be predicted in real time and project risk warnings can be generated. This function is implemented through the following formula:

[0071]

[0072] Where Yt is the predicted project status and f(.) is the machine learning model function.

[0073] In this way, the system can make accurate predictions based on the real-time data of the project and provide intelligent decision-making suggestions to the managers. Specifically, Yt represents the predicted output at time point t, which is usually used to refer to the key performance indicators (KPIs) of project management, such as schedule prediction, resource utilization prediction, and cost overrun prediction, etc. Xt is the input feature at time point t, including project-related data (such as task completion rate, resource usage, and time progress), ensuring that the model captures all dimensions of the project progress and identifies potential problems. Wt is the convolutional kernel weight at the current time point t, which is responsible for weighting the input features to extract the most important information. The update of the weights enables the model to adapt to the dynamic changes of the project. For example, when the impact of a specific feature (such as resource shortage) on the project success increases, the model will automatically adjust its weights to enhance the accuracy of the prediction. f is the activation function, which may be linear, ReLU, or other non-linear functions, and is responsible for performing non-linear transformation on the convolutional output. Introducing non-linearity enables the model to capture complex feature relationships and improve flexibility and adaptability. In project management, this formula realizes the dynamic prediction of project management-related indicators by combining the analysis of real-time data and historical data, enabling project managers to adjust strategies in a timely manner to cope with the possible changes and challenges in the project, thereby enhancing the success rate and efficiency of the project.

[0074] Specifically, the visualization module 13 includes:

[0075] The visualization option unit 131 is used to provide a variety of visualization charts to suit different types of project data; among them, the visualization charts include: line charts, bar charts, pie charts, and heatmaps.

[0076] The visualization option unit 131 is specifically used to: according to the user's needs, provide a variety of visualization charts suitable for displaying different types of data: Line Chart: used to display continuous data changing over time, such as the daily changes in project progress. The line chart is drawn using libraries such as D3.js or Plotly. Bar Chart: suitable for displaying comparison data of different categories, such as cost analysis of different project phases. Pie Chart: used to display proportion data, such as budget allocation, resource utilization, etc. Heatmap: can be used to display project risk distribution or task execution status, helping users quickly locate key areas. When generating the chart, first extract the required data from the database, perform format conversion, and then transfer it to the chart library function.

[0077] The custom design unit 132 is used to extract specific indicators from the project data according to the user's needs and configure the corresponding visualization charts to generate a dashboard that meets the user's needs.

[0078] The custom design unit 132 is specifically used for: providing a user-defined dashboard function, where users can, according to their personal needs, select the metrics and corresponding charts to be displayed. The specific steps are as follows: Metric selection: Through a drop-down menu or checkboxes, users can select the key performance indicators (KPIs) to be displayed on the dashboard, such as project progress, budget utilization, resource allocation, etc. Chart configuration: Users can select a suitable visualization method (such as a line chart or a pie chart) for each metric. Through a drag-and-drop interface, users can customize the layout of the charts on the dashboard. Saving settings: After the user completes the configuration, the system saves the user's personalized settings to the background database for automatic loading during subsequent accesses.

[0079] The interaction design unit 133 is used to provide interactive icons to enhance the user experience; among them, the interactive icons include: data point hover prompt icons, zoom and drag icons, and click icons.

[0080] The interaction design unit 133 is specifically used for: enhancing the user experience by providing interactive charts; Data point hover prompt: When the user hovers the mouse over a data point or a chart, detailed data information (such as value, time, status, etc.) is displayed. Zoom and drag: Users can zoom the chart view through the mouse wheel or gestures, or adjust the time axis range by dragging to quickly view data within a specific time period. Click event: By clicking on a data point in the chart, the system can further display the detailed information of the data or the associated task situation.

[0081] Specifically, the visualization module 13 further includes:

[0082] The real-time data acquisition unit 134 is used to obtain real-time updated project data from the data processing module 12 and dynamically refresh the visualization charts to ensure that project managers can always keep track of the project status.

[0083] The real-time data acquisition unit 134 is specifically used for: The visualization module supports obtaining real-time updated data from the data processing module and dynamically refreshing the charts to ensure that project managers can always keep track of the project progress. The implementation steps are as follows: Data push: When there is new data update in the background data processing module, the updated data is pushed to the front end using WebSocket or Server-Sent Events (SSE) technology. Front-end reception and refresh: After the front end receives the new data, it automatically calls the refresh function of the chart to update the content in the chart.

[0084] The data update unit 135 is used to send a project data update request to the data processing module according to the project data update frequency set by the user.

[0085] The data update unit 135 is specifically used for: allowing users to customize the data update frequency (such as every 5 seconds, 10 seconds, or manual refresh), which improves flexibility. Users can select an appropriate update frequency in the dashboard settings, and the system will automatically request the latest data from the background according to the set frequency and update the chart.

[0086] The status monitoring and warning unit 136 is used to monitor the project status based on the project data obtained in real time. When an abnormal situation is detected, a warning signal is automatically issued on the dashboard.

[0087] The status monitoring and warning unit 136 is specifically used for: the system will perform status monitoring based on real-time data. When an abnormal situation (such as task delay or over-budget) is detected, a warning signal is automatically issued on the dashboard to remind the user to take measures. The implementation steps are as follows: Status monitoring: Set threshold conditions and continuously detect data. For example, if the project progress is lower than 80% of the predetermined progress, a warning is issued. Warning display: Display a warning icon on the dashboard or prompt the user through color changes (such as highlighting in red). Clicking on the warning can view detailed information.

[0088] Specifically, the intelligent warning module 14 includes:

[0089] The key indicator setting unit 141 is used to set corresponding thresholds for key indicators related to the project; among them, the key indicators include: project progress, budget consumption, resource utilization rate, task status.

[0090] The key indicator setting unit 141 is specifically used for: project managers set key performance indicators (KPIs) and their corresponding thresholds according to project requirements. These indicators include but are not limited to project progress, budget consumption, resource utilization rate, and task completion. The specific steps are as follows: Managers can select the indicators to be monitored in the system and set the corresponding thresholds (such as progress completion lower than 80% or budget exceeding 10%). After the threshold for each indicator is set, the system will regularly check these data. Once it detects that the data exceeds the threshold, an alarm is triggered. For example, the threshold for project progress P is set to 80%. When the current progress P current is detected, if P current < 80%, the system will trigger an alarm.

[0091] The real-time monitoring unit 142 is used to obtain key indicator data based on the project data updated in real time obtained from the data processing module 12 and detect whether the key indicator data exceeds the corresponding threshold.

[0092] The real-time monitoring unit 142 is specifically used for: The system checks whether the current data exceeds a preset threshold by monitoring the data obtained from the data processing module in real time. Once the data exceeds the threshold, the system will automatically trigger an alarm. The specific implementation steps are as follows: Real-time data collection: The system obtains the latest data from the project management database or sensors through timed tasks or real-time data push methods such as WebSocket. Threshold detection: Every time new data is obtained, the system will perform threshold detection to check whether any indicators exceed the preset values.

[0093] The warning trigger unit 143 is used to send a warning notice containing detailed abnormal information to project managers by means of email, text message, or interface pop-up window when it detects that the key indicator data exceeds the corresponding threshold; wherein, the detailed abnormal information includes: the name of the key indicator, the current key indicator data, and the threshold corresponding to the key indicator.

[0094] The warning trigger unit 143 is specifically used for: Warning notice: Once an abnormality is detected, the system sends a warning notice to project managers by email, text message, or interface pop-up window, including detailed abnormal information (such as indicator name, current value, threshold, etc.).

[0095] Specifically, the intelligent warning module 14 further includes:

[0096] The risk prediction unit 144 is used to perform regression analysis and time series analysis based on historical project data to predict the future risk situation of the project.

[0097] The risk prediction unit 144 is specifically used for: The system not only relies on real-time data but also combines historical data for trend analysis and prediction. By performing regression analysis or time series analysis on historical data, it predicts the future risk situation. For example, the ARIMA model is used for time series prediction, and its formula is:

[0098]

[0099] In the formula, y t is the project indicator at the current moment, φ and θ are model parameters, and ∈ t is the error term. By predicting the future indicator value y t , the system can give an early warning of potential risks.

[0100] The multi-dimensional risk analysis unit 145 is used to aggregate and calculate multiple key indicators to evaluate the overall health status of the project to judge the overall risk trend of the project.

[0101] The multi-dimensional risk analysis unit 145 is specifically used for: In addition to the risk monitoring of individual indicators, the system can also comprehensively analyze multi-dimensional data. By aggregating multiple indicators (such as the weighted average of project progress, resource utilization rate, and cost consumption), the overall health status of the project is evaluated. The system can judge the overall risk trend through algorithms such as multiple linear regression or support vector machine (SVM). The formula is as follows:

[0102] Risk score =w1KPI1+w2KPI2+…+w n KPI n

[0103] In the formula, w1, w2, …, w n are the weights of different indicators, and KPI1, KPI2, …, w n KPI n are the values of each key performance indicator.

[0104] Specifically, the intelligent early warning module 14 further includes:

[0105] A decision-making generation unit 146, which is used to automatically generate decision-making suggestions according to the early warning situation, future risk situation, and overall risk trend of the project.

[0106] The decision-making generation unit 146 is specifically used for: Collecting data: The system automatically collects information such as the current project status, historical data, and key indicators in the background. Analyzing data: Using the machine learning algorithm in the data processing module, the system analyzes the current project data and combines it with the project historical data to judge potential risks and bottlenecks. Generating decision-making suggestions: According to the analysis results, the system automatically generates decision-making suggestions. For example, if the system detects that a certain task is delayed, it will suggest modifying the project schedule, adjusting the task priority, or increasing resource investment.

[0107] A decision-making optimization unit 147, which is used to optimize the quality of the decision-making suggestions according to the adoption situation of the decision-making suggestions by the project manager.

[0108] The decision-making optimization unit 147 is specifically used for: Project managers can give feedback on the suggestions given by the system. The system will record the decisions selected by the user and learn their preferences, so as to optimize the quality of subsequent suggestions. For example, when the user adopts a certain suggestion and achieves good results, the system will increase the weight of this decision-making plan and give priority to recommending similar plans in the future.

[0109] The above content is only the preferred embodiment of the present invention. For those of ordinary skill in the art, according to the idea of the present technical content, many changes can be made in the specific implementation manner and application scope. As long as these changes do not deviate from the concept of the present invention, they all belong to the protection scope of the present invention.

Claims

1. A comprehensive monitoring and data integration system for intelligent project management, characterized in that: The system is deployed on a cloud computing platform based on a microservice architecture, and includes: A data collection module is used to collect project data from multiple data sources in real time; wherein the data sources include: databases, external APIs and sensors; the project data includes: project progress, resource allocation and environmental parameters; Data processing module, used to use adaptive time convolution technology and machine learning algorithms to perform project status prediction and risk assessment on the collected project data; The visualization module is used to select specific indicators according to user needs to generate dashboards, display them to users according to specific data display methods, and update project status in real time; Intelligent early warning module, used to monitor project risks in real time and provide effective management decision support.

2. The comprehensive monitoring and data integration system for intelligent project management according to claim 1, characterized in that: The data collection module includes: Database connection unit, used to connect with various databases within the enterprise, such as MySQL, PostgreSQL, and Oracle; API integration unit, used to integrate external API interfaces to collect project data in real time from project management tools such as Jira and Asana; The sensor data acquisition unit is used to collect project data in real time at the project site through IoT sensors.

3. The comprehensive monitoring and data integration system for intelligent project management according to claim 1, characterized in that: The data processing module comprises: A data preprocessing unit, used to preprocess and standardize the collected project data, and to fuse the project data collected from different data sources; Adaptive temporal convolution unit, used to capture the features of project data by combining convolution operation and the characteristics of time series; A machine learning algorithm unit is used to predict project status in real time and identify anomalies in project data based on the characteristics of the captured project data.

4. The comprehensive monitoring and data integration system for intelligent project management according to claim 1, characterized in that: The visualization module comprises: A visualization option unit, used to provide a variety of visualization charts to suit different types of project data; wherein the visualization charts include: line charts, bar charts, pie charts and heat maps; Custom design unit, used to extract specific indicators from project data according to user needs, and configure corresponding visualization charts to generate dashboards that meet user needs; The interactive design unit is used to provide interactive icons to enhance the user experience; wherein the interactive icons include: data point hover prompt icons, zoom and drag icons, and click icons.

5. The comprehensive monitoring and data integration system for intelligent project management according to claim 4, characterized in that: The visualization module also includes: Real-time data acquisition unit, used to obtain real-time updated project data from the data processing module and dynamically refresh the visual chart to ensure that project managers can grasp the project status at any time; A data updating unit, used to send a project data updating request to the data processing module according to the project data updating frequency set by the user; The status monitoring and early warning unit is used to monitor the project status based on the project data obtained in real time. When an abnormal situation is detected, a warning signal is automatically issued on the dashboard.

6. The comprehensive monitoring and data integration system for intelligent project management according to claim 1, characterized in that: The intelligent early warning module comprises: A key indicator setting unit is used to set corresponding thresholds for key indicators related to the project; wherein the key indicators include: project progress, budget consumption, resource utilization, and task status; A real-time monitoring unit, used to obtain key indicator data based on the real-time updated project data obtained from the data processing module, and detect whether the key indicator data exceeds a corresponding threshold; The early warning trigger unit is used to send an early warning notification containing detailed abnormal information to the project management personnel via email, SMS, or interface pop-up window when it detects that the key indicator data exceeds the corresponding threshold; wherein the detailed abnormal information includes: the name of the key indicator, the current key indicator data, and the threshold corresponding to the key indicator.

7. The integrated monitoring and data integration system for intelligent project management according to claim 6, characterized in that: The intelligent early warning module also includes: The risk prediction unit is used to perform regression analysis and time series analysis based on historical project data to predict the future risk of the project; Multi-dimensional risk analysis is used to aggregate and calculate multiple key indicators to conduct an overall project health status assessment to determine the overall risk trend of the project.

8. The comprehensive monitoring and data integration system for intelligent project management according to claim 6, characterized in that: The intelligent early warning module also includes: The decision generation unit is used to automatically generate decision suggestions based on the project's early warning status, future risk status, and overall risk trends; The decision optimization unit is used to optimize the quality of decision suggestions based on the adoption of decision suggestions by project managers.

Images