A Cross-Departmental Collaboration Efficiency Dynamic Optimization System and Method

Abstract

The present invention discloses a dynamic optimization system and method for cross-departmental collaboration efficiency, which relates to the technical field of cross-departmental collaboration and includes the following steps: Based on the basic information of cross-departmental collaboration tasks, construct a task assignment network containing each task to comprehensively describe the structural characteristics and mutual dependencies of tasks during the collaboration process; During the operation of cross-departmental collaboration, set a fixed monitoring window for each task, and collect conflict data between the target task and other tasks in real time during the collaboration process to construct a conflict data analysis set; Based on the conflict data analysis set, extract the indicators where the target task has serious conflicts with other tasks. The present invention can realize the intelligent determination and classification of task conflicts, quickly optimize for mild conflicts, adaptively split subtasks for severe conflicts, relieve bottlenecks, improve the flexibility and collaboration efficiency of task scheduling, and ensure the efficient and stable operation of cross-departmental collaboration in a complex environment.

Description

Technical Field

[0001] The present invention relates to the technical field of cross - departmental collaboration, and particularly relates to a system and method for dynamically optimizing the efficiency of cross - departmental collaboration. Background Art

[0002] A system for dynamically optimizing the efficiency of cross - departmental collaboration is a comprehensive management system integrating information sharing, process collaboration, and intelligent optimization decision - making, aiming to solve problems such as poor communication, resource waste, and inconsistent goals that occur during the collaboration process among different departments within an enterprise or organization. Based on real - time collection and analysis of multi - dimensional data, the system dynamically senses the task progress, resource status, and collaboration bottlenecks of each department. Through process modeling, efficiency index evaluation, and intelligent optimization algorithms, it can adjust collaboration strategies and resource allocation in real - time to improve the overall collaboration efficiency. At the same time, the system supports information transparency, goal alignment, and intelligent early warning among different departments, and can automatically generate optimization plans when task conflicts, bottlenecks occur, or the external environment changes, ensuring the high - efficiency, flexibility, and sustainability of the collaboration process.

[0003] The prior art has the following deficiencies:

[0004] When dealing with task conflicts in cross - departmental collaboration, the prior art generally has insufficient optimization capabilities. Especially when there are serious conflicts (such as high resource dependence, overlapping time windows, and priority contradictions) between a key task and multiple related tasks, conventional optimization methods can only be processed based on static rules or simple priority adjustments, making it difficult to take into account the complex dependence relationships and global collaboration efficiency among tasks, easily leading to some tasks being forcibly postponed or resource allocation imbalance, thus affecting the overall collaboration efficiency and project execution stability, and it is difficult to meet the actual needs in complex collaboration scenarios with high dynamics and multiple constraints.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The object of the present invention is to provide a cross - departmental collaboration efficiency dynamic optimization system and method, which comprehensively depicts the structural characteristics and dependency relationships of cross - departmental collaboration tasks based on a task assignment network, combines real - time conflict data, and quantifies and intelligently determines the task conflict degree through a machine - learning model, achieving precise classification and hierarchical processing of mild and severe conflicts. For mild conflicts, the system can quickly generate a task optimization plan through an automatic optimization unit to improve collaboration flexibility and response speed; for severe conflicts, the system can adaptively divide and reconstruct the task into subtasks with controllable granularity based on the severity of the conflict, significantly alleviating the bottleneck problem caused by concentrated task conflicts, enhancing the flexibility of task scheduling and the optimization ability of global collaboration, thereby ensuring that cross - departmental collaboration can still operate efficiently and stably in a highly dynamic and multi - constraint complex environment to solve the problems in the above - mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solution: A cross - departmental collaboration efficiency dynamic optimization method, comprising the following steps:

[0008] Based on the basic information of cross - departmental collaboration tasks, construct a task assignment network containing each task, comprehensively describing the structural characteristics and mutual dependency relationships of tasks during collaboration;

[0009] During the operation of cross - departmental collaboration, set a fixed monitoring window for each task, and collect in real - time the conflict data between the target task and other tasks during collaboration to construct a conflict data analysis set;

[0010] Based on the conflict data analysis set, extract the indicators of severe conflict between the target task and other tasks. Within the fixed monitoring window, conduct in - depth analysis of the extracted indicators to form a conflict feature vector of the task, representing the conflict pressure of the target task in the entire task network;

[0011] Input the extracted conflict feature vector into a machine - learning model that has been pre - trained based on historical collaboration tasks using a supervised learning algorithm to evaluate the severity of the conflict of the target task and output the conflict degree score of the target task;

[0012] According to the conflict degree judgment result output by the machine - learning model, execute decision - branch processing: when the conflict degree between the target task and other tasks is mild, directly generate a collaboration optimization plan using an automatic optimization unit; when the conflict degree between the target task and other tasks is severe, that is, when there are high - degree couplings, resource - concentrated dependencies, or insoluble time conflicts between the task and multiple other tasks, divide the target task into multiple independently schedulable subtask units, reduce the dependence on the original conflict path to the greatest extent through fine - grained task splitting, and adaptively adjust the number of divided subtasks according to the severity of the conflict, and reduce the intensity of concentrated conflicts through decomposition to achieve efficient dynamic optimization of task collaboration.

[0013] Preferably, based on the basic information of cross-departmental collaboration tasks, a task assignment network including each task is constructed. The specific steps are as follows:

[0014] It is necessary to collect information such as the basic description, executor, required resources, expected duration, and priority of each task according to the business needs of each department and the project goals, and standardize this information;

[0015] After obtaining the basic information of each task, each task is defined as a node (Node) in the graph, a unique identifier is assigned to it, and key information such as the executor, resource requirements, and planned time of the task is recorded in the node attributes;

[0016] After the nodes are established, corresponding associated edges are established for the task nodes that need to interact or connect according to constraints such as the pre-post order, resource sharing, and time window conflicts;

[0017] After integrating all node and edge information, a complete task assignment network is formed, and possible redundancies or circular dependencies in the network are checked and corrected to ensure the usability and correctness of the network topology.

[0018] Preferably, indicators in which the target task has serious conflicts with other tasks are extracted from the conflict data analysis set. Among them, the extracted indicators include the longest path depth of the conflict dependence chain formed between the target task and other conflicting tasks and the intensity of the two-way dependence relationship and mutual conflict between the target task and other tasks. After in-depth analysis of the extracted indicators within a fixed monitoring window, a conflict chain depth reference value and a two-way conflict dependence reference value are generated respectively. A conflict feature vector of the task is formed through the conflict chain depth reference value and the two-way conflict dependence reference value, which characterizes the conflict pressure of the target task in the entire task network.

[0019] Preferably, the conflict feature vector composed of the conflict chain depth reference value and the two-way conflict dependence reference value is input into a machine learning model that has been pre-trained based on historical collaboration tasks. The conflict pressure coefficient is output through the machine learning model, and the conflict severity of the target task is intelligently evaluated based on the conflict pressure coefficient.

[0020] Preferably, the conflict pressure coefficient generated when evaluating the conflict severity of the target task through a machine learning model pre-trained based on historical collaboration tasks is compared and analyzed with a pre-set conflict pressure coefficient reference threshold to further divide the conflict degree of the target task. The specific division steps are as follows:

[0021] If the conflict pressure coefficient is greater than the conflict pressure coefficient reference threshold, the conflict degree between the target task and other tasks is classified as severe; if the conflict pressure coefficient is less than or equal to the conflict pressure coefficient reference threshold, the conflict degree between the target task and other tasks is classified as mild.

[0022] Preferably, when the target task is determined to be a severe conflict task, the target task is automatically split into subtasks, and according to the specific value of the conflict pressure coefficient, the splitting granularity, that is, the number of subtasks, is dynamically adjusted. The following subtask division formula is adopted: , where represents the final number of subtask divisions of the target task; is the basic number of subtask divisions, that is, the minimum number of divided tasks; is the conflict pressure coefficient of the target task; is the conflict pressure coefficient reference threshold set by the system; is the division granularity adjustment coefficient, which is used to control the influence of the conflict severity on the number of subtask divisions; is the conflict sensitivity index, which is used to control the non-linear enhancement of the division number with the increase of the conflict pressure; represents the ceiling operation to ensure that the division number is an integer.

[0023] Preferably, within a fixed monitoring window, the specific steps for generating the conflict chain depth reference value after in-depth analysis of the maximum path depth of the conflict dependence chain formed between the target task and other conflicting tasks are as follows:

[0024] Within a fixed monitoring window, starting from the target task, recursively search for all tasks in the task assignment network that have direct or indirect conflict relationships with it, and construct a conflict dependence chain graph of the target task. In the conflict dependence chain graph, define the length of each path as the number of nodes on that path, and take the length of the longest path as the maximum depth of the conflict dependence chain of the target task;

[0025] Based on the maximum depth of the conflict dependence chain of the target task, combined with the branch expansibility of the conflict chain, calculate the conflict chain depth reference value.

[0026] Preferably, within a fixed monitoring window, the specific steps for generating the two-way conflict dependence reference value after in-depth analysis of the strength of the two-way dependence relationship and mutual conflict between the target task and other tasks are as follows:

[0027] Within a fixed monitoring window, for the target task, first identify the task set with two-way dependence in the other task set. For each pair of two-way dependence relationships, calculate the dependence strength score of this pair of two-way dependence relationships, which represents the actual dependence tightness and conflict intensity between tasks;

[0028] Couple and superimpose the dependency strength scores of the target task with all its two-way dependent task pairs, and introduce a conflict diffusivity coefficient to form a two-way conflict dependency reference value of the target task, which is used to characterize its conflict pressure level in the entire task assignment network.

[0029] A dynamic optimization system for cross-departmental collaboration efficiency, including a task assignment network construction module, a conflict data monitoring and acquisition module, a conflict feature extraction and vectorization module, a conflict severity intelligent evaluation module, and a conflict classification optimization and task reconstruction module;

[0030] The task assignment network construction module constructs a task assignment network containing each task based on the basic information of cross-departmental collaboration tasks, comprehensively describing the structural characteristics and mutual dependencies of tasks during the collaboration process;

[0031] The conflict data monitoring and acquisition module sets a fixed monitoring window for each task during the operation of cross-departmental collaboration, and collects the conflict data between the target task and other tasks during the collaboration process in real time to construct a conflict data analysis set;

[0032] The conflict feature extraction and vectorization module extracts the indicators of serious conflicts between the target task and other tasks from the conflict data analysis set. After in-depth analysis of the extracted indicators within the fixed monitoring window, a conflict feature vector of the task is formed to characterize the conflict pressure of the target task in the entire task network;

[0033] The conflict severity intelligent evaluation module inputs the extracted conflict feature vector into a machine learning model that has been pre-trained using a supervised learning algorithm based on historical collaboration tasks, evaluates the conflict severity of the target task, and outputs the conflict degree score of the target task;

[0034] The conflict classification optimization and task reconstruction module executes decision branch processing based on the conflict degree judgment result output by the machine learning model: when the conflict degree between the target task and other tasks is mild, an automatic optimization unit is used to directly generate a collaboration optimization plan; when the conflict degree between the target task and other tasks is severe, the target task is divided into multiple independently schedulable subtask units, and the number of subtask divisions is adaptively adjusted according to the severity of the conflict.

[0035] In the above technical solution, the technical effects and advantages provided by the present invention:

[0036] Based on the task assignment network, the present invention comprehensively depicts the structural characteristics and dependency relationships of cross-departmental collaboration tasks. Combining real-time conflict data, through a machine learning model, it quantifies and intelligently determines the degree of task conflict, achieving precise classification and hierarchical processing of mild and severe conflicts. For mild conflicts, the system can quickly generate task optimization solutions through an automatic optimization unit, improving collaboration flexibility and response speed; while for severe conflicts, the system can adaptively divide and reconstruct tasks with controllable granularity based on the severity of the conflict, significantly alleviating the bottleneck problems caused by concentrated task conflicts, enhancing the flexibility of task scheduling and the optimization ability of global collaboration, thereby ensuring that cross-departmental collaboration can still operate efficiently and stably in a highly dynamic and multi-constrained complex environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] 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 in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0038] Figure 1 It is a method flow chart of a method for dynamically optimizing cross-departmental collaboration efficiency according to the present invention.

[0039] Figure 2 It is a module schematic diagram of a system for dynamically optimizing cross-departmental collaboration efficiency according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] Now, the exemplary embodiments will be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these exemplary embodiments are provided so that the present disclosure will be more complete and comprehensive, and will fully convey the concept of the exemplary embodiments to those skilled in the art.

[0041] The present invention provides a method for dynamically optimizing cross-departmental collaboration efficiency as shown in Figure 1 and includes the following steps:

[0042] Based on the basic information of cross-departmental collaboration tasks, construct a task assignment network including each task to comprehensively describe the structural characteristics and mutual dependency relationships of tasks during the collaboration process;

[0043] Step 1: Collect and organize the basic information of cross-departmental collaboration tasks;

[0044] First, it is necessary to collect information such as the basic description, executor, required resources, expected duration, and priority of each task according to the business needs of each department and the project goals, and standardize this information. Function: Laying a data foundation for subsequent graph structure modeling to ensure that the system has a full and accurate understanding of the core attributes and limiting conditions of each task.

[0045] Standardization processing refers to uniformly formatting and processing the information of each task collected to make it conform to certain standard specifications, facilitating subsequent system processing and analysis. Specifically, it includes:

[0046] Standardization of task descriptions: Unify the expression methods of task descriptions to ensure that information such as task names, types, and goals is clear and consistent.

[0047] Standardization of executors: Clearly define and unify the role definitions of task executors (such as departments, teams, individuals, etc.) to ensure clear task responsibility attribution.

[0048] Standardization of resource requirements: Uniformly classify and quantify the resources required for tasks (such as manpower, materials, equipment, etc.) for resource allocation and scheduling.

[0049] Standardization of expected duration: Use a unified unit to represent the expected completion time and duration of each task (such as days, hours, etc.) to ensure the consistency of time information.

[0050] Standardization of priorities: Uniformly define and label the priorities of tasks to ensure clear distinction of priorities among tasks.

[0051] Standardization processing can unify the format and expression methods of task information, eliminate information inconsistencies or ambiguities, facilitate efficient system processing and analysis, improve the accuracy and efficiency of task scheduling, and provide accurate and consistent input data for subsequent task assignment, resource optimization, and scheduling.

[0052] Step 2: Determine graph nodes and assign task identifiers;

[0053] After obtaining the basic information of each task, define each task as a node (Node) in the graph, assign it a unique identifier, and record key information such as the executor, resource requirements, and planned time of the task in the node attributes. Function: Through clear node representation, subsequent analysis and visualization of task relationships become more intuitive, facilitating the system to quickly retrieve and manage the tasks of each department.

[0054] Step 3: Clarify the dependencies between tasks and construct edges (Edge);

[0055] After the nodes are established, corresponding associated edges are established for the task nodes that need to interact or connect according to constraints such as the order of pre and post, resource sharing, and time window conflicts. For example, if task B needs to be started after task A is completed, a directed edge from A to B is set in the graph. Function: Through the establishment of these edges, the system can accurately present the hierarchical structure, resource competition relationship, and time mutual exclusion relationship between tasks, providing a basis for conflict identification and subsequent optimization.

[0056] Step 4: Generate and store the task allocation network and complete consistency verification;

[0057] After integrating all node and edge information, a complete task allocation network is formed, and redundant or circular dependencies that may exist in the network are checked and corrected to ensure the usability and correctness of the network topology. Function: In the final available network structure, all tasks of each department and their dependency relationships are clearly presented, providing high-quality basic support for subsequent functions such as conflict analysis, progress management, and dynamic scheduling.

[0058] Through graph modeling, the structural characteristics and mutual dependencies of tasks during the collaboration process can be comprehensively described, key constraints such as resource sharing, time window, and priority relationship between tasks can be clarified, providing structured basic information for subsequent conflict perception and optimization.

[0059] During the cross-departmental collaboration operation process, a fixed monitoring window is set for each task, and conflict data during the collaboration process between the target task and other tasks is collected in real time to construct a conflict data analysis set;

[0060] The fixed monitoring window refers to a task life cycle interval preset for each task during the cross-departmental collaboration process, which is used to continuously monitor the conflict situation between the target task and other tasks during the collaboration process. This fixed monitoring window usually corresponds to the planned execution cycle, key nodes, or dependency relationship time periods of the task, ensuring that conflict behavior data related to it (such as resource conflicts, time conflicts, dependency conflicts, etc.) can be collected in real time and completely during the key stages of the task. By setting a fixed monitoring window for the task, data redundancy and computational pressure caused by ineffective full-cycle monitoring can be avoided, and at the same time, the system is ensured to focus on collecting and analyzing conflict data during the time periods when task conflicts are most intensive and critical, providing accurate and effective conflict data support for subsequent quantification of conflict severity and optimization decisions.

[0061] Based on the conflict data analysis set, indicators of serious conflicts between the target task and other tasks are extracted. After in-depth analysis of the extracted indicators within the fixed monitoring window, a conflict feature vector of the task is formed, which characterizes the conflict pressure of the target task in the entire task network.

[0062] Extract the metrics where the target task has severe conflicts with other tasks from the conflict data analysis set. Among them, the extracted metrics include the maximum path depth of the conflict dependency chain formed between the target task and other conflicting tasks, and the intensity of the two-way dependency relationship and mutual conflict between the target task and other tasks. Within a fixed monitoring window, after in-depth analysis of the extracted metrics, generate the conflict chain depth reference value and the two-way conflict dependency reference value respectively. Form the conflict feature vector of the task through the conflict chain depth reference value and the two-way conflict dependency reference value, which characterizes the conflict pressure of the target task in the entire task network.

[0063] The deeper the maximum path depth of the conflict dependency chain formed between the target task and other conflicting tasks, the more severe the conflict of the target task usually indicates. This is because in cross-departmental collaboration, the conflict dependency chain reflects the conflict transmission relationship between the target task and other tasks in terms of time, resources, or logic. The deeper the path, it means that the conflict not only exists between directly adjacent tasks, but also spreads and superimposes in the task network through multiple levels and links, forming a cascading conflict effect. The spread of this conflict will cause more tasks to be affected in a chain reaction, resulting in a significant decline in the flexibility of resource scheduling, time arrangement, and task execution, and may even lead to the failure or paralysis of the local collaboration network. Compared with single or shallow-level conflicts, deep-path conflict chains are often difficult to alleviate through simple priority adjustments or resource reallocations. Therefore, the path depth of the conflict dependency chain is an important implicit indicator for measuring the severity of task conflicts and has significant engineering guiding value.

[0064] The specific steps for generating the conflict chain depth reference value after in-depth analysis of the maximum path depth of the conflict dependency chain formed between the target task and other conflicting tasks within a fixed monitoring window are as follows:

[0065] Within a fixed monitoring window, starting from the target task, recursively search for all tasks in the task assignment network that have direct or indirect conflict relationships with it, and construct the conflict dependency chain graph of the target task. In the conflict dependency chain graph, the set of all paths from the target task to other conflicting tasks is denoted as where each path represents the conduction link of the conflict, represents the total number of conflict dependency chains formed by the target task within the fixed monitoring window. Define the length of each path as the number of nodes (tasks) on that path, and take the length of the longest path as the maximum depth of the target task conflict dependency chain. Then the expression for the maximum depth of the target task conflict dependency chain is:

[0066] where: is the number of nodes of path i.e., the path length, is the maximum depth of the target task conflict dependency chain;

[0067] In this step, by means of dependency chain modeling and the extraction of the deepest conflict chain, the "depth range" affected by conflicts of the target task in the collaborative task network is accurately identified, providing a basis for subsequent quantification.

[0068] Based on the maximum depth of the conflict dependency chain of the target task , and further combining with the branch expansion property of the conflict chain (i.e., the expansion speed of the conflict branch during propagation), the conflict chain depth reference value is calculated, and the calculation formula is:

[0069] , where: is the conflict chain depth reference value of the target task, is the conflict branch expansion coefficient, representing the average branch factor of the conflict dependency chain starting from the target task during propagation, calculated as the average number of branches of all non-leaf nodes in the conflict chain, is the conflict sensitivity coefficient, controlling the contribution degree of branch expansion, and its value can be set according to the system scale or the design experience of the scheduler (such as );

[0070] The average number of branches of non-leaf nodes refers to the sum of the actual branch numbers of all task nodes with downstream branches (i.e., having one or more subtasks) in the conflict dependency chain of the target task, divided by the total number of these nodes, and the obtained average value is used to describe the diffusion speed and branch density of the conflict chain during propagation.

[0071] This conflict chain depth reference value not only considers the propagation depth of the conflict chain (the deeper, the wider the influence range), but also introduces the branch expansion property. That is, if a conflict dependency chain shows multi-branch diffusion (non-linear propagation) during propagation, the conflict chain depth reference value will be further amplified, truly reflecting the conflict diffusion pressure of this task and the conflict load within the task network.

[0072] It can be seen from the conflict chain depth reference value that within a fixed monitoring window, the larger the performance value of the conflict chain depth reference value generated after in-depth analysis of the longest path depth of the conflict dependence chain formed between the target task and other conflicting tasks, the more serious the conflict between the target task and other tasks. The reason is that this conflict chain depth reference value comprehensively reflects two core factors: one is the depth of the conflict dependence chain (that is, the more layers the conflict impact spreads in the task network, the longer the task path involved, and the larger the conflict diffusion range); the other is the branch expansibility of the conflict (that is, the more branches the conflict has during the propagation process, the faster it spreads, and the more complex the formed conflict network structure). When the conflict chain depth reference value is larger, it indicates that the conflict of the target task is not only limited to the local area, but also transmitted to more downstream tasks in terms of time, resources or dependencies, forming a multi-level and multi-branch conflict link, resulting in a sharp increase in the complexity and coordination difficulty faced by task scheduling, resource allocation and collaboration arrangement, seriously affecting the overall executability and stability of the collaboration system; on the contrary, if the conflict chain depth reference value is smaller, it indicates that the conflicts are mostly small-scale conflicts at a shallow level and within a local range, and are easy to alleviate through conventional task rearrangement or resource fine-tuning.

[0073] The higher the intensity of the two-way dependence relationship and the mutual conflict between the target task and other tasks, usually the more serious the conflict between the target task and other tasks. The essential reason is that the two-way dependence relationship itself will form a highly coupled mutual restraint effect. When two or more tasks are mutually dependent (that is, A depends on the result of B, and B depends on the resources or progress of A), it will form a closed loop or two-way deadlock phenomenon in terms of resources, time and task flow. At this time, even if the system tries to optimize through simple priority adjustment or resource allocation, it often cannot break this mutual restraint relationship, resulting in severely limited optimization space and being prone to local deadlocks or system-level bottlenecks. Therefore, the two-way dependence conflict not only increases the severity and complexity of the conflict, but also directly exacerbates the difficulty of task scheduling and collaboration optimization, belonging to a high-risk conflict structure in the collaboration network.

[0074] Within a fixed monitoring window, the specific steps for generating the two-way conflict dependence reference value after in-depth analysis of the intensity of the two-way dependence relationship and the mutual conflict between the target task and other tasks are as follows:

[0075] Within a fixed monitoring window, for the target task , first identify the task set with two-way dependence in its set of other tasks, and denote this task set as , , that is, the task set that the target task mutually depends on, represents the task with two-way dependence on the target task . For each pair of two-way dependence relationships , calculate the dependency strength score of this pair of two-way dependencies , which represents the actual dependency tightness and conflict intensity between tasks. The calculation formula is:

[0076] , where: is the resource interaction degree, representing the number of resource types shared between task and task ; is the dependency coupling degree, representing the strength of the dependency relationship between task and task , which can be represented by the reciprocal of the dependency path length (the shorter the dependency, the stronger the coupling); is the buffer margin, representing the adjustable buffer duration in time between task and task . The less buffer, the more serious the conflict;

[0077] The dependency path length refers to the number of task nodes passed through by the connection of dependency relationships from the target task to its dependent tasks in the task assignment network, that is, it represents the number of task levels spanned by the shortest dependency chain between two tasks. The shorter the path, the closer the dependency relationship between the two and the higher the coupling degree.

[0078] The adjustable buffer duration refers to the flexible adjustment time margin between the target task and its dependent tasks without affecting the overall project progress or task dependency relationship, that is, the available idle time window that can be freely allocated and optimized by the scheduler between the two in time.

[0079] This step models the conflict intensity between the target task and each pair of its two-way dependent tasks to form a basic strength score, which is used to measure the severity of the two-way conflict between a single pair of tasks.

[0080] Coupling and superimposing the dependency strength scores of the target task T with all pairs of its two-way dependent tasks, and introducing the conflict diffusivity coefficient, a two-way conflict dependency reference value of the target task is formed, which is used to characterize its conflict pressure level in the entire task assignment network. The generation formula of the two-way conflict dependency reference value is: , where: is the two-way conflict dependency reference value, is the conflict diffusivity coefficient, representing the influence factor of the conflict of the target task spreading in the task network (which can be represented by the product of the out-degree and in-degree of the target task in the network, reflecting the ease of conflict propagation of this task), is the conflict sensitivity amplification index (generally greater than 1), which is used to emphasize the influence of high-intensity conflicts and non-linearly enhance the contribution of conflict severity to the index;

[0081] The out-degree and in-degree of the target task in the network can be directly obtained by analyzing the number of dependency edges starting from this task (out-degree) and the number of dependency edges ending at this task (in-degree) in the task assignment network, which respectively represent the number of downstream tasks that this task depends on and the number of upstream tasks that depend on this task.

[0082] This step generates the global conflict pressure index of the target task by coupling and aggregating the intensities of multiple bidirectional conflict pairs and combining the diffusion ability of conflicts in the network. , reflecting its conflict centrality and potential influence in the collaborative task network.

[0083] As can be seen from the bidirectional conflict dependency reference value, within a fixed monitoring window, the larger the performance value of the bidirectional conflict dependency reference value generated after in-depth analysis of the intensity of the bidirectional dependency relationship and mutual conflict between the target task and other tasks does indeed indicate that the conflict between the target task and other tasks is more serious, and vice versa, the less serious the conflict. The reason is that this bidirectional conflict dependency reference value comprehensively reflects the resource competition degree, dependency coupling degree, insufficient buffer margin, and conflict diffusion ability between the target task and other tasks in terms of structure by accumulating and non-linearly amplifying the dependency strength scores between the target task and all bidirectional dependency tasks. When the bidirectional conflict dependency reference value is larger, it means that the target task not only forms a tight and difficult-to-alleviate bidirectional dependency with multiple tasks, but also the conflict shows high intensity and high propagation in terms of time, resources, and network structure, resulting in this task becoming a serious conflict center in the collaborative network; on the contrary, if the bidirectional conflict dependency reference value is relatively small, it means that although there may be a dependency relationship for this task, the conflict degree, influence range, or buffer ability is relatively controllable, and the threat of the conflict to the overall collaboration is low. Therefore, the bidirectional conflict dependency reference value can effectively serve as a criterion for measuring the severity of the conflict.

[0084] Input the extracted conflict feature vector into a machine learning model that has been pre-trained based on historical collaborative tasks using a supervised learning algorithm to evaluate the conflict severity of the target task and output the conflict degree score of this target task;

[0085] Input the conflict feature vector composed of the conflict chain depth reference value and the bidirectional conflict dependency reference value into a machine learning model that has been pre-trained based on historical collaborative tasks. Output the conflict pressure coefficient through the machine learning model, and conduct an intelligent evaluation of the conflict severity of the target task based on the conflict pressure coefficient.

[0086] In the cross - departmental collaboration conflict optimization method, the machine - learning model pre - trained based on historical collaboration tasks refers to, before system deployment or actual operation, using a large amount of historical project or collaboration task data as training samples to perform supervised or semi - supervised learning on the conflict severity assessment model, enabling it to have the ability to identify and quantify the relationship between conflict characteristics and conflict pressure among different tasks. Specifically, the system first extracts the structural attributes of each task (such as task dependency level, department to which it belongs, resource allocation situation, etc.), conflict records (such as resource contention events, task delay frequency, actual coordination times, etc.), and the final execution results of the tasks (such as whether there is a delay, whether it triggers downstream chain problems, the cost of conflict coordination, etc.) from the historical cross - departmental projects that have been executed, as the basic training data set. On this data set, the system constructs corresponding conflict feature vectors in combination with key conflict characteristics such as the depth reference value of the conflict chain and the two - way conflict dependency reference value of the task, and uses these vectors as model inputs. At the same time, the "severity of conflict consequences" in the task execution results is used as a label or output target. For example, quantitative indicators such as conflict consequence severity scores, conflict handling costs, or conflict propagation scopes are used as supervision signals. Through model training, the machine - learning system can learn to automatically identify in complex, high - dimensional conflict scenarios which feature combinations often correspond to high conflict pressure and which combinations can usually be quickly coordinated, and then form an intelligent assessment model that can be generally applied to new task conflict judgments.

[0087] This model can be trained using a variety of machine - learning methods, including but not limited to: Random Forest, Gradient Boosting Decision Trees (such as XGBoost), Support Vector Machines (SVM), Graph Neural Networks (GNN, for processing task - dependency network graphs), or Multi - Layer Perceptron Neural Networks (MLP). In particular, since there are usually graph - structure characteristics among collaboration tasks and the task - dependency relationship naturally forms a directed graph, using a graph neural network can better capture the structural conflict characteristics among tasks, such as conflict - chain propagation paths and node - centrality impacts. After the model training is completed, its parameters are fixed and it can be called in real - time as a runtime model. During the operation of cross - departmental collaboration tasks, the system only needs to extract the conflict feature vector of the current target task (such as the depth reference value of the conflict chain and the two - way conflict dependency reference value of the current task), and use it as input to pass into this trained machine - learning model, then it can predict in real - time a conflict pressure coefficient, which is a continuous or graded value, reflecting the conflict pressure level of the current task in the system. The introduction of this machine - learning model breaks through the technical bottlenecks of inaccurate classification and inflexible processing of conflict tasks by traditional static rule judgments or single - priority strategies, and realizes the intelligent identification and optimization decision - making ability for conflict characteristics in cross - departmental collaboration.

[0088] The deep learning model is not specifically limited herein, as long as it can implement the comprehensive analysis of the conflict chain depth reference value and the bidirectional conflict dependence reference value to generate a conflict pressure coefficient Any deep learning model can be used. To implement the technical solution of the present invention, the present invention provides a specific implementation method; the expression for generating the conflict pressure coefficient is: , where in the formula, , are respectively the preset proportionality coefficients of the conflict chain depth reference value and the bidirectional conflict dependence reference value of the target task, and , are both greater than 0. The preset proportionality coefficient refers to the weight coefficient set by the system artificially or based on experience for each conflict feature index (such as the conflict chain depth reference value and the bidirectional conflict dependence reference value ) when calculating the conflict pressure coefficient, that is, and . Since different indicators contribute differently to the conflict pressure, in order to reasonably reflect the importance of each feature when comprehensively calculating the conflict pressure, the system needs to pre-allocate corresponding proportionality coefficients to each feature during the modeling stage. For example, when experience or historical data shows that the conflict chain depth has a relatively greater impact on the conflict pressure, a larger value can be assigned to ; if the bidirectional conflict dependence can better reflect the actual conflict propagation ability, a higher weight is assigned to . The role of the preset proportionality coefficient is to regulate the contribution ratio of each conflict feature in the calculation of the conflict pressure coefficient, so that the finally calculated conflict pressure coefficient better meets the requirements for judging the severity of conflicts in the actual business scenario. In practical applications, , can be obtained through domain expert experience, data analysis or machine learning optimization.

[0089] It can be seen from the conflict pressure coefficient that within a fixed monitoring window, the larger the value of the conflict chain depth reference value generated by in-depth analysis of the longest path depth of the conflict dependence chain formed between the target task and other conflict tasks, and the larger the value of the bidirectional conflict dependence reference value generated by in-depth analysis of the intensity of the bidirectional dependence relationship and mutual conflict between the target task and other tasks, that is, the larger the value of the conflict pressure coefficient generated when evaluating the severity of the conflict of the target task through a machine learning model pre-trained based on historical collaboration tasks, the more serious the conflict between the target task and other tasks, and vice versa, it indicates that the conflict between the target task and other tasks is less serious.

[0090] When evaluating the severity of conflicts in a target task using a machine learning model pre-trained based on historical collaborative tasks, compare the generated conflict pressure coefficient with a pre-set reference threshold for the conflict pressure coefficient, and further classify the degree of conflict in the target task. The specific classification steps are as follows:

[0091] If the conflict pressure coefficient is greater than the reference threshold for the conflict pressure coefficient, classify the degree of conflict between the target task and other tasks as severe; if the conflict pressure coefficient is less than or equal to the reference threshold for the conflict pressure coefficient, classify the degree of conflict between the target task and other tasks as mild.

[0092] Based on the conflict degree judgment result output by the machine learning model, perform decision branch processing: when the degree of conflict between the target task and other tasks is mild, use an automatic optimization unit (such as task order rearrangement, resource priority allocation, buffer period adjustment, etc.) to directly generate a collaborative optimization plan; when the degree of conflict between the target task and other tasks is severe, that is, when there are high couplings, resource concentration dependencies, or insoluble time conflicts between the task and multiple other tasks, divide the target task into multiple independently schedulable subtask units, reduce the dependence on the original conflict path to the greatest extent through task fine-grained splitting, and adaptively adjust the number of subtask divisions according to the severity of the conflict, and reduce the concentrated conflict intensity through disassembly to achieve efficient dynamic optimization of task collaboration;

[0093] When the degree of conflict between the target task and other tasks is mild, it indicates that although there are certain conflict phenomena such as resource contention, time overlap, or tense dependency relationships during the collaboration process, the scope and intensity of its conflicts are small and not sufficient to seriously impede the overall collaboration process. In this case, the system does not need to perform complex structural adjustments or splits on the task, but through an automatic optimization unit, based on the scheduling information of the current task and its related tasks, intelligently adopts common optimization means such as task order rearrangement, resource priority allocation, and buffer period adjustment. Task order rearrangement means adjusting the execution order of tasks to relieve resource or time conflicts without violating the front-back dependency relationship; resource priority allocation means preferentially allocating idle or low-load resources to tasks with mild conflicts to reduce the risk of contention; buffer period adjustment means appropriately extending or shortening the execution buffer time of tasks to increase scheduling flexibility. Through the combined application of the above optimization strategies, the mild conflict problem can be quickly and low-costly solved, enabling the task to smoothly integrate into the collaboration plan without introducing major structural changes and ensuring the smooth progress of cross-departmental collaboration.

[0094] The partitioning process takes into account the logical divisibility, resource independence, and time parallelism within the task. This means that when dividing a target task with severe conflicts into multiple subtasks, the system needs to comprehensively analyze the internal structural characteristics of the task to ensure that the divided subtasks have relatively independent and schedulable capabilities. Logical divisibility refers to whether the task itself can be decomposed into several subtasks with clear functional or phase divisions, and each subtask can jointly meet the goals of the original task after completion; resource independence means that during the execution of subtasks, it is necessary to avoid continued dependence on the same batch of limited or tense key resources as much as possible, thereby reducing secondary conflicts caused by resource contention; time parallelism refers to whether there is a possibility of parallel or partially overlapping execution between the divided subtasks, so as to improve the overall scheduling freedom through flexible time scheduling. By comprehensively considering these three elements, it is possible to reasonably refine the structure of the original task while ensuring the quality of task completion, making the divided subtasks easier to be independently optimized and scheduled in the collaboration network, and effectively reducing the local bottlenecks and global collaboration pressure brought by severe conflicts.

[0095] When the target task is determined to be a severely conflicting task, the target task is automatically split into subtasks, and the splitting granularity (i.e., the number of subtasks) is dynamically adjusted according to the specific value of the conflict pressure coefficient. The following subtask partitioning formula is used: , where represents the final number of subtask partitions of the target task; is the basic number of subtask partitions, that is, the minimum number of partition tasks (for example, it can be initially set to 2 - 3); is the conflict pressure coefficient of the target task; is the reference threshold of the conflict pressure coefficient set by the system; is the partitioning granularity adjustment coefficient (positive value), which is used to control the impact of the conflict severity on the number of subtask partitions. When the conflict is more severe, this partitioning granularity adjustment coefficient can increase the sensitivity of the increase in the number of subtasks, thereby achieving an adaptive enhancement of the task partitioning granularity; is the conflict sensitivity index (greater than 1), which is used to control the non-linear increase in the number of partitions as the conflict pressure rises; represents the ceiling operation to ensure that the number of partitions is an integer;

[0096] Through the above adaptive partitioning mechanism, it can be ensured that when the conflict pressure coefficient is only slightly higher than the reference threshold of the conflict pressure coefficient, the number of task partitions is close to the basic number of partitions ; When the conflict pressure coefficient is much higher than the reference threshold of the conflict pressure coefficient, the number of subtask divisions increases significantly, achieving refined splitting under high conflict intensity. This step can convert the severe conflict pressure into multiple independently schedulable subtasks with low conflicts, reduce the local bottleneck effect, and at the same time form higher scheduling flexibility and optimizability in the task assignment network, providing a good structural foundation for subsequent resource allocation and schedule coordination.

[0097] Through the above solution, it is possible to effectively solve the problem of insufficient optimization ability in the prior art when facing serious conflicts between key tasks and multiple associated tasks. Specifically, it is reflected in that the system can comprehensively characterize the structural characteristics and dependency relationships of cross-departmental collaborative tasks based on the task assignment network, combine real-time conflict data, and quantitatively and intelligently determine the degree of task conflict through a machine learning model, realizing accurate classification and hierarchical processing of mild and severe conflicts. For mild conflicts, the system can quickly generate a task optimization plan through the automatic optimization unit to improve collaboration flexibility and response speed; for severe conflicts, the system can adaptively divide and reconstruct tasks with controllable granularity based on the severity of the conflict, significantly alleviating the bottleneck problem caused by concentrated task conflicts, and improving the flexibility of task scheduling and the optimization ability of global collaboration, thereby ensuring that cross-departmental collaboration can still operate efficiently and stably in a highly dynamic and multi-constrained complex environment.

[0098] The present invention provides a Figure 2 cross-departmental collaboration efficiency dynamic optimization system as shown, including a task assignment network construction module, a conflict data monitoring and acquisition module, a conflict feature extraction and vectorization module, a conflict severity intelligent evaluation module, and a conflict classification optimization and task reconstruction module;

[0099] The task assignment network construction module constructs a task assignment network including each task based on the basic information of cross-departmental collaborative tasks, comprehensively describing the structural characteristics and mutual dependencies of tasks during the collaboration process;

[0100] The conflict data monitoring and acquisition module sets a fixed monitoring window for each task during the operation of cross-departmental collaboration, and collects conflict data between the target task and other tasks during the collaboration process in real time to construct a conflict data analysis set;

[0101] The conflict feature extraction and vectorization module extracts the indicators of serious conflicts between the target task and other tasks from the conflict data analysis set, and after in-depth analysis of the extracted indicators within the fixed monitoring window, forms a conflict feature vector of the task, characterizing the conflict pressure of the target task in the entire task network;

[0102] The conflict severity intelligent evaluation module inputs the extracted conflict feature vectors into a machine learning model that has been pre-trained using a supervised learning algorithm based on historical collaboration tasks, evaluates the conflict severity of the target task, and outputs the conflict degree score of the target task;

[0103] The conflict classification optimization and task reconstruction module performs decision branch processing based on the conflict degree judgment result output by the machine learning model: when the conflict degree between the target task and other tasks is mild, the automatic optimization unit directly generates a collaboration optimization plan; when the conflict degree between the target task and other tasks is severe, the target task is divided into multiple independently schedulable subtask units, and the number of subtask divisions is adaptively adjusted according to the severity of the conflict.

[0104] The dynamic optimization method for cross-departmental collaboration efficiency provided by the embodiments of the present invention is implemented through the above-mentioned cross-departmental collaboration efficiency dynamic optimization system. The specific methods and processes of the cross-departmental collaboration efficiency dynamic optimization system are described in detail in the embodiments of the above-mentioned cross-departmental collaboration efficiency dynamic optimization method, and will not be elaborated here.

[0105] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0106] Only some exemplary embodiments of the present invention have been described by way of illustration above. Undoubtedly, for those of ordinary skill in the art, without departing from the spirit and scope of the present invention, the described embodiments can be modified in various different ways. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the protection scope of the claims of the present invention.

[0107] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A dynamic optimization method for cross - departmental collaboration efficiency, characterized in that It includes the following steps: Based on the basic information of cross-departmental collaboration tasks, construct a task assignment network containing each task, comprehensively describing the structural characteristics and interdependencies of tasks during the collaboration process; During the operation of cross-departmental collaboration, set a fixed monitoring window for each task, and collect conflict data between the target task and other tasks in real time during the collaboration process to construct a conflict data analysis set; Based on the conflict data analysis set, extract the indicators where the target task has serious conflicts with other tasks. Within the fixed monitoring window, after in-depth analysis of the extracted indicators, form a conflict feature vector of the task, which characterizes the conflict pressure of the target task in the entire task network; Input the extracted conflict feature vector into a machine learning model that has been pre-trained based on historical collaboration tasks to evaluate the severity of the conflict of the target task, and output the conflict degree score of the target task; According to the conflict degree judgment result output by the machine learning model, execute decision branch processing: when the conflict degree between the target task and other tasks is mild, use the automatic optimization unit to directly generate a collaboration optimization plan; When the conflict degree between the target task and other tasks is severe, divide the target task into multiple independently schedulable subtask units, and adaptively adjust the number of subtask divisions according to the severity of the conflict; Extract the indicators where the target task has serious conflicts with other tasks from the conflict data analysis set. Among them, the extracted indicators include the longest path depth of the conflict dependency chain formed between the target task and other conflicting tasks, and the intensity of the two-way dependency relationship and mutual conflict between the target task and other tasks. Within the fixed monitoring window, after in-depth analysis of the extracted indicators, generate a conflict chain depth reference value and a two-way conflict dependency reference value respectively, and form a conflict feature vector of the task through the conflict chain depth reference value and the two-way conflict dependency reference value, which characterizes the conflict pressure of the target task in the entire task network; Input the conflict feature vector composed of the conflict chain depth reference value and the two-way conflict dependency reference value into a machine learning model that has been pre-trained based on historical collaboration tasks, output the conflict pressure coefficient through the machine learning model, and conduct an intelligent evaluation of the severity of the conflict of the target task based on the conflict pressure coefficient; When the target task is determined to be a severely conflicting task, automatically split the target task into subtasks, and dynamically adjust the splitting granularity, that is, the number of subtasks, according to the specific value of the conflict pressure coefficient. The following subtask division formula is adopted: , where represents the final number of subtask divisions for the target task; is the basic number of subtask divisions, i.e., the minimum number of division tasks; is the conflict pressure coefficient of the target task; is the reference threshold of the conflict pressure coefficient set by the system; is the division granularity adjustment coefficient, used to control the impact of the conflict severity on the number of subtask divisions; is the conflict sensitivity index, used to control the non-linear enhancement of the division number with the increase of the conflict pressure; represents the ceiling operation to ensure that the division number is an integer.

2. The dynamic optimization method for cross - departmental collaboration efficiency according to claim 1, wherein Based on the basic information of cross-departmental collaboration tasks, construct a task assignment network containing each task. The specific steps are as follows: It is necessary to collect the basic information of each task according to the business needs and project goals of each department, and standardize the information; After obtaining the basic information of each task, define each task as a node in the graph, assign a unique identifier to it, and record the key information of the task in the node attributes; After the nodes are established, according to the constraint conditions, establish corresponding association edges for the task nodes that need to interact or connect; After integrating all node and edge information, a complete task assignment network is formed, and redundant or circular dependencies in the network are checked and corrected.

3. The dynamic optimization method for cross - departmental collaboration efficiency according to claim 1, wherein When evaluating the conflict severity of the target task by a machine learning model pre-trained based on historical collaborative tasks, the conflict pressure coefficient generated is compared with a pre-set reference threshold of the conflict pressure coefficient, and the conflict degree of the target task is further divided. The specific division steps are as follows: If the conflict pressure coefficient is greater than the reference threshold of the conflict pressure coefficient, the conflict degree between the target task and other tasks is classified as severe; if the conflict pressure coefficient is less than or equal to the reference threshold of the conflict pressure coefficient, the conflict degree between the target task and other tasks is classified as mild.

4. A dynamic optimization method for cross - departmental collaboration efficiency according to claim 1, characterized in that, The specific steps for generating a conflict chain depth reference value by deeply analyzing the maximum path depth of the conflict dependency chain formed between the target task and other conflicting tasks within a fixed monitoring window are as follows: Within a fixed monitoring window, starting from the target task, recursively search in the task assignment network for all tasks that have direct or indirect conflict relationships with it, and construct a conflict dependency chain graph of the target task. In the conflict dependency chain graph, define the length of each path as the number of nodes on that path, and take the length of the longest path as the maximum depth of the conflict dependency chain of the target task; Based on the maximum depth of the conflict dependency chain of the target task, combined with the branch expansion of the conflict chain, calculate the conflict chain depth reference value.

5. A dynamic optimization method for cross - departmental collaboration efficiency according to claim 1, characterized in that, The specific steps for generating a two-way conflict dependency reference value by deeply analyzing the intensity of the two-way dependency relationship and mutual conflict between the target task and other tasks within a fixed monitoring window are as follows: Within a fixed monitoring window, for the target task, first identify the task set with two-way dependencies in other task sets. For each pair of two-way dependency relationships, calculate the dependency strength score of this pair of two-way dependency relationships, which represents the actual dependency tightness and conflict intensity between tasks; Couple and superimpose the dependency strength scores of the target task and all its two-way dependency task pairs, and introduce a conflict diffusion coefficient to form a two-way conflict dependency reference value of the target task, which is used to characterize its conflict pressure level in the entire task assignment network.

6. A cross - departmental collaboration efficiency dynamic optimization system for implementing the cross - departmental collaboration efficiency dynamic optimization method described in any one of claims 1 - 5 above, characterized in that, It includes a task assignment network construction module, a conflict data monitoring and acquisition module, a conflict feature extraction and vectorization module, a conflict severity intelligent evaluation module, and a conflict classification optimization and task reconstruction module; The task assignment network construction module constructs a task assignment network containing each task based on the basic information of cross-departmental collaborative tasks, comprehensively describing the structural characteristics and mutual dependency relationships of tasks during the collaboration process; The conflict data monitoring and acquisition module sets a fixed monitoring window for each task during the cross-departmental collaborative operation, and real-time collects the conflict data between the target task and other tasks during the collaboration process to construct a conflict data analysis set; The conflict feature extraction and vectorization module extracts the indicators of serious conflicts between the target task and other tasks based on the conflict data analysis set. Within a fixed monitoring window, after deeply analyzing the extracted indicators, a conflict feature vector of the task is formed to characterize the conflict pressure of the target task in the entire task network; The intelligent conflict severity assessment module inputs the extracted conflict feature vectors into a machine learning model that has been pre-trained based on historical collaborative tasks to evaluate the conflict severity of the target task and outputs the conflict degree score of the target task; The conflict classification optimization and task reconstruction module performs decision branch processing based on the conflict degree judgment result output by the machine learning model: when the conflict degree between the target task and other tasks is mild, the automatic optimization unit is used to directly generate a collaborative optimization plan; When the conflict degree between the target task and other tasks is severe, the target task is divided into multiple independently schedulable subtask units, and the number of subtask divisions is adaptively adjusted according to the severity of the conflict.

Images