Project intelligent management method and system based on enterprise digital information

Abstract

The invention provides an intelligent project management method and system based on enterprise digital information. According to the method, firstly, real-time process data and dynamic image data in an enterprise project are collected, and the dynamic image data cover operation records and a project initial framework; then, extracting a personnel action track and an equipment state from the image data, forming an operation feature set comprising operation coherence parameters and abnormal frequency, analyzing a sequential logic relationship of process data, and generating a standard project task book containing a task decomposition structure; then, the information is matched and converted into multi-dimensional management parameters containing dynamic task priority weights, a dynamic process topological structure isomorphic to the standard task book is constructed based on the multi-dimensional management parameters, and a real-time feedback path is embedded in the dynamic process topological structure to trigger version iteration of the standard project task book. According to the technical scheme provided by the invention, the efficiency and flexibility of intelligent project management can be improved.

Description

Technical Field

[0001] This application relates to the technical field of project intelligent management, and particularly to a project intelligent management method and system based on enterprise digital information. Background Art

[0002] In modern enterprise project management, with the continuous growth of business complexity and scale, higher requirements are put forward for the real-time monitoring and dynamic adjustment capabilities during the project execution process. In projects involving cross-departmental collaboration, multi-task parallel processing, and high dependence on equipment operation and personnel coordination, it becomes particularly important to provide effective decision support based on these data. This not only requires managing static information such as operation records and task book frameworks in the project process, but also needs to analyze the movement trajectories of personnel and the operating states of equipment in real time to promptly discover potential problems or bottlenecks and ensure the efficient progress of the project.

[0003] Currently, some enterprises have begun to adopt integrated enterprise resource planning systems to achieve the digital transformation of project management. Through the enterprise resource planning system, various project-related data can be centrally managed and integrated, including but not limited to financial information, human resource allocation, material management, etc., thus providing a comprehensive data view for project managers. In addition, some advanced enterprise resource planning systems also integrate data analysis tools, which can deeply mine historical project data, assist in predicting future project trends, and improve the overall execution and success rate of projects.

[0004] Although enterprise resource planning systems have made significant progress in improving project management efficiency, there are still certain limitations. First, most enterprise resource planning systems focus on post-event analysis rather than real-time monitoring, and are slow to respond to subtle changes during the project execution process, making it difficult to achieve real-time anomaly detection and rapid response. Second, the data analysis functions of such systems are usually relatively general, lacking customized analysis models for specific industries or project types, resulting in insufficient in-depth or accurate insights when dealing with complex and specific-domain projects. Finally, due to the complexity and high cost of enterprise resource planning systems, small and medium-sized enterprises often cannot afford their deployment and maintenance costs, restricting the popularization and application of this advanced technology. Summary of the Invention

[0005] This application provides a project intelligent management method and system based on enterprise digital information to solve the problems of low efficiency and poor flexibility in project intelligent management in the prior art.

[0006] In a first aspect, this application provides a project intelligent management method based on enterprise digital information, including:

[0007] Obtain the process data and dynamic image data generated in real time in the enterprise project. The process data includes the operation records of project execution nodes and the initial framework of the project task book;

[0008] Extract the personnel action trajectories and equipment operation status from the dynamic image data, and generate an operation feature set including operation coherence parameters and abnormal action frequencies;

[0009] Analyze the temporal logic relationship in the process data, and generate a standard project task book including the task breakdown structure in combination with the initial framework of the project task book;

[0010] Match the temporal logic relationship with the operation feature set, construct a project execution feature vector based on the task breakdown structure, and convert the project execution feature vector into a multi-dimensional management parameter including dynamic task priority weights according to the resource allocation parameters and historical project evaluation indicators in the enterprise digital information;

[0011] Generate a dynamic process topology structure isomorphic to the standard project task book based on the multi-dimensional management parameter, and embed a real-time feedback path in the dynamic process topology structure to trigger the version iteration of the standard project task book.

[0012] Optionally, the generating a dynamic process topology structure isomorphic to the standard project task book based on the multi-dimensional management parameter includes:

[0013] Bind the dynamic task priority weight and resource adaptation coefficient in the multi-dimensional management parameter to the node connection rule and resource channel capacity of the topology node respectively, where the node connection rule is associated with the task breakdown structure level in the standard project task book;

[0014] Establish the initial connection path of the topology node based on the task breakdown structure level, and dynamically allocate path bandwidth according to the resource channel capacity to form a basic topology framework;

[0015] Plant a status response mechanism in the basic topology framework. When the operation records of project execution nodes and the abnormal action frequency in the dynamic image data exceed the preset tolerance, activate the recalculation of the connection rule of the topology node;

[0016] Based on the temporal logic relationship, constrain the connection direction between nodes, and generate a dynamic process topology structure isomorphic to the standard project task book in combination with the result of the recalculation of the connection rule.

[0017] Optionally, the activating the recalculation of the connection rule of the topology node when the operation records of project execution nodes and the abnormal action frequency in the dynamic image data exceed the preset tolerance includes:

[0018] Obtain the operation records and dynamic image data of the project execution nodes in real time, extract the event markers in the operation records and the action trajectory features in the dynamic image data, and align and generate the joint feature vector of events and actions within the time series window;

[0019] Calculate the projection distance between the abnormal action matching degree index and the preset abnormal pattern library based on the joint feature vector of events and actions. When the average value of the projection distances in consecutive windows exceeds the preset tolerance threshold, trigger a recalculation instruction;

[0020] According to the recalculation instruction, fuse the historical connection rules, resource channel capacity, and node level constraints of the topological nodes to construct a dynamic optimization target algorithm, and iteratively adjust the weight distribution matrix of the node connection rules until the convergence condition is met;

[0021] Update the adjusted weight distribution matrix to the connection rule engine of the topological node, and activate the recalculation of the connection rules of the topological node.

[0022] Optionally, the calculating the projection distance between the abnormal action matching degree index and the preset abnormal pattern library based on the joint feature vector of events and actions, and triggering a recalculation instruction when the average value of the projection distances in consecutive windows exceeds the preset tolerance threshold includes:

[0023] Decompose the joint feature vector of events and actions into an event marker and an action trajectory subspace, extract the principal component features of the action trajectory subspace, and construct a dynamic mapping matrix aligned with the dimension of the preset abnormal pattern library;

[0024] Based on the dynamic mapping matrix, project the joint feature vector of events and actions into the implicit space of the preset abnormal pattern library, calculate the weighted Mahalanobis distance between the projection features and the preset abnormal pattern library, and generate a multi-dimensional projection distance sequence;

[0025] Perform sliding window truncation on the multi-dimensional projection distance sequence, extract the extreme value distribution and covariance parameters of the window projection distance, and align the window distribution characteristics through dynamic time warping to obtain the sliding decay factor of the abnormal action matching degree index;

[0026] When the weighted average value of the sliding decay factors in consecutive windows exceeds the preset tolerance threshold, trigger a recalculation instruction according to the extreme value distribution and the covariance parameters.

[0027] Optionally, embedding a real-time feedback path in the dynamic process topology structure to trigger the version iteration of the standard project task book includes:

[0028] Identify a feedback trigger node associated with the dynamic task priority weight in the multi-dimensional management parameters in the dynamic process topology structure, and extract the resource consumption rate and task delay rate of the feedback trigger node as real-time state parameters;

[0029] Compare the real-time state parameters with a preset threshold vector to generate the trigger signal strength of the feedback path, and construct a feedback path priority queue from the feedback trigger node to the version control node of the standard project task book based on the trigger signal strength;

[0030] Locate the task level to be iterated in the task breakdown structure according to the cumulative signal strength of the feedback path priority queue, and extract the logical dependency strength and historical version difference features to generate a task breakdown difference matrix;

[0031] Optimize and adjust the node connection rules in the task breakdown structure based on the task breakdown difference matrix, and trigger the version iteration of the standard project task book.

[0032] Optionally, the locating the task level to be iterated in the task breakdown structure according to the cumulative signal strength of the feedback path priority queue, and extracting the logical dependency strength and historical version difference features to generate a task breakdown difference matrix includes:

[0033] Decompose the cumulative signal strength of the feedback path priority queue into a time decay factor and a spatial distribution weight to generate a hierarchical location weight assignment matrix, traverse each task level in the task breakdown structure, and construct a logical dependency matrix based on the logical dependency strength;

[0034] Extract the change operation sequence and parameter offset of the task level node in the historical version of the task breakdown structure, map the change operation sequence to an operation type coding vector, and generate a hierarchical difference metric tensor in combination with the parameter offset;

[0035] Perform a modal product operation on the logical dependency matrix and the hierarchical difference metric tensor to obtain cross-hierarchical difference propagation features, and perform a Hadamard association with the hierarchical location weight assignment matrix to generate an initial component of the task breakdown difference;

[0036] Based on the sparse characteristics of the initial component, perform reverse gradient pruning on the task breakdown difference propagation features, and retain the difference components associated with the current feedback signal strength to generate a task breakdown difference matrix.

[0037] Optionally, the parsing the temporal logic relationship in the process data and generating a standard project task book including a task breakdown structure in combination with the initial framework of the project task book includes:

[0038] Parse the operation records of project execution nodes in the process data into a discrete event marker sequence, extract the temporal tightness parameter, and construct a temporal directed graph structure with the time interval between event trigger timestamps as the edge weight;

[0039] Traverse the critical path in the temporal directed graph structure, calculate the overlapping execution probability and resource preemption conflict frequency of event nodes on the critical path, and generate a logical dependence strength matrix between the event nodes;

[0040] Map and align the task nodes in the initial framework of the project task book with the event nodes, perform subgraph segmentation on the task hierarchy based on the logical dependence strength matrix, and extract task node embedding vectors;

[0041] Generate an initial hierarchical connection rule according to the clustering center distribution of the task node embedding vectors and the overlapping execution probability between the subgraphs, and combine the dynamic offset in the temporal directed graph structure to adjust the parallelism threshold in the initial hierarchical connection rule to generate a standard project task book containing a task breakdown structure.

[0042] In a second aspect, the present application provides a project intelligent management system based on enterprise digital information, including:

[0043] An acquisition module that acquires process data and dynamic image data generated in real time in an enterprise project, where the process data includes operation records of project execution nodes and an initial framework of a project task book;

[0044] An extraction module that extracts human action trajectories and device operation states from the dynamic image data, and generates an operation feature set including operation coherence parameters and abnormal action frequencies;

[0045] An analysis module that analyzes the temporal logical relationship in the process data, and generates a standard project task book containing a task breakdown structure in combination with the initial framework of the project task book;

[0046] A construction module that matches the temporal logical relationship with the operation feature set, constructs a project execution feature vector based on the task breakdown structure, and converts the project execution feature vector into a multi-dimensional management parameter including dynamic task priority weights according to resource allocation parameters and historical project evaluation indicators in enterprise digital information;

[0047] A generation module that generates a dynamic process topology structure isomorphic to the standard project task book based on the multi-dimensional management parameter, and embeds a real-time feedback path in the dynamic process topology structure to trigger version iteration of the standard project task book.

[0048] In a third aspect, the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a project intelligent management method based on enterprise digital information as described in the first aspect above.

[0049] In a fourth aspect, the present application provides a computer storage medium storing a computer program, which when executed by a computer, implements a project intelligent management method based on enterprise digital information as described in the first aspect.

[0050] In an embodiment of the present application, process data and dynamic image data generated in real time in an enterprise project are obtained. The process data includes operation records of project execution nodes and an initial framework of a project task book; a personnel action trajectory and a device operation state are extracted from the dynamic image data to generate an operation feature set including operation coherence parameters and abnormal action frequencies; the temporal logic relationship in the process data is parsed, and a standard project task book including a task breakdown structure is generated in combination with the initial framework of the project task book; the temporal logic relationship is matched with the operation feature set, and a project execution feature vector is constructed based on the task breakdown structure. According to resource allocation parameters and historical project evaluation indicators in enterprise digital information, the project execution feature vector is converted into a multi-dimensional management parameter including dynamic task priority weights; a dynamic process topology structure isomorphic to the standard project task book is generated based on the multi-dimensional management parameter, and a real-time feedback path is embedded in the dynamic process topology structure to trigger version iteration of the standard project task book.

[0051] The technical solution of the present application has the following beneficial effects:

[0052] This application obtains the process data and dynamic image data generated in real time in enterprise projects, ensuring comprehensive monitoring of project execution and being able to capture every detail change during the project process. Through the collection of operation records and initial frameworks, it provides basic data support for subsequent analysis. Extract the personnel action trajectories and equipment operation status from the dynamic image data to generate an operation feature set. This step realizes the detailed tracking of personnel behavior and equipment status, helps to identify potential operation problems or efficiency bottlenecks, and adjusts the work process based on this information. Combine the initial framework of the project task book to generate a standard project task book containing a work breakdown structure. This step clarifies the logical relationship between tasks through the analysis of chronological order, thereby optimizing task allocation and resource planning and improving the overall execution power of the project. Embed a real-time feedback path in the dynamic process topology to trigger the version iteration of the standard project task book. The final step is to create a flexible project management model that can be automatically adjusted and updated according to the actual execution situation to ensure that the project always moves forward along the optimal path.

[0053] Further, the method for generating a dynamic process topology isomorphic to the standard project task book based on multi-dimensional management parameters includes binding the dynamic task priority weight and resource adaptation coefficient to the rules and capacities of topological nodes, establishing a preliminary connection path and forming a basic framework by dynamically allocating path bandwidth; on this basis, implant a status response mechanism to handle abnormal operations, and constrain the connection direction between nodes according to the chronological logic relationship, and then generate a dynamic process topology. This method makes project management more intelligent and flexible. It can not only adjust resource allocation and task priorities according to real-time data, but also quickly respond to abnormal situations during project execution, effectively improving the project execution efficiency and success rate, and at the same time promoting the continuous optimization and update of project documents.

[0054] These aspects or other aspects of this application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0056] Figure 1 Shows a flowchart of a project intelligent management method based on enterprise digital information provided by this application;

[0057] Figure 2Shows a schematic structural diagram of a project intelligent management system based on enterprise digital information provided by this application;

[0058] Figure 3 Shows a schematic structural diagram of a computing device provided by this application. Detailed implementation manners

[0059] In order to enable those skilled in the art of this technology to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application.

[0060] In some processes described in the specification, claims and the above-mentioned accompanying drawings of this application, there are multiple operations that appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish each different operation, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., do not represent a sequence, and do not limit that "first" and "second" are different types.

[0061] This solution aims to integrate the real-time process data and dynamic image data in enterprise projects to achieve comprehensive monitoring and analysis of the project execution situation. By collecting operation records and initial framework information, it lays a foundation for subsequent parsing of task logical relationships to ensure that the project progress can be accurately captured.

[0062] The technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts belong to the scope protected by this application.

[0063] Figure 1 The flowchart of a project intelligent management method based on enterprise digital information provided for the embodiments of this application is as Figure 1 shown, and the method includes:

[0064] 101. Obtain the process data and dynamic image data generated in real time in the enterprise project, where the process data includes the operation records of project execution nodes and the initial framework of the project task book;

[0065] In this step, the process data generated in real time in the enterprise project refers to the operation records of each node during the project execution, including but not limited to information such as start time, end time, operation content, etc.

[0066] The dynamic image data is the video stream or picture sequence captured by cameras or other monitoring devices, which is used to reflect the actual on-site situation.

[0067] The initial framework of the project task book is the task outline defined in the initial stage of the project startup, which includes the overall project objectives, expected outcomes, and preliminary task decomposition.

[0068] In the embodiment of this application, first, the real-time data stream is collected through sensors and cameras deployed in each work area. After preprocessing, these data are divided into two categories: process data and dynamic image data. For the process data, a log collection tool is used to capture it from various management systems; while the dynamic image data is analyzed through image recognition technology to extract key frames and scene descriptions. Finally, these two types of data are integrated with the initial framework of the project task book to provide basic data support for the subsequent steps.

[0069] In a manufacturing enterprise, each machine on the production line is equipped with sensors to monitor the operating status and upload the data to the central server. At the same time, cameras installed in the workshop record the working conditions of employees, and video analysis software is used to extract the movement trajectories of personnel. The project manager formulates a preliminary project task book according to the project requirements, which clarifies the various task indicators for producing new products. As the production line operates, real-time data continuously flows into the system, providing rich materials for the subsequent analysis.

[0070] 102. Extract the movement trajectories of personnel and the operating status of equipment from the dynamic image data, and generate an operation feature set including operation coherence parameters and abnormal action frequencies;

[0071] In this step, the operation feature set includes operation coherence parameters and abnormal action frequencies obtained from the analysis of dynamic image data.

[0072] The operation coherence parameter measures the continuity and smoothness in the operation process.

[0073] The abnormal action frequency refers to the frequency of actions that do not conform to the pre-set standard operation specifications in the operation process. These actions may include incorrect operation steps, non-standard work behaviors, or any behavior deviating from the normal operation process. By counting the abnormal action frequency, the work efficiency and quality of the operator can be evaluated, and at the same time, the operation links that need to be improved can be identified.

[0074] In the embodiments of the present application, first, computer vision algorithms are used to deeply analyze dynamic image data to identify the specific actions and trajectories of personnel. Then, by comparing the actual operations with the set standard operation process template, the operation coherence parameter is calculated. At the same time, any behavior deviating from the normal behavior pattern is marked as an abnormal action, and the number of occurrences is counted. Finally, a comprehensive set of operation characteristics is generated.

[0075] In the case of the above manufacturing enterprise, by analyzing the operation videos of workers, the system can accurately track each action of each worker on the assembly line and evaluate whether these actions conform to the predetermined operation specifications. For example, if a certain worker frequently needs to adjust the position of parts, this behavior will be recorded as an abnormal action, which will in turn affect the overall operation coherence score.

[0076] 103. Analyze the temporal logic relationship in the process data, and generate a standard project task book containing a task breakdown structure in combination with the initial framework of the project task book;

[0077] In this step, the temporal logic relationship describes the time sequence and dependency relationship between tasks during the project execution process. It includes which tasks must be completed first before other tasks can start, as well as the expected start time and end time of each task.

[0078] The task breakdown structure is a method of decomposing a project into smaller and more manageable parts according to a hierarchical structure. It not only clarifies the overall goals of the project but also details all the work tasks required to achieve these goals.

[0079] The standard project task book is a document formulated based on analyzing the temporal logic relationship in the process data and in combination with the initial framework of the project task book. It details the task breakdown structure of the project, that is, the result of dividing all the work tasks of the project according to a hierarchical structure.

[0080] In the embodiments of the present application, first, natural language processing technology is used to analyze the text information in the process data to determine the sequence and dependency relationship between different tasks. Then, based on the initial framework of the project task book, a clear task breakdown structure is constructed to ensure that each subtask has clear goals and deliverables. The finally formed document not only covers all the task details of the project but also reflects the time sequence and interrelationships between tasks.

[0081] Continuing with the example of a manufacturing enterprise, after clarifying the operation process on the production line, the system automatically generates a detailed project task book. This document not only lists all the necessary production steps but also indicates which steps must be completed first before starting the next link, thus helping the team better plan resources and time.

[0082] 104. Match the timing logic relationship with the set of operation characteristics, construct a project execution feature vector based on the task decomposition structure, and convert the project execution feature vector into a multi-dimensional management parameter containing dynamic task priority weights according to the resource allocation parameters and historical project evaluation indicators in the enterprise digital information;

[0083] In this step, the project execution feature vector is a mathematical model used to represent the key features in the project execution process, including but not limited to operation coherence parameters, abnormal action frequencies, etc.

[0084] The historical project evaluation indicators refer to various evaluation criteria and results in past completed projects, such as cost control situation, schedule compliance degree, quality compliance rate, etc.

[0085] The multi-dimensional management parameter is a set of values converted from the project execution feature vector, comprehensively considering factors such as resource allocation parameters and historical project evaluation indicators, and is used to quantify the dynamic priority weights of each task in the project execution process.

[0086] In the embodiment of the present application, first, combine the previously obtained set of operation characteristics with the timing logic relationship to form a project execution feature vector. Then, use a mathematical model and optimization algorithm to adjust each dimension in the feature vector according to the internal resource allocation situation of the enterprise and the evaluation criteria of past similar projects, so that it is transformed into a multi-dimensional management parameter with practical guiding significance.

[0087] In the context of a manufacturing enterprise, based on the data accumulated in the previous stages, the system can calculate the importance and urgency of each production task. For example, when it is found that a certain process often causes the production line to stagnate, the system will automatically increase the weight of this process in the multi-dimensional management parameter to remind the management to pay attention and solve this problem.

[0088] 105. Generate a dynamic process topology structure isomorphic to the standard project task book based on the multi-dimensional management parameter, and embed a real-time feedback path in the dynamic process topology structure to trigger the version iteration of the standard project task book.

[0089] In this step, the dynamic process topology structure is a visual representation method used to display various activities and their interrelationships in the project execution process, and embeds a real-time feedback path, allowing the standard project task book to be updated according to the actual situation to promote version iteration.

[0090] The real-time feedback path refers to the mechanism embedded in the dynamic process topology structure, which allows the system to automatically update the project status according to the latest data input and provide instant feedback.

[0091] In the embodiments of the present application, first, with the help of a graphical modeling tool, multi-dimensional management parameters are transformed into a visual flow chart. On this basis, a real-time feedback mechanism is added so that whenever new data is input or external conditions change, the content of the flow chart can be immediately adjusted, and the corresponding part can be triggered to update, ensuring the flexibility and adaptability of the entire project management system.

[0092] For manufacturing enterprises, once the system detects problems such as certain equipment failures or raw material shortages, it can quickly mark them in the dynamic process topology structure and suggest corresponding solutions. This not only helps to quickly solve problems, but also prompts the project task book to be updated in a timely manner to ensure that the project progresses as planned.

[0093] In summary, steps 101 to 105 achieve full-process coverage of enterprise projects from data collection, feature extraction, task decomposition, priority setting to dynamic management by integrating a variety of advanced technologies. This method improves the efficiency and accuracy of project management, enhances the ability to respond to emergencies, promotes the effective allocation and utilization of resources, and provides a solid guarantee for the enterprise to achieve efficient operation.

[0094] In order to further improve the flexibility and response speed of project management, this solution focuses on using multi-dimensional management parameters to construct a dynamic process topology structure isomorphic to the standard project task book. By binding the priority weight and resource adaptation coefficient to the node rules and capacity, a preliminary connection path is established, and the path bandwidth is dynamically adjusted according to the resource channel capacity to form a highly adaptable basic framework. In some embodiments, the generating of the dynamic process topology structure isomorphic to the standard project task book as described in step 105 includes:

[0095] 201. Bind the dynamic task priority weight and resource adaptation coefficient in the multi-dimensional management parameters to the node connection rule and resource channel capacity of the topology node respectively, where the node connection rule is associated with the task decomposition structure level in the standard project task book;

[0096] In step 201, the dynamic task priority weight in the multi-dimensional management parameter is used to quantify the importance and urgency of each task during project execution, and the resource adaptation coefficient reflects the adjustment ratio of task allocation according to the current resource status. The node connection rule is associated with the task decomposition structure level in the standard project task book, defining the logical relationship and dependency between different tasks. The resource channel capacity represents the amount of data that can be transmitted or the number of tasks that can be completed on a specific path, ensuring the effective utilization of resources.

[0097] In the embodiments of the present application, first, the dynamic task priority weights of each task are determined by analyzing multi-dimensional management parameters, and the resource adaptation coefficients are adjusted accordingly. Then, these weights and coefficients are bound to the node connection rules and resource channel capacities of the topology nodes. Next, a logical connection between tasks is established using graph theory algorithms to ensure that the hierarchical structure of the task decomposition is accurately reflected. Finally, based on the above information, a preliminary topology node configuration is formed to provide a basis for subsequent steps.

[0098] 202. Establish an initial connection path for the topology nodes based on the hierarchical structure of the task decomposition, and dynamically allocate path bandwidth according to the resource channel capacity to form a basic topology framework.

[0099] In step 202, the hierarchical structure of the task decomposition is the result of dividing project tasks according to their importance and execution order, which helps to identify which tasks need to be completed first. The initial connection path is established based on this hierarchical relationship, and the path bandwidth refers to the amount of data or tasks that can pass through a certain path within a certain period of time. Reasonable allocation of path bandwidth can ensure the effective flow of resources and the smooth execution of tasks.

[0100] In the embodiments of the present application, first, an initial connection path between topology nodes is established based on the hierarchical structure of the task decomposition. Then, a traffic control algorithm is used to dynamically allocate path bandwidth according to the resource channel capacity to ensure that each node has sufficient resources to support its operations. Next, the entire network is checked for bottlenecks or redundancies, and the path design is optimized. Finally, a stable basic topology framework is constructed to provide a platform for real-time adjustment.

[0101] 203. Implant a status response mechanism in the basic topology framework. When the operation records of the project execution nodes and the abnormal action frequencies in the dynamic image data exceed a preset tolerance, activate the recalculation of the connection rules of the topology nodes.

[0102] In step 203, the status response mechanism is a mechanism that monitors the running status of the system and can automatically trigger corresponding measures. The preset tolerance refers to the allowable range of operation errors. Once this range is exceeded, it is regarded as abnormal. The recalculation of the connection rules means that when an abnormality is detected, the relationship between nodes is re-evaluated and adjusted to adapt to the new situation. The preset tolerance refers to the maximum range of allowable operation errors or abnormal behaviors. Once this range is exceeded, it is regarded as abnormal and requires intervention and adjustment. The resource channel capacity plays a key role in this process, defining the amount of data that can be transmitted or the number of tasks that can be completed on a specific path to ensure the effective utilization of resources and the smooth execution of tasks.

[0103] In the embodiments of the present application, first, a state response mechanism is implanted in the basic topology framework, and a preset tolerance is set as the judgment criterion. Then, the operation records of the project execution nodes and the abnormal action frequencies in the dynamic image data are monitored in real time. Then, once a situation exceeding the preset tolerance is detected, for example, a certain task frequently has incorrect operations resulting in low efficiency, the connection rule recalculation process is immediately activated. At this time, the system will re-evaluate the relationships between the affected nodes and their associated nodes based on the latest data, and adjust the connection rules between the nodes according to the current resource channel capacity. Finally, the dynamic process topology structure is updated to reflect these changes, ensuring the flexibility and adaptability of the system, while maintaining the stability and efficiency of the overall project.

[0104] 204. Based on the temporal logic relationship, constrain the connection direction between nodes, and combine the results of the connection rule recalculation to generate a dynamic process topology structure isomorphic to the standard project task book.

[0105] In step 204, the temporal logic relationship is used to describe the time sequence and dependency relationship between tasks during the project execution process, ensuring that tasks are carried out in the correct order. The connection rule recalculation refers to the process of re-evaluating and adjusting the connection rules between nodes when abnormal operations or exceeding the preset tolerance are detected. The dynamic process topology structure is a visual representation method used to display various activities and their interrelationships during the project execution process, and allows for quick adjustment of the project plan according to the actual situation.

[0106] In the embodiments of the present application, first, based on the established basic topology framework, time series analysis technology is used to determine the temporal logic relationship of each task, ensuring that the sequence of tasks is accurately reflected. Then, combined with the results of the connection rule recalculation, the connection direction between nodes is adjusted through graph theory algorithms to conform to the actual operation process and logical dependencies. Then, an optimization algorithm is used to further optimize the entire network, ensuring reasonable allocation of resource channel capacity and path bandwidth and avoiding bottlenecks. Finally, all information is integrated to generate a dynamic process topology structure isomorphic to the standard project task book, making project management more flexible and efficient, capable of responding to changes in real time and making rapid adjustments.

[0107] The following is a specific example:

[0108] On the production line of a manufacturing enterprise, real-time data is collected by integrating sensors and cameras. First, based on the analysis of previous data, the dynamic task priority weights and resource adaptation coefficients for each process are determined and applied to each workstation (node) on the production line. Then, the connection paths between workstations are planned according to the task breakdown structure hierarchy, and the bandwidth is dynamically adjusted according to resource requirements. Next, a status response mechanism is set up to monitor the operating status of the production line. When frequent failures occur in a certain process, the system automatically triggers the recalculation of connection rules, rearranges the relationship between this process and other processes, optimizes resource allocation, and ensures the efficient operation of the production line.

[0109] In summary, steps 201 to 204 achieve precise management and rapid response to complex projects by dynamically adjusting task priorities and resource allocations during project execution. It can not only effectively avoid resource waste but also quickly respond to emergencies, greatly improving the success rate and efficiency of projects, and providing strong support for enterprises to achieve more efficient operation management.

[0110] To further improve the response speed and accuracy to abnormal situations during project execution, this solution further refines the recalculation mechanism triggered when the abnormal action frequency exceeds the tolerance. By real-time extracting the event markers in the operation records and the action trajectory features of dynamic image data, a joint feature vector is generated within the time series window, and based on this, an abnormal matching degree index is calculated. Once it exceeds the preset threshold, the recalculation instruction is started to optimize the node connection rules. In some embodiments, when the abnormal action frequency in the operation record of the project execution node and the dynamic image data exceeds the preset tolerance in step 203, activating the recalculation of the connection rules of the topology node includes:

[0111] 301. Real-time obtain the operation record of the project execution node and the dynamic image data, extract the event markers in the operation record and the action trajectory features in the dynamic image data, and align and generate an event and action joint feature vector within the time series window;

[0112] In step 301, the event marker is the key information point extracted from the operation record, used to identify the change of a specific operation or state. The action trajectory feature refers to the action path and pattern of personnel or equipment extracted from the dynamic image data. The time series window divides a series of consecutive time periods to facilitate aligning different data streams within the same time range. The event and action joint feature vector is a comprehensive description generated by combining the event marker and the action trajectory feature within the same time series window.

[0113] In the embodiments of the present application, first, operation records and dynamic image data of project execution nodes are obtained through a real-time monitoring system. Then, data mining techniques are used to extract event tags from the operation records, and computer vision algorithms are used to extract action trajectory features from the dynamic image data. Next, these features are aligned within the same time series window to form a joint feature vector of events and actions. Finally, these vectors are used as inputs to provide basic data support for subsequent steps.

[0114] 302. Calculate the projection distance between the abnormal action matching degree index based on the joint feature vector of events and actions and a preset abnormal pattern library. When the average value of the projection distances in consecutive windows exceeds a preset tolerance threshold, trigger a recalculation instruction.

[0115] In step 302, the abnormal action matching degree index is a value used to measure the similarity between the current operation and a preset abnormal pattern. The preset abnormal pattern library is a set of predefined abnormal behavior patterns used to compare and identify abnormal situations in actual operations. The projection distance is a measure of the difference between the joint feature vector of events and actions and the preset abnormal pattern library. When the average value of the projection distances in consecutive windows exceeds the preset tolerance threshold, it indicates that there are significant abnormalities in the current operation and a recalculation instruction needs to be triggered.

[0116] In the embodiments of the present application, first, calculate the projection distance between the joint feature vector of events and actions and the preset abnormal pattern library, and use machine learning algorithms such as support vector machines or neural networks to evaluate the abnormal action matching degree index. Then, continuously monitor the average value of the projection distances in multiple consecutive time series windows. Once it is found that this average value exceeds the preset tolerance threshold, immediately trigger a recalculation instruction. This process ensures the timely detection and response to abnormal situations.

[0117] 303. According to the recalculation instruction, fuse the historical connection rules, resource channel capacities, and node level constraints of the topology nodes to construct a dynamic optimization target algorithm, and iteratively adjust the weight assignment matrix of the node connection rules until the convergence condition is met.

[0118] In step 303, the historical connection rules record the connection patterns and dependency relationships between topology nodes over a past period of time. The resource channel capacity reflects the amount of data that can be transmitted or the number of tasks that can be completed on a specific path. The node level constraint refers to the hierarchical relationship and logical order between nodes determined according to the task breakdown structure. The dynamic optimization target algorithm is a mathematical model used to adjust the weight assignment matrix of the node connection rules to meet specific optimization goals. The convergence condition refers to the state where there are no significant changes after the algorithm iteratively updates to a certain extent.

[0119] In the embodiments of the present application, first, after receiving the recalculation instruction, a dynamic optimization target algorithm is constructed by integrating the historical connection rules, resource channel capacities, and node level constraints of the fusion topology nodes. Then, an optimization algorithm such as a genetic algorithm or a gradient descent method is used to iteratively adjust the weight assignment matrix of the node connection rules. Next, it is continuously checked whether the adjusted result meets the convergence condition until the optimal solution is reached. Finally, a new weight assignment matrix is obtained to provide parameter support for the subsequent steps.

[0120] 304. Update the adjusted weight assignment matrix to the connection rule engine of the topology node, and activate the recalculation of the connection rules of the topology node.

[0121] In step 304, the weight assignment matrix is a set of numerical values representing the importance or priority of the connections between nodes. The connection rule engine is a processing module responsible for updating the connection rules of the topology nodes according to the weight assignment matrix. By updating the adjusted weight assignment matrix to the connection rule engine, the recalculation of the connection rules of the topology node can be activated, realizing the dynamic adjustment of the project execution process.

[0122] In the embodiments of the present application, first, the adjusted weight assignment matrix is imported into the connection rule engine. Then, the connection rule engine recalculates the connection rules between nodes according to the new weight assignment matrix to ensure that all nodes operate according to the latest resource configuration and logical order. Next, the updated topology structure is applied to the actual production environment, enabling the entire system to quickly adapt to changes and maintain efficient operation. Finally, the effective management and rapid response to abnormal situations are realized.

[0123] The following is a specific example:

[0124] On the production line of a manufacturing enterprise, a real-time monitoring system collects operation records and action videos of employees. In a certain process, due to equipment failure, frequent shutdowns occur, exceeding the preset tolerance. The system first extracts event markers and action trajectory features and generates a joint feature vector within the same time sequence window. Then, the projection distance between these features and the preset abnormal pattern library is calculated, triggering a recalculation instruction. Subsequently, the historical connection rules, resource channel capacities, and node level constraints are integrated, and a genetic algorithm is used to iteratively adjust the weight assignment matrix until convergence. Finally, the adjusted matrix is updated to the connection rule engine to recalculate the connection rules between nodes, solving the problems brought by equipment failure and improving the overall efficiency of the production line.

[0125] In summary, steps 301 to 304 achieve fast response and precise management of abnormal situations during the execution of complex projects through real-time monitoring, data analysis, and dynamic adjustment. This not only improves the success rate and efficiency of the project but also enhances the flexibility and adaptability of the system, providing strong support for enterprises to achieve more efficient operation management. In particular, by accurately identifying and promptly intervening in abnormal actions, potential risks are significantly reduced, ensuring the smooth progress of the project.

[0126] To further improve the accuracy and response speed of abnormal action recognition, the solution deeply explores the specific method of accurately calculating the abnormal matching degree index based on the joint feature vector of events and actions, including decomposing the feature vector, extracting the principal component features, and constructing a dynamic mapping matrix. The abnormal behavior is evaluated through the projection distance sequence, and when the average value of the attenuation factor of consecutive windows exceeds the preset threshold, recalculation is triggered to ensure the quality of project execution. In some embodiments, calculating the projection distance between the abnormal action matching degree index based on the joint feature vector of events and actions and the preset abnormal pattern library in step 302, when the average projection distance of consecutive windows exceeds the preset tolerance threshold, triggering a recalculation instruction includes:

[0127] 401. Decompose the joint feature vector of events and actions into an event marker and an action trajectory subspace, extract the principal component features of the action trajectory subspace, and construct a dynamic mapping matrix aligned with the dimension of the preset abnormal pattern library;

[0128] In step 401, the event marker is a key information point extracted from the operation record, used to identify specific operations or state changes. The action trajectory subspace refers to the feature space composed of the action paths and patterns extracted from the dynamic image data. The principal component features are the main feature vectors obtained through dimensionality reduction technology, which can represent the main change directions of the original data. The dynamic mapping matrix is a transformation matrix used to map the joint feature vector of events and actions to a space consistent with the dimension of the preset abnormal pattern library for comparison.

[0129] In the embodiment of the present application, first, the joint feature vector of events and actions is decomposed into an event marker and an action trajectory subspace. Then, the principal component analysis method is used to extract the principal component features from the action trajectory subspace. Then, a dynamic mapping matrix aligned with the dimension of the preset abnormal pattern library is constructed based on these principal component features. Finally, the original feature vector is converted into a form suitable for subsequent analysis using this matrix, providing prepared data for the subsequent steps.

[0130] 402. Based on the dynamic mapping matrix, project the joint feature vector of events and actions into the implicit space of the preset abnormal pattern library, calculate the weighted Mahalanobis distance between the projected features and the preset abnormal pattern library, and generate a multi-dimensional projection distance sequence;

[0131] In step 402, the dynamic mapping matrix is used to transform the feature vector into a space consistent with the preset abnormal pattern library. The implicit space refers to the feature representation space obtained through a certain mathematical transformation, which is usually used to capture the essential features of the data. The weighted Mahalanobis distance is a method for measuring the difference between two distributions, taking into account the correlation between different dimensions. The multi-dimensional projection distance sequence is a data sequence composed of projection distances at multiple time points, used to describe the feature differences changing over time.

[0132] In the embodiment of the present application, first, based on the dynamic mapping matrix, the event and action joint feature vector is projected into the implicit space of the preset abnormal pattern library. Then, the weighted Mahalanobis distance algorithm is used to calculate the distance between the projected feature and the preset abnormal pattern library, generating a multi-dimensional projection distance sequence. Next, by analyzing the values in these sequences, the similarity degree between the current operation and the preset abnormal pattern is evaluated. Finally, a set of projection distance sequences reflecting the feature differences is obtained, providing basic data support for subsequent steps.

[0133] 403. Perform a sliding window interception on the multi-dimensional projection distance sequence, extract the extreme value distribution and covariance parameters of the window projection distance, and obtain the sliding decay factor of the abnormal action matching degree index by aligning the window distribution characteristics through dynamic time warping;

[0134] In step 403, the sliding window interception is to extract a fixed-length time period from the continuous time series data for local feature analysis. The extreme value distribution refers to statistical characteristics such as the maximum and minimum values of the projection distance within the window. The covariance parameter describes the linear dependence relationship between different variables. The sliding decay factor is a way to adjust the weight, used to balance the influence of new and old data, enabling the system to adapt to changes faster. Dynamic time warping is a technique for time series comparison, capable of aligning time series of different lengths.

[0135] In the embodiment of the present application, first, the sliding window technique is adopted to intercept the multi-dimensional projection distance sequence, and the extreme value distribution and covariance parameters within each window are extracted. Then, the dynamic time warping method is used to align the window distribution characteristics to ensure the comparability of data in different time periods. Next, the sliding decay factor is calculated, and its weight is adjusted according to the feature changes within the window. Finally, by synthesizing these parameters, the sliding decay factor of the abnormal action matching degree index is generated, providing a basis for determining whether to trigger the recalculation instruction.

[0136] 404. When the weighted mean of the sliding decay factors of consecutive windows exceeds the preset tolerance threshold, trigger the recalculation instruction according to the extreme value distribution and the covariance parameters.

[0137] In step 404, the weighted mean of the sliding decay factor is the average of the sliding decay factors over a period of time, reflecting the cumulative impact of abnormal actions. The preset tolerance threshold is the allowable range of operating errors, and exceeding this range is regarded as abnormal. The recalculation instruction is a process that triggers the re-evaluation of the topological node connection rules when significant anomalies are detected.

[0138] In the embodiment of the present application, first, the weighted mean of the sliding decay factors of consecutive windows is calculated. Then, this mean is compared with the preset tolerance threshold. If it is found that the weighted mean exceeds the threshold, the recalculation instruction is triggered according to the extreme value distribution and covariance parameters. Then, by integrating the historical connection rules, resource channel capacity, and node level constraints, the weight assignment matrix of the node connection rules is iteratively adjusted until the convergence condition is met. Finally, the updated topological structure is applied to the actual production environment, realizing the effective management and rapid response to abnormal situations.

[0139] The following is a specific example:

[0140] On the production line of a manufacturing enterprise, the real-time monitoring system collects operation records and the action videos of employees. Due to equipment failures, a certain process has frequent downtimes, exceeding the preset tolerance. The system first decomposes the joint feature vector of the event and the action, extracts the principal component features of the action trajectory subspace, and constructs a dynamic mapping matrix. Then, using this matrix, the feature vector is projected into the implicit space of the preset abnormal pattern library, and the projection distance is calculated. These distances are analyzed through the sliding window technique to calculate the sliding decay factor. When the weighted mean of the sliding decay factors of consecutive windows exceeds the preset tolerance threshold, the connection rules between nodes are adjusted, solving the problems brought by equipment failures and improving the overall efficiency of the production line.

[0141] In summary, steps 401 to 404 improve the stability and efficiency in the project execution process by accurately identifying abnormal actions and intervening in a timely manner. It not only enhances the flexibility and adaptability of the system, but also reduces potential risks and ensures the smooth progress of the project. In particular, through the precise analysis of abnormal actions and the dynamic adjustment mechanism, the success rate and management level of the project are greatly improved, providing strong support for the enterprise to achieve more efficient operation and management.

[0142] To further improve the adaptability and flexibility of the standard project task book to the actual project progress, this solution describes a method of embedding a real-time feedback path in a dynamic process topology. By identifying feedback trigger nodes associated with dynamic task priorities, comparing real-time status parameters with preset thresholds, constructing a feedback path priority queue, locating the task levels to be iterated based on the cumulative signal strength, and optimizing the node connection rules in the task decomposition structure, version iteration is promoted. In some embodiments, embedding a real-time feedback path in the dynamic process topology in step 105 to trigger version iteration of the standard project task book includes:

[0143] 501. Identify feedback trigger nodes in the dynamic process topology associated with the dynamic task priority weights in the multi-dimensional management parameters, and extract the resource consumption rate and task delay rate of the feedback trigger nodes as real-time status parameters;

[0144] In step 501, the feedback trigger node refers to a key node in the dynamic process topology associated with the dynamic task priority weights in the multi-dimensional management parameters, and is used to monitor and evaluate the execution status of the current project. The resource consumption rate represents the amount of resources required to complete a specific task and is an important indicator for measuring task execution efficiency. The task delay rate refers to the difference between the actual completion time and the planned completion time of a task, reflecting the time deviation during task execution. The real-time status parameters include the resource consumption rate and the task delay rate, and are used to reflect the current operating conditions of the feedback trigger node.

[0145] In the embodiments of the present application, first, feedback trigger nodes associated with the dynamic task priority weights in the multi-dimensional management parameters are identified in the dynamic process topology. Then, data on the resource consumption rate and task delay rate of these nodes are collected through sensors and management systems. Then, data analysis techniques are used to extract these real-time status parameters, providing basic data support for subsequent steps. Finally, based on these parameters, the actual operating conditions of each key node can be accurately understood, providing a basis for adjusting the project plan.

[0146] 502. Compare the real-time status parameters with a preset threshold vector to generate the trigger signal strength of the feedback path, and construct a feedback path priority queue from the feedback trigger node to the version control node of the standard project task book based on the trigger signal strength;

[0147] In step 502, the threshold vector is a set of preset standard values used to determine whether the real-time status parameters exceed the normal range. The trigger signal strength represents the signal strength generated based on the comparison result between the real-time status parameters and the threshold vector, and is used to decide whether to trigger the feedback path. The feedback path priority queue is a task list sorted according to the trigger signal strength, and is used to guide the data flow direction from the feedback trigger node to the version control node of the standard project task book.

[0148] In the embodiment of the present application, first, the real-time status parameters are compared with the preset threshold vector, and the statistical analysis method is used to calculate the trigger signal strength. Then, based on the trigger signal strength, a feedback path priority queue from the feedback trigger node to the version control node of the standard project task book is constructed. Then, by comparing the trigger signal strengths of different nodes, it is determined which nodes need to be processed preferentially. Finally, an ordered task list is formed to ensure that high-priority problems can be solved in a timely manner, thereby optimizing the execution process of the entire project.

[0149] 503. Locate the task level to be iterated in the work breakdown structure according to the cumulative signal strength of the feedback path priority queue, and extract the logical dependency strength and historical version difference features to generate a work breakdown difference matrix;

[0150] In step 503, the cumulative signal strength is the cumulative value of the trigger signal strength over a period of time, reflecting the severity and duration of the problem. The logical dependency strength describes the mutual dependency relationship between tasks at each level in the work breakdown structure. The historical version difference feature refers to the main change points or improvement points between the old and new versions. The work breakdown difference matrix is a dataset in matrix form, used to record and analyze the changes in the work breakdown structure between different versions.

[0151] In the embodiment of the present application, first, according to the cumulative signal strength of the feedback path priority queue, locate the task level to be iterated in the work breakdown structure. Then, extract the logical dependency strength and historical version difference features within this level to generate a work breakdown difference matrix. Then, use data analysis techniques to compare the differences between the old and new versions and find the parts that need to be adjusted. Finally, by integrating this information, clarify the specific content that needs to be updated, providing a detailed operation guide for the subsequent steps.

[0152] 504. Optimize and adjust the node connection rules in the work breakdown structure based on the work breakdown difference matrix, and trigger the version iteration of the standard project task book.

[0153] In step 504, the task decomposition difference matrix provides specific information about changes in the task decomposition structure to guide optimization and adjustment. The node connection rule refers to a set of rules that define the logical relationships and dependencies between tasks. By optimizing and adjusting the node connection rules in the task decomposition structure, version iteration of the standard project task book can be achieved to ensure that it always remains consistent with the actual project progress.

[0154] In the embodiments of the present application, first, based on the task decomposition difference matrix, analyze and determine the specific node connection rules that need to be optimized and adjusted. Then, use graph theory algorithms to re-plan the connection methods between tasks to ensure that the new connection rules can not only meet the current requirements but also maintain the stability of the overall structure. Next, update the relevant parts of the standard project task book to trigger version iteration. Finally, verify the effectiveness of the new version through the system to ensure that all adjustments meet the expected goals and can effectively improve the project management level.

[0155] The following is a specific example:

[0156] On a production line of a manufacturing enterprise, real-time data is collected by integrating sensors and cameras. Due to equipment failures, a certain process frequently stops, exceeding the preset tolerance. The system first identifies the feedback trigger nodes related to this process in the dynamic process topology structure, and extracts the resource consumption rate and task delay rate as real-time status parameters. Then, compare these parameters with the preset threshold vector and construct a feedback path priority queue based on this. The system locates the task level to be iterated in the task decomposition structure and generates a task decomposition difference matrix. Finally, based on this matrix, optimize and adjust the node connection rules in the task decomposition structure to trigger version iteration of the standard project task book, solve the problems brought by equipment failures, and improve the overall efficiency of the production line.

[0157] In summary, steps 501 to 504 achieve rapid response and precise management of abnormal situations during the execution of complex projects through real-time monitoring, data analysis, and dynamic adjustment. It not only improves the success rate and efficiency of the project but also enhances the flexibility and adaptability of the system, providing strong support for the enterprise to achieve more efficient operation and management. In particular, through the precise management of the feedback path and the version iteration mechanism, potential risks are greatly reduced, ensuring the smooth progress of the project.

[0158] To further improve the dynamic adjustment ability of the task breakdown structure and the accuracy of version iteration, the solution details the process of locating the task levels to be iterated based on the cumulative signal strength of the feedback path priority queue, including decomposing the cumulative signal strength into a time decay factor and a spatial distribution weight, traversing each level in the task breakdown structure, and generating a task breakdown difference matrix based on the logical dependency strength and historical version differences, thereby achieving accurate task level update and optimization. In some embodiments, in step 503, according to the cumulative signal strength of the feedback path priority queue, locate the task levels to be iterated in the task breakdown structure, extract the logical dependency strength and historical version difference features, and generate a task breakdown difference matrix, including:

[0159] 601. Decompose the cumulative signal strength of the feedback path priority queue into a time decay factor and a spatial distribution weight, generate a level positioning weight allocation matrix, traverse each task level in the task breakdown structure, and construct a logical dependency matrix based on the logical dependency strength;

[0160] In step 601, the time decay factor is used to measure the importance of the cumulative signal strength in different time periods, which gradually decreases over time. The spatial distribution weight represents the importance and influence range of each task level in the overall project. The level positioning weight allocation matrix is a matrix-form data set used to quantify the importance of each task level, and the logical dependency matrix constructed based on the logical dependency strength describes the mutual dependency relationship between tasks.

[0161] In the embodiments of the present application, first, decompose the cumulative signal strength of the feedback path priority queue into a time decay factor and a spatial distribution weight. Then, use the weighted average method to generate a level positioning weight allocation matrix. Next, traverse each task level in the task breakdown structure and construct a logical dependency matrix based on the logical dependency strength. Finally, by integrating this information, determine which task levels need to be prioritized for adjustment, providing basic data support for subsequent steps.

[0162] 602. Extract the change operation sequence and parameter offset of the task level nodes in the task breakdown structure of the historical version, map the change operation sequence to an operation type coding vector, and generate a level difference measurement tensor in combination with the parameter offset;

[0163] In step 602, the change operation sequence refers to the change operations of the task level nodes recorded in the task breakdown structure of the historical version, such as addition, deletion, or modification. The parameter offset is a value describing the change in parameter values before and after the change. The operation type coding vector is a form of converting various change operations into digital codes for easy computer processing. The level difference measurement tensor is a multi-dimensional array used to quantify the degree of difference between task levels.

[0164] In the embodiments of the present application, first, the change operation sequence and parameter offset of the task level nodes are extracted from the task decomposition structure of the historical version. Then, these change operation sequences are mapped to operation type encoding vectors, and a hierarchical difference metric tensor is generated in combination with the parameter offset. Next, data analysis techniques are used to compare the differences between the new and old versions to find the parts that need to be adjusted. Finally, a detailed hierarchical difference metric tensor is generated to provide specific operation guidelines for the subsequent steps.

[0165] 603. Perform a mode product operation on the logical dependency matrix and the hierarchical difference metric tensor to obtain the cross-hierarchical difference propagation feature, and perform a Hadamard association with the hierarchical positioning weight assignment matrix to generate the initial component of the task decomposition difference;

[0166] In step 603, the mode product operation refers to the multiplication operation between two high-order tensors, which is used to calculate the cross-hierarchical difference propagation feature. The Hadamard association is an element-wise multiplication operation, which is used to multiply two matrices of the same dimension. The initial component of the task decomposition difference is the preliminary result obtained through the above operations, which reflects the difference situation in the task decomposition structure.

[0167] In the embodiments of the present application, first, perform a mode product operation on the logical dependency matrix and the hierarchical difference metric tensor to obtain the cross-hierarchical difference propagation feature. Then, perform a Hadamard association of this feature with the hierarchical positioning weight assignment matrix to generate the initial component of the task decomposition difference. Next, use a mathematical model to analyze these initial components to find the key difference points. Finally, by integrating this information, clarify the specific content that needs to be updated to provide detailed operation preparations for the subsequent steps.

[0168] 604. Based on the sparse characteristics of the initial component, perform reverse gradient pruning on the task decomposition difference propagation feature, retain the difference components associated with the current feedback signal strength, and generate a task decomposition difference matrix.

[0169] In step 604, the sparse characteristic refers to the characteristic that most elements in the data set are zero. Reverse gradient pruning is an optimization algorithm used to remove unimportant difference components and retain the difference components associated with the current feedback signal strength. The task decomposition difference matrix is a finally generated result matrix that contains all the task decomposition difference information that needs to be adjusted.

[0170] In the embodiments of the present application, first, based on the sparse characteristics of the initial component, perform reverse gradient pruning on the task decomposition difference propagation feature to remove unimportant difference components. Then, retain the difference components associated with the current feedback signal strength. Next, adjust the remaining difference components through an optimization algorithm to ensure that they meet the actual requirements. Finally, generate a task decomposition difference matrix as the final adjustment basis to trigger the version iteration of the standard project task book.

[0171] The following is a specific example:

[0172] On the production line of a manufacturing enterprise, a certain process frequently stopped due to equipment failures, exceeding the preset tolerance. The system first decomposed the cumulative signal strength of the feedback path priority queue into a time decay factor and a spatial distribution weight, and constructed a logical dependency matrix. Then, it extracted the change operation sequence and parameter offset of the task-level nodes, and generated a hierarchical difference metric tensor. Next, it performed a modal product operation on the logical dependency matrix and the hierarchical difference metric tensor to generate the initial components of the task decomposition difference. Finally, it performed reverse gradient pruning on the task decomposition difference propagation characteristics to generate a task decomposition difference matrix, triggering the version iteration of the standard project task book, solving the problems brought by equipment failures, and improving the overall efficiency of the production line.

[0173] In summary, steps 601 to 604 improve the success rate and efficiency of the project by accurately identifying the differences in the task decomposition structure and making timely adjustments. It not only enhances the flexibility and adaptability of the system, but also reduces potential risks and ensures the smooth progress of the project. In particular, through the refined management and dynamic adjustment mechanism of task decomposition differences, the project management level has been greatly improved, providing strong support for the enterprise to achieve more efficient operation management.

[0174] To further improve the accuracy and flexibility of project management, this solution focuses on analyzing the temporal logic relationships in process data. By constructing a temporal directed graph structure and calculating the overlapping execution probability and resource conflict frequency on the critical path, a logical dependency strength matrix is generated. Combining the task node mapping alignment of the initial framework of the project task book, splitting the subgraph and adjusting the parallelism threshold, a standard project task book containing the task decomposition structure is finally generated to improve the rationality of project planning. In some embodiments, the step of parsing the temporal logic relationships in the process data in step 103 and generating a standard project task book containing the task decomposition structure in combination with the initial framework of the project task book includes:

[0175] 701. Parse the operation records of project execution nodes in the process data into a discrete event marker sequence, extract the temporal tightness parameter, and construct a temporal directed graph structure with the time stamp interval between event triggers as the edge weight;

[0176] In step 701, the discrete event marker sequence is a time series of key operation records extracted from the process data, used to identify changes in specific operations or states. The temporal tightness parameter measures the time interval between different events and reflects the compactness of event occurrence. The temporal directed graph structure is a graphical representation method, where nodes represent events, edges represent the temporal relationships between events, and the edge weights are calculated based on the time stamp interval between event triggers.

[0177] In the embodiments of the present application, first, the operation records of project execution nodes in process data are parsed into a discrete event tag sequence. Then, time series analysis techniques are used to extract the temporal tightness parameters, and a temporal directed graph structure with the time interval between event trigger timestamps as edge weights is constructed. Next, by analyzing these edge weights, the relative time order between events is determined. Finally, a directed graph structure that can accurately reflect the temporal relationship between events is formed, providing basic data support for subsequent steps.

[0178] 702. Traverse the critical path in the temporal directed graph structure, calculate the overlapping execution probability and resource preemption conflict frequency of event nodes on the critical path, and generate a logical dependency strength matrix between the event nodes;

[0179] In step 702, the critical path refers to a series of consecutive events that take the longest time from start to end, which determines the shortest completion time of the project. The overlapping execution probability represents the possibility that multiple events occur simultaneously within the same time period. The resource preemption conflict frequency describes the competition situation of different events for the same resource. The logical dependency strength matrix is a dataset in matrix form used to quantify the logical dependency relationship between event nodes.

[0180] In the embodiments of the present application, first traverse the critical path in the temporal directed graph structure, calculate the overlapping execution probability and resource preemption conflict frequency of event nodes on the critical path. Then, use statistical analysis methods to generate a logical dependency strength matrix. Next, by comparing the logical dependency strengths between different event nodes, identify the task nodes that need to be focused on. Finally, obtain a detailed logical dependency strength matrix, providing specific operation guidelines for subsequent steps.

[0181] 703. Map and align the task nodes in the initial framework of the project task book with the event nodes, perform subgraph segmentation on the task hierarchy based on the logical dependency strength matrix, and extract task node embedding vectors;

[0182] In step 703, map and align means matching the task nodes in the initial framework of the project task book with the event nodes to ensure the accuracy of the corresponding relationship between the two. Subgraph segmentation is a process of dividing the task hierarchy based on the logical dependency strength matrix, aiming to identify sets of tasks that are independent of each other but closely related. The task node embedding vector is to convert the task node into a vector representation in a high-dimensional space through a certain algorithm (such as deep learning) for further analysis.

[0183] In the embodiments of the present application, first, the task nodes in the initial framework of the project task book are mapped and aligned with the event nodes. Then, based on the logical dependency strength matrix, the task hierarchy is segmented into subgraphs, and the task node embedding vectors are extracted. Next, techniques such as graph neural networks are used to perform embedding representation on the task nodes to capture their inherent features. Finally, a set of embedding vectors that can accurately reflect the characteristics of the task nodes is formed, providing detailed information support for the subsequent steps.

[0184] 704. Generate an initial hierarchical connection rule according to the clustering center distribution of the task node embedding vectors and the overlapping execution probability between the subgraphs, and adjust the parallelism threshold in the initial hierarchical connection rule in combination with the dynamic offset in the time-sequential directed graph structure to generate a standard project task book including the task breakdown structure.

[0185] In step 704, the clustering center distribution describes the aggregation of the task node embedding vectors in the high-dimensional space, reflecting the similarity and difference between the task nodes. The overlapping execution probability refers to the possibility that different task nodes are executed simultaneously within the same time period. The parallelism threshold is a set value used to control the degree of parallel execution between the task nodes. The standard project task book is the final generated result document containing all the information of the task breakdown structure.

[0186] In the embodiments of the present application, first, an initial hierarchical connection rule is generated according to the clustering center distribution of the task node embedding vectors and the overlapping execution probability between the subgraphs. Then, the parallelism threshold in the initial hierarchical connection rule is adjusted in combination with the dynamic offset in the time-sequential directed graph structure. Next, an optimization algorithm is used to ensure a reasonable degree of parallel execution between the task nodes. Finally, a standard project task book including the task breakdown structure is generated to ensure that it is always consistent with the actual project progress.

[0187] The following is a specific example:

[0188] On the production line of a manufacturing enterprise, the system first parses the operation records of the project execution nodes in the process data into a discrete event tag sequence and constructs a time-sequential directed graph structure with the time interval between event trigger timestamps as the edge weight. Then, the overlapping execution probability of the event nodes on the critical path and the frequency of resource preemption conflicts are calculated to generate a logical dependency strength matrix. Next, based on the logical dependency strength matrix, the task hierarchy is segmented into subgraphs, and the task node embedding vectors are extracted. Finally, an initial hierarchical connection rule is generated, and in combination with the dynamic offset in the time-sequential directed graph structure, a standard project task book including the task breakdown structure is generated, improving the overall efficiency and management level of the production line.

[0189] In summary, steps 701 to 704 generate a detailed task breakdown structure by precisely analyzing the timing logic relationships during project execution and combining with the initial framework of the project task book, improving the success rate and efficiency of the project. It not only enhances the flexibility and adaptability of the system, but also reduces potential risks and ensures the smooth progress of the project. In particular, through the refined management and dynamic adjustment mechanism of task nodes, the management level of the project is greatly improved, providing strong support for the enterprise to achieve more efficient operation management.

[0190] Figure 2 FIG. provides a schematic structural diagram of a project intelligent management system based on enterprise digital information. As Figure 2 shown, the device includes:

[0191] An acquisition module 21 that acquires process data and dynamic image data generated in real time in an enterprise project, where the process data includes operation records of project execution nodes and the initial framework of the project task book;

[0192] An extraction module 22 that extracts human action trajectories and equipment operation states from the dynamic image data to generate an operation feature set including operation coherence parameters and abnormal action frequencies;

[0193] An analysis module 23 that analyzes the timing logic relationships in the process data and combines with the initial framework of the project task book to generate a standard project task book including a task breakdown structure;

[0194] A construction module 24 that matches the timing logic relationships with the operation feature set, constructs a project execution feature vector based on the task breakdown structure, and converts the project execution feature vector into a multi-dimensional management parameter including dynamic task priority weights according to resource allocation parameters and historical project evaluation indicators in enterprise digital information;

[0195] A generation module 25 that generates a dynamic process topology structure isomorphic to the standard project task book based on the multi-dimensional management parameter, and embeds a real-time feedback path in the dynamic process topology structure to trigger version iteration of the standard project task book.

[0196] Figure 2 The described project intelligent management system based on enterprise digital information can execute Figure 1 The described project intelligent management method based on enterprise digital information in the embodiments shown. Its implementation principle and technical effects will not be elaborated further. For the project intelligent management system based on enterprise digital information in the above embodiments, the specific ways for each module and unit to execute operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0197] In a possible design, Figure 2 An intelligent project management system based on enterprise digital information in the illustrated embodiment can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0198] The storage component 31 stores one or more computer instructions, where the one or more computer instructions are for the processing component 32 to call and execute.

[0199] The processing component 32 is used for the Figure 1 An intelligent project management method based on enterprise digital information in the illustrated embodiment.

[0200] Among them, the processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0201] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0202] Of course, the computing device may necessarily also include other components, such as an input / output interface, a display component, a communication component, etc.

[0203] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above peripheral interface module may be an output device, an input device, etc.

[0204] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0205] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above processing component, storage component, etc. may be basic server resources rented or purchased from the cloud computing platform.

[0206] The embodiments of the present application also provide a computer storage medium storing a computer program, and when the computer program is executed by a computer, the above-mentioned Figure 1 intelligent project management method based on enterprise digital information shown in the embodiments can be implemented.

[0207] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0208] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0209] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0210] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or equivalently replace some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A project intelligent management method based on enterprise digital information, characterized in that: include: Acquire process data and dynamic image data generated in real time in enterprise projects, wherein the process data includes operation records of project execution nodes and the initial framework of the project task book; Extracting the movement trajectory of personnel and the operation status of equipment from the dynamic image data, and generating an operation feature set including operation continuity parameters and abnormal movement frequency; Analyze the temporal logic relationship in the process data, and generate a standard project task book including a task breakdown structure in combination with the initial framework of the project task book; Matching the temporal logic relationship with the operation feature set, constructing a project execution feature vector based on the task decomposition structure, and converting the project execution feature vector into a multidimensional management parameter including dynamic task priority weights according to resource allocation parameters and historical project evaluation indicators in enterprise digital information; A dynamic process topology structure isomorphic to the standard project task book is generated based on the multi-dimensional management parameters, and a real-time feedback path is embedded in the dynamic process topology structure to trigger version iteration of the standard project task book.

2. The method according to claim 1, characterized in that The generating of a dynamic process topology structure isomorphic to the standard project task book based on the multi-dimensional management parameters includes: Binding the dynamic task priority weight and resource adaptation coefficient in the multi-dimensional management parameter to the node connection rule and resource channel capacity of the topological node respectively, wherein the node connection rule is associated with the task decomposition structure level in the standard project task book; Establishing an initial connection path of the topological nodes based on the task decomposition structure level, and dynamically allocating path bandwidth according to the resource channel capacity to form a basic topological framework; A state response mechanism is embedded in the basic topology framework, and when the operation record of the project execution node and the frequency of abnormal actions in the dynamic image data exceed a preset tolerance, the connection rule recalculation of the topology node is activated; Based on the connection direction between the time-series logic relationship constraints and the result of the recalculation of the connection rules, a dynamic process topology structure is generated that is isomorphic to the standard project task book.

3. The method according to claim 2, characterized in that When the operation record of the project execution node and the frequency of abnormal actions in the dynamic image data exceed the preset tolerance, activating the connection rule recalculation of the topological node includes: Acquire the operation records and dynamic image data of the project execution node in real time, extract the event marks in the operation records and the action trajectory features in the dynamic image data, and align and generate event and action joint feature vectors within the time sequence window; Calculate the projection distance between the abnormal action matching index and the preset abnormal pattern library based on the event and action joint feature vector, and trigger a recalculation instruction when the mean projection distance of the continuous windows exceeds the preset tolerance threshold; According to the recalculation instruction, the historical connection rules, resource channel capacity and node level constraints of the topological nodes are integrated to construct a dynamic optimization target algorithm, and the weight distribution matrix of the node connection rules is iteratively adjusted until the convergence condition is met; The adjusted weight distribution matrix is ​​updated to the connection rule engine of the topological node to activate the recalculation of the connection rules of the topological node.

4. The method according to claim 3, characterized in that The calculation of the projection distance between the abnormal action matching index and the preset abnormal pattern library based on the event and action joint feature vector, when the mean of the projection distances of the continuous windows exceeds the preset tolerance threshold, triggering a recalculation instruction, includes: Decomposing the event and action joint feature vector into event marker and action trajectory subspace, extracting the principal component features of the action trajectory subspace, and constructing a dynamic mapping matrix aligned with the dimension of a preset abnormal pattern library; Based on the dynamic mapping matrix, the event and action joint feature vector is projected to the implicit space of the preset abnormal pattern library, and the weighted Mahalanobis distance between the projected feature and the preset abnormal pattern library is calculated to generate a multi-dimensional projection distance sequence; The multi-dimensional projection distance sequence is subjected to sliding window interception, the extreme value distribution and covariance parameters of the window projection distance are extracted, and the sliding attenuation factor of the abnormal action matching index is obtained by aligning the window distribution characteristics through dynamic time warping; When the weighted mean of the sliding attenuation factors of the continuous windows exceeds a preset tolerance threshold, a recalculation instruction is triggered according to the extreme value distribution and the covariance parameter.

5. The method according to claim 1, characterized in that The method of embedding a real-time feedback path in the dynamic process topology structure to trigger version iteration of the standard project task book includes: Identifying, in the dynamic process topology structure, a feedback trigger node associated with a dynamic task priority weight in a multidimensional management parameter, and extracting a resource consumption rate and a task delay rate of the feedback trigger node as a real-time status parameter; Comparing the real-time status parameter with a preset threshold vector, generating a trigger signal strength of a feedback path, and constructing a feedback path priority queue from the feedback trigger node to the version control node of the standard project task book based on the trigger signal strength; According to the accumulated signal strength of the feedback path priority queue, the task level to be iterated is located in the task decomposition structure, and the logic dependency strength and historical version difference features are extracted to generate a task decomposition difference matrix; The node connection rules in the task decomposition structure are optimized and adjusted based on the task decomposition difference matrix, triggering a version iteration of the standard project task book.

6. The method according to claim 5, characterized in that According to the cumulative signal strength of the feedback path priority queue, the task level to be iterated is located in the task decomposition structure, and the logic dependency strength and historical version difference features are extracted to generate a task decomposition difference matrix, including: Decomposing the cumulative signal strength of the feedback path priority queue into a time attenuation factor and a spatial distribution weight, generating a hierarchical positioning weight allocation matrix, traversing each task level in the task decomposition structure, and constructing a logical dependency matrix based on the logical dependency strength; Extracting the change operation sequence and parameter offset of the task level node in the task decomposition structure of the historical version, mapping the change operation sequence into an operation type encoding vector, and generating a level difference metric tensor in combination with the parameter offset; Performing a modal product operation on the logic dependency matrix and the hierarchical difference metric tensor to obtain a cross-hierarchical difference propagation feature, and performing a Hadamard correlation with the hierarchical positioning weight allocation matrix to generate an initial component of the task decomposition difference; Based on the sparse characteristics of the initial components, reverse gradient pruning is performed on the task decomposition difference propagation features, the difference components associated with the current feedback signal strength are retained, and the task decomposition difference matrix is ​​generated.

7. The method according to claim 1, characterized in that The step of analyzing the temporal logic relationship in the process data and combining the initial framework of the project task book to generate a standard project task book containing a task breakdown structure includes: Parsing the project execution node operation records in the process data into discrete event tag sequences, extracting timing closeness parameters, and constructing a timing directed graph structure with event triggering timestamp intervals as edge weights; Traversing the critical path in the time-series directed graph structure, calculating the overlapping execution probability and resource preemption conflict frequency of event nodes on the critical path, and generating a logic dependency strength matrix between the event nodes; Mapping and aligning the task nodes and event nodes in the initial framework of the project task book, performing sub-graph segmentation on the task level based on the logic dependency strength matrix, and extracting task node embedding vectors; According to the cluster center distribution of the task node embedding vector and the overlapping execution probability between the subgraphs, an initial hierarchical connection rule is generated. Combined with the dynamic offset in the time-series directed graph structure, the parallelism threshold in the initial hierarchical connection rule is adjusted to generate a standard project task book containing a task decomposition structure.

8. A project intelligent management method based on enterprise digital information, characterized in that: include: An acquisition module, which acquires process data and dynamic image data generated in real time in enterprise projects, wherein the process data includes operation records of project execution nodes and an initial framework of a project task book; An extraction module extracts the movement trajectory of personnel and the operation status of equipment from the dynamic image data to generate an operation feature set including operation continuity parameters and abnormal movement frequency; A parsing module, which parses the temporal logic relationship in the process data and generates a standard project task book including a task breakdown structure in combination with the initial framework of the project task book; A construction module matches the temporal logic relationship with the operation feature set, constructs a project execution feature vector based on the task decomposition structure, and converts the project execution feature vector into a multidimensional management parameter including a dynamic task priority weight according to resource allocation parameters and historical project evaluation indicators in the enterprise digital information; A generation module generates a dynamic process topology structure isomorphic to the standard project task book based on the multi-dimensional management parameters, and embeds a real-time feedback path in the dynamic process topology structure to trigger version iteration of the standard project task book.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a project intelligent management method based on enterprise digital information as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, an intelligent project management method based on enterprise digital information as described in any one of claims 1 to 7 is implemented.

Images