A method and system for intelligent statistical analysis of production project implementation progress

Abstract

The present invention proposes an intelligent statistical analysis method and system for the implementation progress of a production project. The method includes: initially classifying all task lists in the production project, and constructing a directed acyclic task graph based on the initially classified task lists to represent the dependencies between tasks; collecting data on the execution status of each task according to the initial monitoring granularity of each task, and determining whether the actual progress of each task deviates from the planned progress based on the collected data; collecting behavioral data for each project role, and then calculating the behavioral deviation of each role based on regularization. Based on the behavioral deviation of each role, the collaborative efficiency between the roles is calculated, and then task allocation and progress management are dynamically adjusted; task priorities and resource allocation are re-optimized based on the results of the dynamic adjustment; feedback on the execution of the optimized tasks is provided to the project manager, and intelligent decision support is provided. The present invention has higher intelligence and real-time response capabilities.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent statistics, and in particular relates to an intelligent statistical analysis method and system for production project implementation progress. Background Art

[0002] In modern production project management, project progress statistics and analysis are key components of ensuring on-time completion, optimizing resource utilization, and improving overall production efficiency. Traditional project management methods rely on fixed-granularity task decomposition and static progress monitoring. While these approaches are effective for some simple, linear projects, existing technologies often fall short when faced with complex, multi-task, and cross-departmental production projects.

[0003] First, in large-scale production projects, tasks are often highly dependent and unpredictable. Any delays or resource issues in the task chain will have a chain reaction on the progress of the entire project. However, existing project progress statistics methods are mostly based on pre-set fixed granularity for task monitoring. When the task granularity is too large, it is easy to ignore the delays of key tasks. When the task granularity is too small, it will increase the system burden, resulting in redundant monitoring data and affecting statistical efficiency. Therefore, existing technologies are often unable to dynamically adjust the monitoring granularity according to actual progress changes, resulting in opaque progress of key tasks and project managers unable to promptly identify potential bottlenecks or problems. In addition, the dependencies between tasks often mean that the delay of a task will have a serious impact on other tasks. However, existing technologies lack automated dependency analysis and adjustment mechanisms. Task delays cannot be quickly fed back and the priority of related tasks cannot be adjusted, resulting in lagging project management.

[0004] Secondly, during the execution of a project, production projects usually involve the collaborative work of multiple roles, including project managers, technicians, resource dispatchers, and other personnel with different responsibilities. Although existing project management systems can record the assignment and completion status of each role, these systems can only provide basic task progress data and cannot conduct in-depth analysis of role collaboration efficiency issues. In particular, when certain tasks involve cross-team collaboration, task delays caused by poor communication and unclear role division of labor are difficult to identify in a timely manner in existing systems. Due to the lack of in-depth analysis of role behavior data, existing technologies often rely on the experience of project managers for manual adjustments, making it difficult to provide scientific, data-driven role optimization solutions, which ultimately affects the overall progress of the project.

[0005] Furthermore, current project progress statistics systems are mostly static, relying on manually set time nodes and task relationships. This approach makes it impossible to dynamically adjust task plans in real time. In complex production environments, when task status or execution environments change, project managers need to manually adjust plans and update task priorities and progress targets, consuming significant time and effort and reducing management efficiency. Existing systems are particularly inefficient when faced with large amounts of data input, lacking the responsiveness and processing power to respond promptly to risks that arise during project implementation. This severely limits project execution flexibility and responsiveness.

[0006] In summary, the shortcomings of existing technologies in project progress statistics and analysis are mainly reflected in the following aspects: 1) It is impossible to automatically adjust the monitoring granularity and frequency according to the actual task progress, resulting in delays in key tasks not being discovered in a timely manner; 2) There is a lack of automatic analysis and adjustment mechanism for task dependencies, and the impact of delays cannot be quickly fed back to dependent tasks; 3) In the process of multi-role collaboration, there is a lack of in-depth analysis of role behavior data, resulting in the failure to discover the problem of low collaboration efficiency in a timely manner; 4) The system as a whole lacks dynamic adjustment and automatic optimization functions, and relies on manual adjustment of task plans, which reduces the efficiency and flexibility of project management. Summary of the Invention

[0007] The purpose of the present invention is to propose an intelligent statistical analysis method and system for the implementation progress of production projects, which can effectively solve the problems of inflexible task monitoring, low collaboration efficiency, and manual reliance on progress adjustment in traditional project management methods, and has higher intelligence and real-time response capabilities.

[0008] In order to achieve the above-mentioned object, a first aspect of the present invention provides an intelligent statistical analysis method for production project implementation progress, the method comprising:

[0009] S1. Initially classify all task lists in the production project, and construct a directed acyclic task graph based on the task list after initial classification to represent the dependency relationship between tasks, wherein the dependency relationship is quantified as a dependency matrix. When the dependency matrix = 1, it means that task T i Depends on T j The task can be started only after it is completed. The dependency matrix = 0 means there is no dependency between the two. At the same time, the initial priority and monitoring granularity are set for each task based on the initial classification results and dependency relationships. The dependency weight is calculated based on the dependency relationships to represent the task T. j For Task T i the degree of impact of completion;

[0010] S2. Collect data on the execution status of each task based on the initial monitoring granularity. Based on the collected data, determine whether the actual progress of each task deviates from the planned progress. If a task anomaly occurs, introduce a deviation regularization term λ i To correct the progress deviation calculation of abnormal tasks, and transmit the corrected deviation to downstream tasks through task dependencies;

[0011] S3. Collect behavioral data for each project role, including task response time, task execution time, communication frequency, and progress feedback frequency. Then, based on regularization, calculate the behavioral deviation of each role. Based on the behavioral deviation of each role, calculate the collaborative efficiency between roles, and dynamically adjust task allocation and progress management.

[0012] S4. Re-optimize task priorities and resource allocation based on the results of dynamic adjustments;

[0013] S5. Provide feedback to project managers after executing optimization tasks and provide intelligent decision support.

[0014] Furthermore, the initial classification includes the following categories: critical tasks, common tasks, and auxiliary tasks;

[0015] The structure of the directed acyclic task graph G=(V, E) is as follows:

[0016] The nodes in the graph represent tasks T i , Edge R ij Represents task T i Depends on task T j Completion of, where V is the node of the task set T, E is the dependency relationship R between tasks;

[0017] The initial priority and monitoring granularity are set for each task based on the initial classification results and dependencies, as follows:

[0018] The key task T critical Given the highest initial priority Pr i =1;

[0019] The ordinary task T normal Assign medium priority Pr i =2;

[0020] The auxiliary task T support Assign the lowest priority Pr i =3;

[0021] The dependency weight W ij , which is expressed as follows:

[0022]

[0023] Among them, d i Represents task T i The expected duration of j Represents task T j Resource requirements; i Represents task T i personnel needs.

[0024] Furthermore, in S2, the data collected includes task completion percentage, current time consumption and resource usage.

[0025] The collected data is used to determine whether the actual progress of each task deviates from the planned progress. The specific calculation is as follows:

[0026] First calculate the task T i Plan progress Plan progress It is calculated based on the estimated completion time and resource allocation of the task at the beginning of the project. i and planned progress Compare and get the progress deviation ΔP i,pre , the calculation formula of progress deviation is:

[0027]

[0028] in, Indicates the task T at the current time point i percentage of planned completion; c i Represents task T i The actual completion percentage; if the deviation ΔP i,pre If it is greater than the set threshold ∈, the task is marked as progress abnormal;

[0029] If a task exception occurs, the deviation regularization term λ is introduced i To correct the progress deviation calculation of abnormal tasks, and transmit the corrected deviation to downstream tasks through the task dependency relationship, specifically including:

[0030] Redefine deviation ΔP i The calculation formula is:

[0031]

[0032] Among them, λ i Represents task T i The regularization factor is determined by the task dependency weight W ij The importance of the task determines:

[0033]

[0034] Among them, β j Represents task T j The importance coefficient of

[0035] For task T i Progress deviation ΔP occurs i , which depends on the task T j The progress impact is calculated using the following formula:

[0036]

[0037] in, Represents task T i The progress deviation of task T j degree of impact.

[0038] Furthermore, when a task T i Progress deviation ΔP i If the set threshold ∈ is exceeded, the system will automatically increase the monitoring frequency of the task and adjust its monitoring granularity g i , the specific adjustment rules are as follows:

[0039] If ΔP i >∈, the task T i The monitoring granularity is updated to This means the monitoring frequency is doubled, and twice as much data is obtained;

[0040] If ΔP i Back to normal range, that is, ΔP i ≤∈, then restore the monitoring granularity to the initial state g i .

[0041] Furthermore, the behavioral deviation B role The calculation is as follows:

[0042]

[0043] Among them, t response represents the task response time, reflecting the delay from the time the role is assigned to the start of execution; t exec Indicates the task execution time, which is the total time from the start to the completion of the task; Represents task T i The planned execution time comes from the initial project planning; α and β represent regularization coefficients, reflecting the impact of communication frequency and feedback frequency on efficiency; Indicates the optimal communication frequency value for this task type, derived from historical data or experience. Indicates the optimal feedback frequency of a task, which is used to measure the transparency of feedback on the progress of the task;

[0044] The collaborative efficiency E between the roles role , calculated as follows:

[0045]

[0046] Among them, δ ij Denotes dependency impact deviation, indicating that the role performs task T j Time dependent task T i progress impact.

[0047] Furthermore, the dynamic adjustment of task allocation and progress management is achieved by analyzing the overall impact of collaborative efficiency on dependent tasks, calculated as follows:

[0048]

[0049] in, Indicates role j collaborative efficiency; Represents task T i The progress deviation of its dependent task T j impact.

[0050] Furthermore, the S4 specifically includes:

[0051] A dynamic priority model is designed to dynamically adjust priorities based on task progress, the transmission impact of dependent tasks, and the collaborative efficiency of roles. The dynamic priority model is expressed as follows:

[0052]

[0053] in, Represents task T i The dynamically adjusted priority of i Represents task T i The progress deviation reflects the current execution progress of the task; Represents task T i The planned progress is used to compare with the actual progress; σ and τ are adjustment coefficients, which represent the weight of the progress deviation and the priority adjustment of the dependent tasks respectively; Indicates dependent task T j T i The conduction effect, W ij Represents task T j T i The dependency weight of Indicates the impact of role collaboration efficiency on priority;

[0054] Dynamically adjust resource allocation based on the adjusted priorities, and then automatically generate a new schedule P based on the adjustments to priorities and resources. new; wherein the resource allocation is dynamically adjusted according to the adjusted priority, as shown below:

[0055]

[0056] in, Represents task T i newly allocated resources; Represents task T i The initial resource requirement is based on the initial planning of the task; δ represents the resource allocation weight coefficient, which is used to adjust resource allocation according to priority; The sum of the new priorities of all tasks, used to normalize resource allocation ratios.

[0057] Furthermore, the S4 further includes:

[0058] After generating new priorities, resource allocation plans, and schedules, these adjustments are fed back to the project manager, who can view the adjustment details through a visual interface, including:

[0059] Generate critical task reminders based on the highest priority tasks, prompting managers to focus on these tasks;

[0060] Provide optimization suggestions for resource allocation to help managers reasonably allocate limited resources and ensure that key tasks in the project receive adequate support;

[0061] If the dependencies of certain tasks have a significant impact on the project progress, first adjust the task dependency order or optimize the resource allocation plan.

[0062] Furthermore, the S5 specifically includes:

[0063] Generate feedback reports through an intuitive visual interface, including changes in task priorities, resource allocation adjustments, and new schedules;

[0064] Automatically mark tasks with changed priorities and tasks that may have problems, specifically:

[0065] If task T i Priority If the progress of a task exceeds the set threshold, it will be marked as a "critical task" to remind managers to pay priority attention; if the progress deviation of a task is ΔP i or dependent influence If the set threshold is exceeded, the task will be marked as a "risk task", prompting the manager to intervene in the task;

[0066] Automatically generate optimization suggestions based on feedback data, including:

[0067] If the collaborative efficiency of the execution roles of a task is lower than the set threshold, it will be recommended to assign part or all of the current task to other efficient roles to reduce the risk of task delays caused by coordination issues;

[0068] If there are insufficient resources for certain high-priority tasks, managers are advised to reallocate resources from lower-priority tasks to ensure the successful completion of critical tasks;

[0069] Specifically, resource adjustment suggestions are generated using the following formula:

[0070]

[0071] in, Indicates the resource adjustment amount recommended by the system; Represents task T i Dynamically adjusted resource requirements; Represents task T i Current resource allocation.

[0072] Another aspect of the present invention provides an intelligent statistical analysis system for production project implementation progress, the system comprising:

[0073] The project initialization module is used to initially classify all task lists in the production project and construct a directed acyclic task graph based on the task list after initial classification to represent the dependency relationship between tasks. The dependency relationship is quantified as a dependency matrix. When the dependency matrix = 1, it means that task T i Depends on T j The task can be started only after it is completed. The dependency matrix = 0 means there is no dependency between the two. At the same time, the initial priority and monitoring granularity are set for each task based on the initial classification results and dependency relationships. The dependency weight is calculated based on the dependency relationships to represent the task T. j For Task T i the degree of impact of completion;

[0074] The project correction module is used to collect data on the execution status of each task according to the initial monitoring granularity of each task, and judge whether the actual progress of each task deviates from the planned progress based on the collected data. If a task anomaly occurs, the deviation regularization term λ is introduced. i To correct the progress deviation calculation of abnormal tasks, and transmit the corrected deviation to downstream tasks through task dependencies;

[0075] The task allocation module collects behavioral data for each project role, including task response time, task execution time, communication frequency, and progress feedback frequency. It then calculates the behavioral deviation of each role based on regularization, and calculates the collaborative efficiency between roles based on each role's behavioral deviation, thereby dynamically adjusting task allocation and progress management.

[0076] Allocation optimization module, used to re-optimize task priorities and resource allocation based on the results of dynamic adjustments;

[0077] The project optimization module is used to provide feedback to project managers after executing optimization tasks and provide intelligent decision support.

[0078] The beneficial technical effects of the present invention are at least as follows:

[0079] (1) The first innovation of the present invention is that it can automatically adjust the granularity and frequency of task monitoring according to the actual execution status of the task progress. When the system detects a deviation in the execution of a task, especially a delay in a key task of the project, the system will automatically increase the monitoring frequency of the task and increase the precision of data collection, so as to timely capture the progress problems of the key tasks. This mechanism can dynamically respond to changes in tasks in the project, avoid delays in key tasks being ignored, and reduce excessive monitoring of non-critical tasks through adaptive adjustments. In addition, the system can also automatically analyze the dependencies of tasks, and when a progress deviation occurs in a key task, automatically adjust the priority of related dependent tasks to ensure that the overall progress of the project is not affected by the chain reaction of a single task delay. Through the adaptive adjustment of task granularity and the intelligent feedback mechanism of dependent tasks, the present invention effectively solves the shortcomings of the existing system in responding to task progress issues in a timely manner and making inflexible adjustments.

[0080] (2) The second innovation of the present invention is to achieve dynamic monitoring and optimization of collaborative efficiency through in-depth analysis of the behavioral data of each role involved in the project. The system can collect the operational behavior data of each role in project management (such as task allocation, task completion time, communication frequency, etc.) in real time, and judge whether the collaborative efficiency meets expectations through data analysis models. When the system identifies that certain roles have efficiency problems in collaborative tasks (such as unreasonable task allocation, delays caused by insufficient communication, etc.), it will automatically generate collaborative optimization suggestions to help the project team improve work efficiency and reduce collaborative bottlenecks in project progress. Through this mechanism, the system can quickly and accurately discover collaborative problems and provide optimization solutions, solving the defects of low efficiency of multi-role collaboration and difficulty in timely discovery and adjustment of problems in existing project management systems.

[0081] (3) The present invention also has the ability to dynamically adjust the schedule in real time. The system automatically generates schedule adjustment suggestions based on the results of adaptive granularity adjustment of tasks and role behavior analysis, and provides feedback to project managers. Through this feedback mechanism, the system can not only make intelligent optimization suggestions for progress issues of tasks and roles, but also automatically perform some adjustments, reducing the need for manager intervention and improving management efficiency. This function effectively solves the drawbacks of traditional systems that rely on manual adjustments, making the management of production projects more automated and intelligent.

[0082] (4) The present invention constructs an intelligent production project progress management system through three major innovations: adaptive task granularity adjustment, multi-role collaborative efficiency analysis, and dynamic progress adjustment and feedback. It solves the problems of inflexible progress monitoring, low collaborative efficiency, and manual adjustment in the existing technology, and can significantly improve the execution efficiency and progress accuracy of production projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative effort.

[0084] Figure 1 This is a flow chart of an intelligent statistical analysis method for the implementation progress of a production project according to the present invention.

[0085] Figure 2 This is a framework diagram of an intelligent statistical analysis system for the implementation progress of a production project according to the present invention. DETAILED DESCRIPTION

[0086] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0087] like Figure 1 As shown, an embodiment of the present invention provides an intelligent statistical analysis method for production project implementation progress, the method comprising the following steps S1-S5:

[0088] S1. Initially classify all task lists in the production project, and construct a directed acyclic task graph based on the task list after initial classification to represent the dependency relationship between tasks, wherein the dependency relationship is quantified as a dependency matrix. When the dependency matrix = 1, it means that task T i Depends on T j The task can be started only after it is completed. The dependency matrix = 0 means there is no dependency between the two. At the same time, the initial priority and monitoring granularity are set for each task based on the initial classification results and dependency relationships. The dependency weight is calculated based on the dependency relationships to represent the task T. j For Task T i The degree of impact of completion.

[0089] Specifically, the input data is the list of all tasks in the project T = {T1, T2, ..., T n}, each task T iContains basic attributes such as task name, task time, resource requirements, etc. These input data are the basic data for the project in the planning stage.

[0090] Task attributes: Task T i The properties include: expected duration d i , resource requirements r i , the number of people p i , and the initial state S of the task i (e.g. not started, in progress, completed).

[0091] Task classification: This invention classifies tasks into three categories:

[0092] Critical Tasks critical : If a task is delayed and will affect the overall project progress, mark it as a critical task.

[0093] Normal Tasks normal :This type of task has a relatively flexible time window.

[0094] Auxiliary Tasks support : It will only affect the progress of the main task under special conditions.

[0095] Build task dependency graph

[0096] The core of this step is to establish the dependency relationship of tasks. The present invention uses a directed acyclic graph (DAG) to represent the dependency relationship of tasks. The nodes in the graph represent the task T. i , Edge R ij Represents task T i Depends on task T j The entire dependency graph can be expressed as G = (V, E), where V is the node of the task set T and E is the dependency relationship R between tasks.

[0097] Furthermore, we define a dependency matrix R, where R ij =1 indicates task T i Depends on T j Complete to start, R ij =0 means there is no dependency between the two.

[0098] During project planning, these dependencies will be extracted from the project management tool. For example, Task T2 may require Task T1 to be completed before it can start. 21 = 1. This can be automatically generated based on the attribute data of the task, avoiding errors in manual definition.

[0099]

[0100] Among them, R13 =1 indicates that task T1 depends on T3 to be completed. 21 =1 indicates that task T2 depends on T1 to be completed.

[0101] By constructing this dependency graph G, the present invention can clearly represent the dependency relationships between all tasks in the project, and ensure that the dependency relationships are free of cycles through DAG, so that subsequent task scheduling can be effectively executed.

[0102] Furthermore, based on the classification and dependency of tasks, the present invention needs to set an initial priority Pr for each task. i and monitoring granularity g i .

[0103] Priority definition:

[0104] Critical Tasks critical Given a higher initial priority Pr i =1.

[0105] Normal Tasks normal Assign medium priority Pr i =2.

[0106] Auxiliary Tasks support Assign the lowest priority Pr i =3.

[0107] The initial priority value will be dynamically adjusted in subsequent steps.

[0108] Furthermore, the monitoring granularity of each task g i Is the frequency of task progress monitoring, which is defined based on the importance of the task and project requirements. For critical tasks, T critical The present invention sets an initial higher monitoring granularity g i =1 (indicates high-frequency monitoring), while for normal tasks and auxiliary tasks it is set to g i =2 or g i =3, indicating low-frequency monitoring.

[0109] Furthermore, in addition to the dependency matrix R, the dependency weight W also needs to be calculated ij , indicating task T j For Task T i The degree of impact on completion. The dependency weight is calculated based on multiple factors such as task completion time, resource conflicts, etc. The formula is as follows:

[0110]

[0111] Among them, d i Represents task T i The expected duration of thej Represents task T j Resource requirements. i Represents task T i Personnel demand. Dependency weight W ij Reflects task T j Complete the task T i The larger the value, the stronger the dependency. In subsequent task scheduling and adjustment, tasks with higher weights will be given priority in resource allocation.

[0112] S2. Collect data on the execution status of each task based on the initial monitoring granularity. Based on the collected data, determine whether the actual progress of each task deviates from the planned progress. If a task anomaly occurs, introduce a deviation regularization term λ i To correct the progress deviation calculation of abnormal tasks, and at the same time transmit the corrected deviation to downstream tasks through the task dependency relationship.

[0113] Specifically, based on the monitoring granularity g set for each task in step 1 i Collect data on the execution status of the task. The progress of the task P i Includes the following important information:

[0114] Task completion percentagec i : The percentage of the current task completed (for example, 60% means the task is 60% completed).

[0115] Current time t i : The elapsed time of the task since it started.

[0116] Resource usage The amount of resources used by the task (such as man-hours, equipment operating time, etc.).

[0117] The frequency of real-time data collection is determined by the monitoring granularity of the task g i Control, high priority tasks (such as critical tasks T critical ) monitoring granularity g i The frequency of data collection for common and auxiliary tasks is relatively low. Data can be obtained through Internet of Things (IoT) devices, automated systems, and manual input by humans.

[0118] Furthermore, in order to determine whether the actual progress of each task deviates from the planned progress, the present invention first calculates the task T i Plan progress Plan progress It is calculated based on the estimated completion time and resource allocation of the task at the beginning of the project. i and planned progress Compare and get the progress deviation ΔP i The calculation formula of the progress deviation defined in the present invention is:

[0119]

[0120] in, Indicates the task T at the current time point i The percentage of planned completion. i Represents task T i The actual percentage complete.

[0121] This formula gives the task T i The percentage deviation from the planned schedule. If the deviation ΔP i If the progress is greater than a certain set threshold ∈ (for example, ∈=10%), the system marks the task as "progress abnormality".

[0122] Furthermore, in order to better capture the abnormal points of project progress, the present invention introduces an innovative deviation regularization term λ i To correct the task progress deviation calculation to make it more robust. This regularization term can be set based on the specific complexity of the project and the dependencies of the tasks, reflecting the particularity of certain tasks (such as tight task resources or high task complexity). The present invention redefines the deviation calculation formula as:

[0123]

[0124] Among them, λ i Represents task T i The regularization factor is determined by the task dependency weight W ij The importance of the task determines:

[0125]

[0126] Among them, W ij Represents task T j For Task T i The dependency weights of β (from the dependency weight matrix in step 1). j Represents task T j The importance coefficient of the task (determined by task priority and task complexity).

[0127] Regularization term λ i The introduction of makes deviation detection no longer just a simple comparison of task completion percentages, but also combines task dependency weights and importance to more sensitively identify task deviations in projects that may cause chain reactions.

[0128] Furthermore, the deviation not only affects the current task, but also transmits to the downstream tasks through the task dependencies. Based on the dependency matrix R and dependency weight W in step 1 ij , the present invention can infer the impact of the progress deviation of the upstream task on the downstream task. i Progress deviation ΔP occurs i , which depends on the task T j The progress impact can be calculated by the following formula:

[0129]

[0130] in, Represents task T i The progress deviation of task T j The degree of influence. ij represents the dependency weight from step 1. If the upstream task T i If the deviation is large, the system will automatically adjust the schedule of the downstream tasks related to it to ensure that the downstream tasks can adjust their execution progress in time according to the progress of the upstream tasks.

[0131] Furthermore, when a task T i Progress deviation ΔP i If the set threshold ∈ is exceeded, the system will automatically increase the monitoring frequency of the task and adjust its monitoring granularity g i The specific adjustment rules are as follows:

[0132] If ΔP i >∈, the task T i The monitoring granularity is updated to This means that the monitoring frequency is doubled to obtain more accurate data.

[0133] If ΔP i Return to normal range (i.e. ΔP i ≤∈), then restore the monitoring granularity to the initial state g i .

[0134] Dynamically adjust the monitoring granularity to ensure that the system can more accurately monitor tasks with abnormal progress, especially critical tasks. critical , so that the system can respond in a timely manner if the abnormal situation persists.

[0135] This step provides a more sophisticated and intelligent processing mechanism for project task progress detection by introducing a regularized deviation term and a progress impact analysis based on dependency weights. The present invention combines the dependencies between tasks, the complexity of the tasks themselves, resource usage, and other factors to ensure that progress deviations can not only be detected in real time, but also automatically transmitted to related dependent tasks when deviations occur, and the monitoring frequency can be adjusted in a timely manner. In this way, the deviation detection of the present invention is not only more accurate, but also can prevent potential chain reaction problems in the project in advance.

[0136] S3. Collect behavioral data for each project role, including task response time, task execution time, communication frequency, and progress feedback frequency. Then, calculate the behavioral deviation of each role based on regularization. Calculate the collaborative efficiency between roles based on the behavioral deviation of each role, and dynamically adjust task allocation and progress management.

[0137] Specifically, based on the output in step 2 (task progress deviation ΔP i , the monitoring granularity after regularization and the progress impact of dependent tasks ), the present invention collects behavioral data of each project role (such as project manager, executive, resource coordinator, etc.), specifically including the following key indicators:

[0138] Task response time t response : The time when the role starts to perform the task after receiving the task and the task assignment time t assign difference.

[0139] Task execution time t exec : Start from the task start To complete complete The total time taken and the task planning time comparison.

[0140] Communication frequency f comm :The number of times a role communicates with other roles during task execution, which is counted by the message records in the project management system.

[0141] Progress feedback frequency f feedback : The frequency of the role's feedback on task progress (such as the number of times progress is reported each day) reflects the transparency of the role's task execution.

[0142] The collection of these behavioral data can be carried out in real time through system automation tools, manual input by personnel, project management platform integration, etc.

[0143] Furthermore, in order to ensure that the behavioral data can accurately reflect the collaborative efficiency of the roles, the present invention introduces innovative regularization processing to the above-mentioned behavioral data to avoid deviations caused by the particularity of individual tasks (such as urgent tasks or resource shortages).

[0144] The present invention first calculates the behavior deviation B of each character role , combined with the actual execution of its tasks and the response time deviation. The formula for behavioral deviation is as follows:

[0145]

[0146] Among them, t response Indicates the task response time, reflecting the delay from the time the role is assigned to the start of execution. exec Indicates the task execution time, which is the total duration from the start to the completion of the task. Represents task T i The planned execution time is derived from the initial project plan. α and β represent regularization coefficients, reflecting the impact of communication and feedback frequency on efficiency. The system automatically adjusts these coefficients based on historical data. Indicates the optimal communication frequency value for this task type, derived from historical data or experience. Indicates the optimal feedback frequency of the task, which is used to measure the transparency of the feedback of the role in the progress of the task. Regularization ensures that the behavioral deviation B role It can accurately reflect the character's performance in the task without being distorted by special task conditions.

[0147] Furthermore, based on the regularized behavior data, the present invention defines the role's collaborative efficiency E role , its core goal is to measure the overall efficiency of the role in the task execution process. The innovation lies in that the present invention combines behavioral deviation B role and task dependency weights, a more targeted efficiency calculation formula is constructed:

[0148]

[0149] Among them, B role Indicates behavioral deviation, reflecting the difference between the role's task execution and the ideal state. ij Represents task T j For Task T i The dependency weights of , come from the dependency matrix in step 1. ij It represents the task dependency impact deviation, and it represents the role execution task T j Time dependent task T i The progress impact comes from the dependency analysis in step 2.

[0150] In the formula, E roleThis approach not only considers deviations in individual roles' behaviors (such as response time and execution time), but also incorporates dependencies between tasks. If a role performs inefficiently in a task, this impacts the execution of other tasks through the weight of the dependencies. This innovative calculation method ensures that collaborative efficiency calculations reflect not only individual behaviors but also the overall state of collaboration in the project.

[0151] Furthermore, by calculating the role collaboration efficiency, the present invention further analyzes the impact of collaboration efficiency on the entire task network. Due to the close dependencies between tasks, inefficient behavior of a role will affect multiple tasks through the dependency chain. Therefore, the present invention analyzes the overall impact of collaboration efficiency on dependent tasks using the following formula:

[0152]

[0153] Where ΔP i Represents task T i The progress deviation comes from the progress deviation detection in step 2. Indicates role j collaborative efficiency. Represents task T i The progress deviation of its dependent task T j impact.

[0154] This formula reflects the transmission effect of role inefficiency on the progress deviation of dependent tasks. By quantitatively analyzing this effect, the system can predict in advance the overall project delays that may be caused by role coordination problems.

[0155] Furthermore, according to the calculated synergy efficiency E role Impact analysis of dependent tasks The system automatically generates optimization suggestions for task allocation. Specific optimization measures include:

[0156] Task redistribution: If the collaborative efficiency of a role is lower than the set threshold (e.g. E role <0.75), the system will suggest reallocating some tasks to roles with higher collaborative efficiency to reduce the risk of project delays.

[0157] Feedback and communication optimization: By analyzing the feedback and communication frequencies in the character's behavior data, the system can identify the character's poor communication habits during tasks (such as over-communication or insufficient feedback) and provide optimization suggestions, such as reducing unnecessary communication frequency or increasing feedback frequency.

[0158] Dependent task priority adjustment: Based on role collaboration efficiency and dependent task deviation, the system can recommend adjusting the priority of dependent tasks to prioritize tasks that may cause larger delays.

[0159] For example, if a role is in a key task T critical Poor performance on role <0.75), the system can automatically prompt the project manager to assign some key tasks to other more efficient roles to avoid overall project delays due to efficiency issues of a single role.

[0160] The role collaboration efficiency analysis in this step is directly based on the output data of the first two steps, including task progress deviation, monitoring granularity, dependency, etc. Through refined data collection and innovative collaboration efficiency calculation model, the role behavior data in the project is closely integrated with the task execution performance. role The introduction of ensures that the system can dynamically and in real time analyze the performance of roles in complex project tasks and predict the impact of dependent tasks that may be brought about by inefficient roles.

[0161] S4. Re-optimize task priorities and resource allocation based on the results of dynamic adjustments.

[0162] Specifically, the input data includes the multi-role collaborative efficiency E in step 3 role , task-dependent bias And the task progress deviation ΔP in step 2 i These data are key to dynamic task adjustments and can reflect the current progress of tasks and the impact of dependencies on the overall project.

[0163] Task progress deviation ΔP i :Task T i The actual progress deviation reflects the degree of deviation in task execution.

[0164] Collaborative efficiency E role :The performance of the role in task execution, measuring its execution efficiency.

[0165] Dependent task impact The deviation of the dependent task to the current task T i The influence of ,represents the conduction effect in the task dependency chain.

[0166] The solution in step 4 will use this data to further optimize task priorities and resource allocation in real time.

[0167] Furthermore, the priority of tasks needs to be dynamically adjusted based on progress deviation, dependencies, and collaborative efficiency. The adjustment of priority depends not only on the progress of the task itself, but also on the status of its dependent tasks and the collaborative efficiency of the roles. This invention introduces an innovative dynamic priority model that not only considers the progress of the task, but also combines the transmission effect of dependent tasks and the collaborative efficiency of the roles. The calculation formula of dynamic priority is:

[0168]

[0169] in, Represents task T i The dynamically adjusted priority of i Represents task T i The progress deviation reflects the current execution progress of the task; Represents task T i The planned progress is used to compare with the actual progress; σ and τ are adjustment coefficients, which represent the weight of the progress deviation and the priority adjustment of the dependent tasks respectively; Indicates dependent task T j T i The conduction effect, W ij Represents task T j T i The dependency weight of Indicates the impact of role collaboration efficiency on priority.

[0170] This prioritization model optimizes tasks based on three key factors: task progress deviation, the impact of dependent tasks, and role collaboration efficiency. Tasks with large progress deviations receive a significant priority increase; similarly, if the upstream tasks they depend on have large deviations, their priority also increases. Furthermore, if the role collaboration efficiency of the task is low, the task's priority is also increased accordingly, ensuring that project delays are not caused by role efficiency issues.

[0171] Furthermore, after task priorities are adjusted, resource allocation also needs to be dynamically adjusted based on the priorities. The goal of resource adjustment is to prioritize the smooth execution of high-priority tasks and ensure that tasks can proceed as planned, especially for critical tasks. The innovative resource allocation model is as follows:

[0172]

[0173] in, Represents task T i Newly allocated resources (such as manpower, equipment, etc.). Represents task T i The initial resource requirements are based on the initial planning of the task. δ represents the resource allocation weight coefficient, which is used to adjust resource allocation according to priority. This represents the sum of the new priorities of all tasks and is used to normalize resource allocation. This model ensures that resources are allocated preferentially to higher-priority tasks. Especially when resources are limited, the system prioritizes critical tasks or those with significant schedule deviations by allocating more resources, ensuring these tasks can return to schedule quickly and avoid overall project delays.

[0174] Furthermore, based on the adjustment of priorities and resources, the system will automatically generate a new schedule P new , the adjustment of the schedule will rearrange the execution order and time of tasks according to their priorities. The specific adjustment process is as follows:

[0175] Task prioritization: Based on the new priorities The system reorders tasks to ensure that higher priority tasks are executed first.

[0176] Adjustment of task start and completion times: For tasks with higher priorities, the system will appropriately adjust their start and end times to ensure that resources and time can meet their execution requirements.

[0177] Dependency adjustment: If there is a large deviation between the dependent tasks of a task, the system will adjust the dependency weight W. ij Adjust the start time of related tasks so that downstream tasks can be adjusted in time according to the progress of upstream tasks.

[0178] The newly generated schedule P new It can reflect the priority and dependencies of current tasks in real time to ensure the optimal execution sequence and resource allocation of projects.

[0179] Furthermore, after generating new priorities, resource allocation plans, and schedules, the system will feed back these adjustment results to the project manager, who can view the adjustment details through a visual interface. The system also provides further management decision support, including:

[0180] Critical task reminders: For tasks with significantly increased priority, the system will generate critical task reminders to prompt managers to pay special attention to these tasks.

[0181] Resource allocation suggestions: The system provides optimization suggestions for resource allocation to help managers reasonably allocate limited resources and ensure that key tasks in the project can receive adequate support.

[0182] Dependency adjustment suggestions: If the dependencies of certain tasks have a significant impact on the project progress, the system will suggest adjusting the task dependency order or optimizing the resource allocation plan.

[0183] Managers can choose to automatically execute system recommendations or manually adjust task assignments and priorities to better adapt to real-time changes in the project.

[0184] This step utilizes an innovative dynamic prioritization model and resource allocation mechanism to ensure that projects can adapt to real-time task status, particularly when addressing schedule deviations, the impact of dependent tasks, and collaborative efficiency issues. Compared to traditional static project management models, this solution significantly enhances the dynamic responsiveness of project management by introducing multiple innovative factors (such as role collaboration efficiency and dependent task impact).

[0185] S5. Provide feedback to project managers after executing optimization tasks and provide intelligent decision support.

[0186] Specifically, the input data includes the output in step 4: the updated task priority Resource allocation plan and dynamically adjusted project schedule P new These data reflect the system's real-time adjustments to the tasks in the project, and managers can fully understand the current execution status of the tasks when receiving feedback.

[0187] Task Priority Task T i The latest priority is dynamically adjusted based on progress deviation, dependent task impact and collaborative efficiency.

[0188] Resource Allocation The amount of resources the system allocates to each task after adjusting the priority.

[0189] Project Schedule P new : The optimized overall project schedule combines adjustments to task priorities and dependencies.

[0190] These data will be used to generate feedback reports and provide managers with further decision support.

[0191] Furthermore, managers can clearly understand the system's adjustments to the project through an intuitive visual interface, including changes in task priorities, resource allocation adjustments, and new schedule plans.

[0192] Furthermore, the system will graphically display the changes in task priority (e.g., the task priority changes from Upgrade to ) and compare the progress deviation ΔP i , Dependence Impact and collaborative efficiency E role .

[0193] Furthermore, the system generates a pie chart or bar chart of resource allocation to show the resource reallocation and indicate the degree to which resources are tilted towards high-priority tasks.

[0194] Furthermore, the new progress plan P is displayed through Gantt chart or task progress chart.new , the task’s start time, completion time and dependencies.

[0195] Feedback reports not only display the real-time status of current tasks, but also intuitively present to managers the reasons for adjustments to task priorities and resource allocation, enabling them to better understand project adjustments.

[0196] Furthermore, to help managers more effectively focus on key tasks and tasks with potential risks in the project, the system automatically marks tasks with significant priority changes and tasks that may have problems:

[0197] Key task mark: If task T i Priority The improvement exceeds the set threshold (such as The system marks it as a "critical task" to remind managers to give it priority attention.

[0198] Risk Task Mark: If the progress deviation of a task is ΔP i or dependent influence If the set threshold is exceeded, the system will mark the task as a "risky task" and prompt the manager to intervene in the task.

[0199] For example, if the priority of task T5 is changed from Upgrade to If the progress deviation ΔP5 is large, the system will mark it as a critical task and send a reminder.

[0200] Furthermore, the system automatically generates optimization suggestions based on feedback data to help managers make more reasonable decisions. Optimization suggestions provide refined adjustment plans by combining data on task priorities, resource allocation, and collaborative efficiency, mainly including the following aspects:

[0201] Task reallocation suggestion: If a task T i The execution role collaborative efficiency E role Below the set threshold (e.g. E role <0.75), the system will recommend that the task T i Assign part or all of the tasks to other efficient roles to reduce the risk of task delays due to coordination issues.

[0202] Resource Adjustment Suggestions: If resources for certain high-priority tasks are insufficient, the system will suggest managers reallocate resources from lower-priority tasks to ensure the successful completion of critical tasks. The system generates resource adjustment suggestions using the following formula:

[0203]

[0204] in, Indicates the resource adjustment amount recommended by the system. Represents task T i Dynamically adjusted resource requirements. Represents task T i Current resource allocation.

[0205] Progress remedial plan: If the progress deviation of a task is large, the system will suggest remedial plans to speed up the progress, such as adding more people, extending working hours, or adjusting the order of tasks to ensure that the task is completed on time. i Can be completed on schedule.

[0206] Through this decision support mechanism, the system enables managers to make decisions on resource allocation and task adjustment based on actual conditions.

[0207] Furthermore, although the system will provide automatic optimization suggestions based on task status, managers can also manually adjust task priorities, resource allocation, and schedule plans through a visual interface.

[0208] Manually adjust the priority: Managers can manually adjust the priority of certain tasks according to the actual needs of the project. i For example, if there are external requirements changes in the project, some tasks may need to be executed earlier, and managers can manually increase the priority of these tasks.

[0209] Manually adjust resource allocation: Managers can also adjust resource allocation through the interface based on the actual project situation to ensure that resources are reasonably allocated to key tasks.

[0210] Schedule modification: If the manager finds that the system's schedule needs to be optimized, the system provides a manual modification schedule P new With this function, managers can adjust the start time, completion time and dependencies of tasks according to actual conditions.

[0211] The system also has adaptive learning capabilities, that is, after each manual adjustment, the system will record the manager's adjustment behavior and incorporate it into historical data to optimize the next decision-making model, making feedback and suggestions more intelligent.

[0212] Step 5 helps managers make effective decisions by automatically generating feedback reports, marking critical and risky tasks, and providing optimization suggestions. The core innovation of this step lies in its real-time data-based feedback and intelligent decision support, ensuring managers can accurately monitor project status and make timely adjustments.

[0213] By introducing adaptive feedback and manual adjustment support, the system can not only automatically generate decision recommendations, but also allow managers to manually optimize based on actual conditions, making the system more flexible and intelligent.

[0214] like Figure 2 As shown, another embodiment of the present invention provides an intelligent statistical analysis system for production project implementation progress, the system comprising:

[0215] The project initialization module 301 is used to initially classify all task lists in the production project and construct a directed acyclic task graph based on the task lists after initial classification to represent the dependency relationship between tasks, wherein the dependency relationship is quantified as a dependency matrix. When the dependency matrix = 1, it means that task T i Depends on T j The task can be started only after it is completed. The dependency matrix = 0 means there is no dependency between the two. At the same time, the initial priority and monitoring granularity are set for each task based on the initial classification results and dependency relationships. The dependency weight is calculated based on the dependency relationships to represent the task T. j For Task T i the degree of impact of completion;

[0216] The project correction module 302 is used to collect data on the execution status of each task according to the initial monitoring granularity of each task, and judge whether the actual progress of each task deviates from the planned progress based on the collected data. If a task abnormality occurs, the deviation regularization term λ is introduced. i To correct the progress deviation calculation of abnormal tasks, and transmit the corrected deviation to downstream tasks through task dependencies;

[0217] The task allocation module 303 is used to collect behavioral data of each project role, including task response time, task execution time, communication frequency, and progress feedback frequency. The module then calculates the behavioral deviation of each role based on regularization, and calculates the collaborative efficiency between roles based on the behavioral deviation of each role, thereby dynamically adjusting task allocation and progress management.

[0218] Allocation optimization module 304, used to re-optimize task priorities and resource allocation based on the results of dynamic adjustment;

[0219] The project optimization module 305 is used to provide feedback to the project manager after executing the optimization task and provide intelligent decision support.

[0220] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.

[0221] In addition, for technical details not fully described in this embodiment, please refer to the parameter operation method provided in any embodiment of the present invention, and will not be repeated here.

[0222] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0223] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0224] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0225] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent statistical analysis method for production project implementation progress, characterized in that: The method comprises: S1. Initially classify all task lists in the production project, and construct a directed acyclic task graph based on the task list after initial classification to represent the dependency relationship between tasks, wherein the dependency relationship is quantified as a dependency matrix. When the dependency matrix = 1, it means that task T i Depends on T j The task can be started only after it is completed. The dependency matrix = 0 means there is no dependency between the two. At the same time, the initial priority and monitoring granularity are set for each task based on the initial classification results and dependency relationships. The dependency weight is calculated based on the dependency relationships to represent the task T. j For Task T i the degree of impact of completion; S2. Collect data on the execution status of each task based on the initial monitoring granularity. Based on the collected data, determine whether the actual progress of each task deviates from the planned progress. If a task anomaly occurs, introduce a deviation regularization term λ i To correct the progress deviation calculation of abnormal tasks, and at the same time transmit the corrected deviation to downstream tasks through the task dependency relationship; the data collected includes task completion percentage, current time consumption and resource usage; The actual progress of each task is judged based on the collected data to see whether it deviates from the planned progress. The specific calculation is as follows: First calculate the task T i Plan progress Plan progress It is calculated based on the estimated completion time and resource allocation of the task at the beginning of the project; the actual progress of the task P i and planned progress Compare and get the progress deviation ΔP i,pre , the calculation formula of progress deviation is: in, Indicates the current time point task T i percentage of planned completion; c i Represents task T i The actual completion percentage; if the deviation ΔP i,pre If it is greater than the set threshold ∈, the task is marked as progress abnormal; Among them, if the task abnormality occurs, the deviation regularization term λ is introduced i To correct the progress deviation calculation of abnormal tasks, and transmit the corrected deviation to downstream tasks through task dependencies, specifically including: Redefine deviation ΔP i The calculation formula is: Among them, λ i Represents task T i The regularization factor is determined by the task dependency weight W ij The importance of the task determines: Among them, β j Represents task T j The importance coefficient of For task T i Progress deviation ΔP occurs i , which depends on the task T j The progress impact is calculated using the following formula: in, Represents task T i The progress deviation of task T j the extent of the impact; S3. Collect the behavioral data of each project role, including task response time, task execution time, communication frequency, and progress feedback frequency. Then, calculate the behavioral deviation of each role based on regularization, calculate the collaborative efficiency between roles based on the behavioral deviation of each role, and then dynamically adjust task allocation and progress management. role The calculation is as follows: Among them, t response represents the task response time, reflecting the delay from the time the role is assigned to the start of execution; t exec Indicates the task execution time, which is the total time from the start to the completion of the task; Represents task T i The planned execution time comes from the initial project planning; α and β represent regularization coefficients, reflecting the impact of communication frequency and feedback frequency on efficiency; The optimal communication frequency value for this task type, derived from historical data or experience; Indicates the optimal feedback frequency of a task, which is used to measure the transparency of feedback on the progress of the task; The collaborative efficiency E between the roles role , calculated as follows: Among them, δ ij Denotes dependency impact deviation, indicating that the role performs task T j Time dependent task T i progress impact; S4. Re-optimize task priorities and resource allocation based on the results of dynamic adjustments; S5. Provide feedback to project managers after executing optimization tasks and provide intelligent decision support.

2. The intelligent statistical analysis method for production project implementation progress according to claim 1, characterized in that: The initial classification includes the following categories: critical tasks, common tasks and auxiliary tasks; The structure of the directed acyclic task graph G=(V, E) is as follows: The nodes in the graph represent tasks T i , side R ij Represents task T i Depends on task T j Completion of, where V is the node of the task set T, E is the dependency relationship R between tasks; The initial priority and monitoring granularity are set for each task based on the initial classification results and dependencies, as follows: The key task T critical Given the highest initial priority Pr i =1; The ordinary task T normal Assign medium priority Pr i =2; The auxiliary task T support Assign the lowest priority Pr i =3; The dependency weight W ij , which is expressed as follows: Among them, d i Represents task T i The expected duration of j Represents task T j Resource requirements; i Represents task T i personnel needs.

3. The intelligent statistical analysis method for production project implementation progress according to claim 1, characterized in that: A task T i Progress deviation ΔP i If the set threshold ∈ is exceeded, the system will automatically increase the monitoring frequency of the task and adjust its monitoring granularity g i , the specific adjustment rules are as follows: If ΔP i >∈, the task T i The monitoring granularity is updated to This means the monitoring frequency is doubled, and twice as much data is obtained; If ΔP i Back to normal range, that is, ΔP i ≤∈, then restore the monitoring granularity to the initial state g i .

4. The intelligent statistical analysis method for production project implementation progress according to claim 1, characterized in that: The dynamic adjustment of task allocation and progress management is achieved by analyzing the overall impact of collaborative efficiency on dependent tasks, calculated as follows: in, Indicates role j collaborative efficiency; Represents task T i The progress deviation of its dependent task T j impact.

5. The intelligent statistical analysis method for production project implementation progress according to claim 1, characterized in that: Said S4 specifically includes: A dynamic priority model is designed to dynamically adjust priorities based on task progress, the transmission impact of dependent tasks, and the collaborative efficiency of roles. The dynamic priority model is expressed as follows: in, Represents task T i The dynamically adjusted priority of i Represents task T i The progress deviation reflects the current execution progress of the task; Represents task T i The planned progress is used to compare with the actual progress; σ and τ are adjustment coefficients, which represent the weight of the progress deviation and the priority adjustment of the dependent tasks respectively; Indicates dependent task T j T i The conduction effect, W ij Represents task T j T i The dependency weight of Indicates the impact of role collaboration efficiency on priority; Dynamically adjust resource allocation based on the adjusted priorities, and then automatically generate a new schedule P based on the adjustments to priorities and resources. new ; wherein the resource allocation is dynamically adjusted according to the adjusted priority, as shown below: in, Represents task T i newly allocated resources; Represents task T i The initial resource requirement is based on the initial planning of the task; δ represents the resource allocation weight coefficient, which is used to adjust resource allocation according to priority; The sum of the new priorities of all tasks, used to normalize resource allocation ratios.

6. The method for intelligent statistical analysis of production project implementation progress according to claim 5, characterized in that: Said S4 further includes: After generating new priorities, resource allocation plans, and schedules, these adjustments are fed back to the project manager, who can view the adjustment details through a visual interface, including: Generate critical task reminders based on the highest priority tasks, prompting managers to focus on these tasks; Provide optimization suggestions for resource allocation to help managers reasonably allocate limited resources and ensure that key tasks in the project receive adequate support; If the dependencies of certain tasks have a significant impact on the project progress, first adjust the task dependency order or optimize the resource allocation plan.

7. The method for intelligent statistical analysis of production project implementation progress according to claim 1, characterized in that: Said S5 specifically includes: Generate feedback reports through an intuitive visual interface, including changes in task priorities, resource allocation adjustments, and new schedules; Automatically mark tasks with changed priorities and tasks that may have problems, specifically: If task T i Priority If the progress of a task exceeds the set threshold, it will be marked as a "critical task" to remind managers to pay priority attention; if the progress deviation of a task is ΔP i or dependent influence If the set threshold is exceeded, the task will be marked as a "risk task", prompting the manager to intervene in the task; Automatically generate optimization suggestions based on feedback data, including: If the collaborative efficiency of the execution roles of a task is lower than the set threshold, it will be recommended to assign part or all of the current task to other efficient roles to reduce the risk of task delays caused by coordination issues; If there are insufficient resources for certain high-priority tasks, managers are advised to reallocate resources from lower-priority tasks to ensure the successful completion of critical tasks; Specifically, resource adjustment suggestions are generated using the following formula: in, Indicates the resource adjustment amount recommended by the system; Represents task T i Dynamically adjusted resource requirements; Represents task T i Current resource allocation.

8. A system for executing the method for intelligent statistical analysis of production project implementation progress according to claim 1, characterized in that: The system comprises: The project initialization module is used to initially classify all task lists in the production project and construct a directed acyclic task graph based on the task list after initial classification to represent the dependency relationship between tasks. The dependency relationship is quantified as a dependency matrix. When the dependency matrix = 1, it means that task T i Depends on T j The task can be started only after it is completed. The dependency matrix = 0 means there is no dependency between the two. At the same time, the initial priority and monitoring granularity are set for each task based on the initial classification results and dependency relationships. The dependency weight is calculated based on the dependency relationships to represent the task T. j For Task T i the degree of impact of completion; The project correction module is used to collect data on the execution status of each task according to the initial monitoring granularity of each task, and judge whether the actual progress of each task deviates from the planned progress based on the collected data. If a task anomaly occurs, the deviation regularization term λ is introduced. i To correct the progress deviation calculation of abnormal tasks, and transmit the corrected deviation to downstream tasks through task dependencies; The task allocation module collects behavioral data for each project role, including task response time, task execution time, communication frequency, and progress feedback frequency. It then calculates the behavioral deviation of each role based on regularization, and calculates the collaborative efficiency between roles based on each role's behavioral deviation, thereby dynamically adjusting task allocation and progress management. Allocation optimization module, used to re-optimize task priorities and resource allocation based on the results of dynamic adjustments; The project optimization module is used to provide feedback to project managers after executing optimization tasks and provide intelligent decision support.

Images