Cooperative task complexity analysis method and system based on task network characteristics

Abstract

The embodiment of the invention provides a cooperative task complexity analysis method and system based on task network characteristics, and the method comprises the steps: carrying out the hierarchical decomposition of a command and control task into atomic tasks according to four dimensions, constructing a task network model, traversing the task network model, extracting network scale characteristics, structural relation characteristics and uncertainty characteristics, and carrying out the calculation of the complexity of the atomic tasks. Complexity calculation is carried out on the network scale feature, the structural relationship feature and the uncertainty feature, a corresponding complexity quantification result is determined, and optimization adjustment is carried out on the task network model according to the complexity quantification result, so that the task network complexity of the task network model is reduced, and the task network complexity of the task network model is improved. The accuracy and efficiency of command and control task complexity measurement can be improved.

Description

Technical Field

[0001] This application relates to the field of data processing, specifically to a method and system for analyzing the complexity of collaborative tasks based on task network characteristics. Background Technology

[0002] In command and control systems, the effective execution of command and control tasks is crucial to achieving objectives. Command and control tasks involve a series of complex activities, including detection and monitoring, intelligence analysis, planning, decision-making and command, coordination and control, and evaluation and feedback. The core of these tasks lies in the decision-making process, while team understanding and collaboration are the foundation for successful mission completion. However, different roles (such as end users, R&D management departments, and designers) often have different perceptions and understandings of command and control tasks. These differences can lead to disagreements during mission analysis, thereby affecting key aspects such as mission flow design, equipment function planning and allocation.

[0003] Traditional task analysis methods often focus on the decomposition and evaluation of individual tasks or simple team tasks, with less attention paid to the essential processes of complex command and control tasks and the intrinsic mechanisms of team cognitive collaboration. Furthermore, traditional methods tend to emphasize theoretical research and are not strongly correlated with the actual needs of command and control equipment development.

[0004] Task complexity models and their measurement methods are a key focus of human factors research. Wood argues that task complexity consists of three dimensions: component complexity, relational complexity, and dynamic complexity. Campbell defines four characteristics of task complexity: multiple paths, multiple outcomes, conflicting dependencies between paths, and uncertainty in path / outcome connections. However, these studies primarily focus on individual tasks and simple team tasks, with limited exploration of the internal logic and operational mechanisms of complex task complexity.

[0005] In view of the limitations of traditional task analysis methods and the challenges of task complexity research, there is an urgent need for a collaborative task complexity analysis method based on task network characteristics to improve the accuracy and efficiency of command and control task complexity measurement. Summary of the Invention

[0006] To address the problems in the existing technology, this application provides a collaborative task complexity analysis method and system based on task network characteristics, which can improve the accuracy and efficiency of command and control task complexity measurement.

[0007] To solve at least one of the above problems, this application provides the following technical solution: Firstly, this application provides a method for analyzing the complexity of collaborative tasks based on task network characteristics, including: The command and control task is hierarchically decomposed into four dimensions: observation, judgment, decision-making, and action, until it is decomposed into atomic tasks. The corresponding task network model is constructed based on the set of task nodes after decomposition and the set of connection relationships between nodes. The task network model is traversed to extract the total number of nodes in the task node set, the total number of connection edges in the connection relationship set, and the total number of different target object categories targeted by all leaf node tasks. Based on the extracted data, the corresponding network scale characteristics are determined. The degree of each task node in the task network model is calculated, and the corresponding degree distribution is determined based on the number of nodes with the same degree value in the network. Based on the degree and the degree distribution, the corresponding structural relationship characteristics are determined, where the degree is used to characterize the number of connection edges directly connected to the node. A fuzziness level assessment is performed on each task node in the task network model to determine the corresponding uncertainty characteristics. Complexity calculations are performed on the network size feature, the structural relationship feature, and the uncertainty feature respectively to determine the corresponding complexity quantification results. The task network model is then optimized and adjusted based on the complexity quantification results to reduce the task network complexity of the task network model.

[0008] Further, the process of traversing the task network model, extracting the total number of nodes in the task node set, the total number of connection edges in the connection relationship set, and the total number of different target object categories targeted by all leaf node tasks, and determining the corresponding network size characteristics based on the extracted data, including: Traverse the task node set and connection relationship set of the task network model to determine the total number of nodes and the total number of connection edges. Identify all leaf node tasks in the task network model, perform semantic analysis on the leaf node tasks, determine the execution target, operation object and output result of each leaf node, and group tasks whose execution target, operation object or output result belongs to the same category into the same category, and determine the corresponding total number of categories; The corresponding network scale characteristics are determined based on the total number of nodes, the total number of connected edges, and the total number of categories.

[0009] Further, the step of calculating the degree of each task node in the task network model, determining the corresponding degree distribution based on the number of nodes with the same degree value in the network, and determining the corresponding structural relationship features based on the degree and the degree distribution includes: Construct the adjacency matrix of the task network model, traverse each task node in the adjacency matrix, count the number of non-zero elements in its corresponding row or column, and obtain the degree of the task node. The number of nodes with the same degree value in the task network model is counted, and the probability distribution of each degree value is calculated based on the total number of nodes to determine the corresponding degree distribution. The network structure relationship complexity of the task network model is quantified based on the degree and the degree distribution to determine the corresponding structural relationship features.

[0010] Furthermore, the step of evaluating the fuzziness level of each task node in the task network model and determining the corresponding uncertainty characteristics includes: A fuzzy evaluation index is constructed from three dimensions: the clarity of the implementation standards, the clarity of the implementation methods, and the clarity of the implementation plan. The fuzziness level of each task node in the task network model is evaluated based on the fuzziness evaluation index to determine the corresponding uncertainty features, which include the three-dimensional index.

[0011] Further, the step of calculating the complexity of the network scale features and determining the corresponding complexity quantification result includes: The total number of nodes and the total number of connecting edges are used as quantity parameters, and the total number of categories is used as diversity parameters; The quantity parameter and the diversity parameter are input into a preset network scale complexity calculation model to calculate the complexity and determine the corresponding complexity quantification result of the network scale feature.

[0012] Further, the step of calculating the complexity of the structural relationship features and determining the corresponding complexity quantification result includes: Construct an information entropy formula, wherein the information entropy formula is: , where k is the degree of the node, and p(k) is the degree distribution of the node; Substituting the degree distribution into the information entropy formula, the complex quantification result of the structural relationship features is calculated.

[0013] Further, the step of calculating the complexity of the uncertainty feature and determining the corresponding complexity quantification result includes: The three dimensions of uncertainty characteristics of each task node are added together to determine the local uncertainty value of that node. By integrating the local uncertainties of all task nodes and performing batch summation calculations, a complex quantification result of the overall uncertainty characteristics of the task network is determined.

[0014] Secondly, this application provides a collaborative task complexity analysis system based on task network characteristics, comprising: The task network model construction module is used to hierarchically decompose the command and control task according to four dimensions: observation, judgment, decision-making, and action, until it is decomposed into atomic tasks. The corresponding task network model is constructed based on the set of atomic task nodes and the set of connection relationships between nodes. The task network feature determination module is used to traverse the task network model, extract the total number of nodes in the task node set, the total number of connection edges in the connection relationship set, and the total number of different target object categories targeted by all leaf node tasks, and determine the corresponding network scale features based on the extracted data; calculate the degree of each task node in the task network model, determine the corresponding degree distribution based on the number of nodes with the same degree value in the network, and determine the corresponding structural relationship features based on the degree and the degree distribution, wherein the degree is used to characterize the number of connection edges directly connected to the node; and perform fuzziness level evaluation on each task node in the task network model to determine the corresponding uncertainty features. The task network complexity calculation module is used to calculate the complexity of the network size feature, the structural relationship feature, and the uncertainty feature respectively, determine the corresponding complexity quantification result, and optimize and adjust the task network model according to the complexity quantification result to reduce the task network complexity of the task network model.

[0015] Thirdly, this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the cooperative task complexity analysis method based on task network characteristics.

[0016] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the cooperative task complexity analysis method based on task network characteristics.

[0017] Fifthly, this application provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the cooperative task complexity analysis method based on task network characteristics.

[0018] As can be seen from the above technical solution, this application provides a collaborative task complexity analysis method and system based on task network features. After decomposing the command and control task into atomic tasks according to four dimensions, a task network model is constructed. The task network model is traversed to extract network size features, structural relationship features, and uncertainty features. The complexity of the network size features, structural relationship features, and uncertainty features is calculated respectively to determine the corresponding complexity quantification results. The task network model is optimized and adjusted according to the complexity quantification results to reduce the task network complexity of the task network model, thereby improving the accuracy and efficiency of command and control task complexity measurement. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is one of the flowcharts illustrating the collaborative task complexity analysis method based on task network features in this application embodiment; Figure 2 This is a structural diagram of the collaborative task complexity analysis system based on task network features in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of the electronic device in the embodiments of this application.

[0021] Figure label: Electronic device 9600, central processing unit 9100, memory 9140, communication module 9110, input unit 9120, audio processor 9130, display 9160, power supply 9170, buffer memory 9141, application / function storage unit 9142, data storage unit 9143, driver storage unit 9144, antenna 9111, speaker 9131, microphone 9132. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0024] Given that command and control missions involve a series of complex activities such as detection and surveillance, intelligence analysis, planning, decision-making, coordination and control, and evaluation and feedback, traditional task analysis methods rarely address the essential processes and intrinsic mechanisms of team cognitive collaboration in complex command and control missions. This application provides a collaborative task complexity analysis method and system based on task network characteristics. By hierarchically decomposing command and control missions into atomic tasks along four dimensions, a task network model is constructed. The model is then traversed to extract network size features, structural relationship features, and uncertainty features. The complexity of each feature is calculated to determine the corresponding complexity quantification results. Based on these results, the task network model is optimized to reduce its complexity, thereby improving the accuracy and efficiency of command and control mission complexity measurement.

[0025] To improve the accuracy and efficiency of task complexity measurement, this application provides an embodiment of a collaborative task complexity analysis method based on task network features. See [link to embodiment]. Figure 1 The collaborative task complexity analysis method based on task network characteristics specifically includes the following: Step S101: Decompose the command and control task hierarchically according to the four dimensions of observation, judgment, decision-making and action until it is decomposed into atomic tasks. Construct the corresponding task network model based on the set of task nodes after decomposition and the set of connection relationships between nodes. Optionally, in this embodiment, this step transforms a macroscopic, abstract accusation mission into a structured, quantifiable, and computable analytical model.

[0026] Optionally, in this embodiment, task decomposition is a top-down, layer-by-layer refinement process based on the essential cognitive cycle of command and control—Observation, Orientation, Decision, and Action, i.e., the OODA loop.

[0027] First, the top-level command mission that needs to be analyzed (such as "completing the surface monitoring mission") is taken as the root node or a composite task. This task itself is highly generalized and abstract, and cannot be directly executed or measured.

[0028] Next, the top-level task is broken down into first-level sub-tasks along four main dimensions: O, D, and A. For example: Observation (O): can be broken down into sub-tasks such as "surface search radar monitoring", "sonar array underwater acoustic signal monitoring", and "electronic support measures (ESM)".

[0029] Decision (O): can be broken down into sub-tasks such as "target motion parameter calculation", "target attribute identification", and "hazard level assessment".

[0030] Decision (D): can be broken down into sub-tasks such as "route selection scheme generation", "route planning", and "course rule determination".

[0031] Action (A): can be broken down into sub-tasks such as "path change command issuance", "ship maneuver control", and "implementation of electronic countermeasures".

[0032] Secondly, the aforementioned first-level subtasks may still be complex and require further decomposition. This process is recursively repeated until each subtask meets the "atomicity" criterion. An atomic task is a basic task unit that is indivisible, can be independently executed by a single person or piece of equipment, and produces a definite result. For example, "monitoring underwater acoustic signals from a sonar array" can be further decomposed into a series of atomic tasks such as "starting the sonar system," "setting the sonar operating frequency," "listening to signals in a specific frequency band," and "recording abnormal audio characteristics."

[0033] The final output of the decomposition process is a hierarchical task tree. The root node is the top-level task, the intermediate nodes are composite subtasks at different levels, and all leaf nodes are atomic tasks. After obtaining the complete task decomposition tree, it needs to be transformed into a network model to capture the complex logic and collaborative relationships between tasks, rather than just the hierarchical relationships.

[0034] Specifically, define the node set (U): Each task node in the task decomposition tree (including composite and atomic tasks at all levels) is included in the node set U. Each node is assigned a unique identifier and can record information such as its type (composite / atomic), its OODA dimension, and the executing entity.

[0035] Specifically, define the set of connection relationships (C): This is key to elevating the tree model to a network model. Edges are used to represent various dependencies and temporal relationships between task nodes. The construction of edges is mainly based on the following logic: Temporal sequence: This indicates the order in which tasks are executed. For example, "target motion parameter calculation" can only be performed after "maritime search radar monitoring," and a directed edge is established between the two.

[0036] Information flow relationship: This indicates that the output of one task is the input of another task. For example, the "hazard level assessment" task depends on the output of the "target attribute identification" task, and a directed edge is established between the two.

[0037] Logical dependencies include selection (e.g., if condition A is met, task B is executed; otherwise, task C is executed), loops (a task needs to be executed repeatedly), and synchronization (multiple tasks need to start or end simultaneously). These relationships are also represented by edges and their attributes.

[0038] Collaborative relationships: This reflects the coordination between different positions or roles. For example, the tasks of "route selection scheme generation" and "flight planning" need to be carried out collaboratively, and there may be a two-way information exchange between them.

[0039] Optionally, in this embodiment, the common types of task flow relationships are shown in Table 1 below:

[0040] Table 1 Specifically, a task network model T=(U, C) is formed: Ultimately, a directed network model is constructed through the set of nodes U and the set of connections C. This network model is no longer a simple tree structure, but a complex graph structure containing loops, parallel paths, and branch selection, which can more realistically reflect the complexity and dynamism of actual command and control task processes.

[0041] This step, through systematic decomposition and modeling, transforms the real-world command and control task into a complex network data model rich in information. It transforms the vague, qualitative task description into a clear, quantitative network topology, providing a unique and definite data object for subsequent complexity measurement. The edges in the network model intuitively demonstrate how tasks are connected, how information flows, and how decisions rely on forward perception, making the entire command and control process's operational mechanism visible and analyzable.

[0042] All metrics in subsequent steps, such as network size, structural relationships, and uncertainty, depend on the network model constructed in this step. The accuracy and detail of the model directly determine the reliability of the final complexity analysis results.

[0043] Step S102: Traverse the task network model, extract the total number of nodes in the task node set, the total number of connection edges in the connection relationship set, and the total number of different target object categories targeted by all leaf node tasks, and determine the corresponding network scale features based on the extracted data; calculate the degree of each task node in the task network model, determine the corresponding degree distribution based on the number of nodes with the same degree value in the network, and determine the corresponding structural relationship features based on the degree and the degree distribution, wherein the degree is used to characterize the number of connection edges directly connected to the node; perform fuzziness level evaluation on each task node in the task network model to determine the corresponding uncertainty features; Optionally, in this embodiment, this step transforms the constructed task network model into a series of quantifiable feature indicators that reflect its complexity. The network is scanned and statistically evaluated from three dimensions: scale, structure, and uncertainty. This transforms the abstract topology and task attributes into concrete numerical features, providing accurate data input for subsequent complexity calculations and optimizations.

[0044] Optionally, in this embodiment, network scale features are extracted.

[0045] The task scope of a command and control system task network represents the total number and diversity of all task nodes and connecting edges in the command and control hierarchical task network. Command and control system task networks exhibit typical scale-free characteristics, meaning that the connections between nodes are unevenly distributed. Therefore, the types of nodes and the number of connecting edges around each node are not uniform. Consequently, the more nodes and types a command and control task network has, the larger the network size and the higher the task complexity; conversely, the fewer nodes and the lower the task complexity.

[0046] First, the total number of nodes is calculated. The algorithm traverses the entire task network model, visiting each element in the task node set (U) one by one, counting them, and finally obtaining the total number of nodes (M). Similarly, the algorithm traverses the set of connection relationships (C), counting each directed or undirected connection edge, and obtaining the total number of connection edges (N). This step is a direct measurement of the number of basic constituent elements of the network.

[0047] Secondly, diversity calculation. This process is more refined. The system identifies all "leaf nodes" in the network, that is, atomic tasks that are no longer further decomposed and can be directly executed. Then, for each leaf node task, its core attributes are analyzed, namely the "target object" it targets. The target object refers to the object of the task operation or the specific category of the goal to be achieved, such as "acoustic signals," "heading data," "navigation system," and "navigation commands." The algorithm needs to classify these target objects according to predefined classification rules or through semantic analysis. For example, all tasks that process "target bearing information" can be classified into the "target positioning" category, and all tasks involving "ship control" can be classified into the "ship handling control" category. Finally, the total number (m) of these different categories is counted. This step goes beyond simple quantitative statistics and introduces consideration of task diversity.

[0048] The M and N values ​​extracted in this step are the most basic and intuitive indicators of network size. More nodes generally mean more activities need to be performed; more connection edges indicate more frequent logical dependencies and information exchanges between tasks. These two values ​​directly reflect the scale of the task.

[0049] Introducing the diversity dimension and statistically analyzing the value of m is a key refinement for measuring the scale characteristics of a network. A network with 100 nodes but involving only 2 types of target objects differs in complexity from a network with 80 nodes but involving 15 types of target objects. The latter requires the system or personnel to possess broader knowledge and process more diverse information, resulting in higher complexity. Therefore, the introduction of m makes the scale characteristic more accurately reflect the complexity and breadth of the task.

[0050] Optionally, in this embodiment, structural relationship features are extracted.

[0051] The task structure of the command and control task network refers to the edge paths and connections between nodes in the task network, which is composed of the total task, sub-tasks, and leaf node tasks of the command and control system. In other words, it represents the logical relationships between nodes. Therefore, the simpler and more ordered the edge structure of the command and control task network, the fewer the task-related connections, and the lower the complexity of the command and control system task. Conversely, the more complex and disordered the edge structure of the command and control task network, the higher the complexity of the command and control system task.

[0052] This step aims to quantify the “morphology” and “order” of the connections within the task network, focusing on how the connections are distributed, rather than just their total number.

[0053] First, calculate the node degree. The algorithm traverses each node (u_i) in the task network. For each node, the algorithm checks the set of connections (C) and counts the number of edges that start from or end at that node (in an undirected graph, this is the number of all edges connected to that node). This value is the "degree" (k_i) of that node.

[0054] The degree of a node is a direct measure of its connectivity: a high-degree node (such as a command and decision node) may connect a large number of information input and command output tasks, while a low-degree node (such as a single data record task) has very few connections.

[0055] Secondly, the statistical degree distribution. After obtaining the degree values ​​of all nodes in the network, the next step is to perform a statistical aggregation operation. This calculates the number of nodes in the network with the same degree value k, denoted as n(k). For example, it counts how many nodes have a degree of 1, how many nodes have a degree of 2, and so on. Then, each n(k) is divided by the total number of nodes N in the network to obtain the probability p(k) = n(k) / N for each degree value. This probability distribution p(k) describes the distribution of the number of connections between nodes in the network.

[0056] Next, the extracted "degree" and "degree distribution" data are themselves a structural feature description. However, for quantitative calculations, these data are used to calculate the structural relationship complexity (Task Structure). The degree distribution reveals the structural characteristics of the network: if the degree distribution is concentrated (the degree value of most nodes is close to the average value), the network structure is relatively uniform and simple; if the degree distribution is dispersed, with a small number of "hub" nodes with extremely high connection numbers and a large number of nodes with extremely low connection numbers, the network exhibits "scale-free" characteristics and has a more complex structure.

[0057] This step transforms the macroscopic structure of the network into microscopic, analyzable degree distribution data. By analyzing the degree distribution, we can determine whether the task network resembles a flat structure where all task roles are equal, or a hierarchical, centralized structure with key core tasks.

[0058] While the immediate purpose of this step is to calculate the overall structural complexity, the extracted node degree data is itself an important byproduct. Nodes with high degree counts are typically critical task points in the network; these nodes bear heavy loads, and their performance and reliability are crucial to the smooth execution of the entire task network. This provides direct data support for subsequent task optimization and resource allocation.

[0059] Optionally, in this embodiment, the uncertainty features are extracted.

[0060] Task uncertainty in a command and control network refers to the degree of predictability or clarity of sub-task nodes within the network. It describes the uncertainty of these sub-task nodes in terms of execution standards, methods, and plans. The higher the predictability and clarity of the operational processes, steps, and results of each sub-task node (such as operational plans, schemes, functions, and events) decomposed within the command and control system task, the lower the uncertainty of the command and control task. Task uncertainty is also affected by external events (including the imposition of a series of higher-level command and control orders and random unforeseen events). Therefore, the higher the uncertainty and the lower the predictability of a command and control system task, the higher its objective complexity; conversely, the lower the uncertainty, the lower the objective complexity of the task.

[0061] This section aims to quantify the "ambiguity" or "unpredictability" of each task node in the task network at the execution level, focusing on the cognitive challenges in the task execution process.

[0062] First, a predefined multi-dimensional fuzzy evaluation framework is used. This framework includes three core dimensions: execution criteria (whether there are clear and measurable output quality standards), execution methods (whether there are clear and followable operating procedures or algorithms), and execution plans (whether the execution order and timing are clear and whether they are susceptible to external interference).

[0063] Next, each task node in the network needs to be evaluated across the three dimensions (X_i, Y_i, Z_i). The evaluation uses a Likert scale or similar format, assigning a rating from 1 (very vague) to 5 (very specific) to each dimension. This process is a crucial step in transforming qualitative judgments about the nature of the task into quantitative data.

[0064] For each node, the scores across its three dimensions are summed to obtain the task uncertainty value a(i) = X_i + Y_i + Z_i for that node. This value reflects the degree of ambiguity of a single task node. Subsequently, the weighted summation of the a(i) values ​​for all nodes yields the raw data for the overall task uncertainty characteristic (TaskUncertainty) of the entire task network.

[0065] This step transforms the elusive, "soft" and vague concepts in traditional task analysis into measurable and comparable hard data through a structured and dimensional approach. By evaluating each node individually, this process can precisely depict the distribution of uncertainty across different stages of the task network. It can identify which tasks are highly standardized (low uncertainty) and which tasks are highly variable and heavily reliant on human judgment (high uncertainty).

[0066] The uncertainty data extracted in this step is the core input for intelligent function allocation. The allocation principle is to assign high-uncertainty tasks to human operators (leveraging their cognitive flexibility and judgment), while assigning low-uncertainty, standardized tasks to machines or automated systems (ensuring efficiency and reliability). This transforms function allocation decisions from experience-driven to data-driven.

[0067] Meanwhile, high-uncertainty task nodes are often the vulnerabilities of the entire system, more prone to errors, delays, or requiring additional cognitive resources. Identifying these nodes helps to specifically enhance decision support, provide richer contextual information, or conduct specialized training during system design.

[0068] Step S103: Calculate the complexity of the network size feature, the structural relationship feature, and the uncertainty feature respectively, determine the corresponding complexity quantification results, and optimize and adjust the task network model according to the complexity quantification results to reduce the task network complexity of the task network model.

[0069] Optionally, in this embodiment, this step is the core computation and decision-making link in the task network complexity management and optimization process. The goal is to systematically reduce the overall complexity of the task network, thereby improving the efficiency, reliability and human-machine collaboration performance of the command and control system.

[0070] Optionally, in this embodiment, a feature-based task complexity measurement method is used to conduct research on measurement methods.

[0071] Specifically, network scale feature complexity measurement.

[0072] The network size measurement method for command and control system tasks uses network size-related characteristics as dependent variables and parameters such as the total number and diversity of all task nodes and connection edges in the network as independent variables to establish a quantitative expression of network size characteristics. This calculation mainly evaluates the "volume" and "diversity" of the task network.

[0073] Construct a network scale complexity model:

[0074] Where M and N represent the total number of task nodes and connecting edges, respectively, representing the scale; m represents the target object category of the leaf node task, i.e. the diversity of tasks.

[0075] The design logic of this formula is as follows: the number of nodes and edges (M+N) directly reflects the scale of the network, while the diversity of task types (m) reflects the amount of information and organizational difficulty brought about by the logarithmic function. The output is a scalar value representing the complexity of the network scale. The higher the value, the more task units and relationships that personnel or systems need to process and coordinate, and the greater the cognitive load and coordination cost will be.

[0076] Specifically, the complexity of structural relationship features is measured.

[0077] The structural relationship measurement method for command and control tasks uses structural relationship features as dependent variables and parameters such as edge paths and connections between nodes in the network (i.e., logical relationships between nodes) as independent variables to establish a quantitative expression of network structural relationship features. Considering the scale-free nature of the command and control system, i.e., the uneven distribution of node degree, this step measures structural relationships through node degree and degree distribution.

[0078] node The degree is defined as the number of edges connected to that node. The node degree distribution indicates that the node degree is... Node number distribution probability .by Indicates node degree as The number of nodes, This represents the total number of nodes in the entire network. The node is represented by its degree. The probability is expressed as:

[0079] The above steps counted the number of nodes with different degrees k in the network and calculated the probability p(k) of each degree value. Then, these probability values ​​were substituted into the entropy calculation formula:

[0080] The entropy value directly reflects the uniformity of the node degree distribution: a highly ordered, clearly centralized network (e.g., a few nodes have many connections, while most nodes have few connections) has a concentrated degree distribution and a low entropy value; conversely, a network with chaotic and uniform connections has a dispersed degree distribution and a high entropy value. The output is an entropy value, which quantifies the uncertainty or disorder of the network structure. The higher the entropy value, the more complex the structure, the more unpredictable the information flow path, and the higher the requirements for system coordination.

[0081] Specifically, a measure of the complexity of uncertainty features.

[0082] The uncertainty measurement method for command and control tasks uses uncertainty-related characteristics as the dependent variable and the predictability or certainty of sub-task nodes in the command and control system network (i.e., the uncertainty of sub-task nodes in the command and control system network regarding execution standards, methods, and plans) as independent variables to establish a quantitative expression of uncertainty characteristics. The higher the uncertainty of the execution standards, methods, and plans of each node in the task network, the higher the complexity of the command and control task network.

[0083] The input to the uncertainty complexity calculation is the subjective evaluation results of each task node in the network in three dimensions: execution standard fuzziness (X_i) (whether there is a clear and measurable output standard), execution method fuzziness (Y_i) (whether there is a clear and repeatable operating procedure), and execution plan fuzziness (Z_i) (whether the execution process is stable and whether it will be frequently interrupted by unexpected events).

[0084] Each dimension was evaluated by experts using a Likert scale (5-point rating). The process involved summing the scores of each task node across its three dimensions (a(i) = X_i + Y_i + Z_i) to obtain the local uncertainty of that node. Then, the uncertainty scores of all task nodes (or all leaf nodes) in the network were summed (Σ a(i)). The output was a total score, representing the total uncertainty faced by the entire task network. A higher score indicates more potential ambiguity, judgment, and adaptive adjustments required during task execution, and thus higher demands on personnel skills and adaptability. ,in,

[0085] After obtaining complex quantification results across three dimensions, the process moves into the analysis and decision-making phase. This step is crucial for transforming data into insights.

[0086] First, a comprehensive indicator analysis is conducted, not by viewing the three indicators in isolation, but by making a holistic judgment. For example, a network may have high scale complexity but low structural complexity (highly procedural) and low uncertainty (standardized operations), and its overall challenge may mainly lie in managing a large number of routine tasks. Another network may be small in scale but structurally complex (tightly coupled) and highly uncertain, and its challenge lies in dealing with complex, non-standard collaborative scenarios. By comparing the complexity metrics results of different task schemes or different design iterations, the main sources of complexity and their relative proportions can be clearly identified.

[0087] Quantitative results help pinpoint specific bottlenecks in complexity. High structural complexity entropy values ​​guide analysts to focus on nodes in the network with an abnormally high (too many or too few) number of connections. High uncertainty scores can further trace which task nodes or which types of tasks (such as decision-making or emergency response) contribute the most uncertainty. This granular analysis allows optimization measures to be targeted and effective.

[0088] Based on the above analysis, the task network model is optimized and adjusted in a targeted manner, which is a feedback iterative process.

[0089] For optimization of complex networks, if this value is too high, the optimization strategy focuses on "simplification" and "aggregation." Specific measures include: Task consolidation: merging multiple fine-grained, sequentially executed atomic tasks into a more meaningful composite task, reducing unnecessary task nodes and edges. Functional automation: identifying highly repetitive, well-defined subtasks and assigning them to machines or systems for automatic completion, thereby removing them from the task network requiring manual operation and directly reducing the number of nodes and edges. Interface integration: at the information presentation level, integrating scattered information sources into a unified situational awareness interface, reducing the redundant "tasks" required for personnel to obtain information.

[0090] For optimizations involving complex structural relationships, if this value is too high, the optimization strategy focuses on "simplification" and "restructuring." Specific measures include: reducing coupling: redesigning task flows to reduce unnecessary and overlapping dependencies between task nodes, making information and workflows more linear and modular. Clearly defining central nodes: strengthening the functional support of core decision-making nodes (such as commanders) while simplifying the connection paths of surrounding support nodes, allowing the network structure to evolve from a "mesh" to a more ordered structure such as a "star" or "tree," thereby reducing entropy. Optimizing information routing: establishing clear information transmission rules to avoid information being circulated or ineffectively copied between multiple nodes. For optimization targeting complex uncertainties, if the value is too high, the optimization strategy focuses on "clarity" and "empowerment." Specific measures include: Developing Standard Operating Procedures (SOPs): Establishing detailed and clear execution standards, methods, and contingency plans for high-uncertainty task nodes (i.e., reducing the values ​​of X_i, Y_i, Z_i), transforming fuzzy tasks into procedural tasks. Reasonable function allocation: Allocating human and machine functions based on uncertainty type. Assigning tasks with clear rules but high computational load or requiring precision (low method fuzziness, high load) to machines; leaving unstructured tasks requiring intuition, reasoning, and adaptability (high uncertainty) to human experts, achieving complementary advantages between humans and machines. Enhancing system intelligence: Introducing decision support systems, expert systems, or artificial intelligence assistance to provide real-time suggestions and data insights for humans handling high-uncertainty tasks, reducing their cognitive difficulty.

[0091] This step makes the task load under different mission scenarios, system designs, and even equipment configurations comparable and assessable. This provides objective data support for design decisions and reduces subjective debates. Through three-dimensional decomposition and measurement, the root causes of complexity can be accurately identified, greatly improving design efficiency. Ultimately, all optimization measures aim to improve the overall effectiveness of the command and control system.

[0092] This example demonstrates how this embodiment improves the accuracy and efficiency of task complexity measurement by decomposing tasks to build a task network model, extracting task complexity features, and performing complexity analysis, ultimately improving task execution efficiency.

[0093] As can be seen from the above description, the collaborative task complexity analysis method based on task network features provided in this application can construct a task network model by hierarchically decomposing the command and control task into atomic tasks according to four dimensions, traversing the task network model, extracting network scale features, structural relationship features, and uncertainty features, calculating the complexity of the network scale features, structural relationship features, and uncertainty features respectively, determining the corresponding complexity quantification results, and optimizing and adjusting the task network model according to the complexity quantification results to reduce the task network complexity of the task network model, thereby improving the accuracy and efficiency of command and control task complexity measurement.

[0094] In one embodiment of the collaborative task complexity analysis method based on task network features of this application, the method may further include the following: Step S201: Traverse the task node set and connection relationship set of the task network model to determine the total number of nodes and the total number of connection edges. Step S202: Identify all leaf node tasks in the task network model, perform semantic analysis on the leaf node tasks, determine the execution target, operation object and output result of each leaf node, and group tasks whose execution target, operation object or output result belongs to the same category into the same category, and determine the corresponding total number of categories; Step S203: Determine the corresponding network scale characteristics based on the total number of nodes, the total number of connected edges, and the total number of categories.

[0095] Optionally, in this embodiment, this step is the network scale feature extraction process.

[0096] First, the constructed task network model is scanned and analyzed as a whole, systematically traversing all task nodes and their connections. This traversal process accurately counts the total number of task nodes and connections in the model. This step serves to grasp the macroscopic size and connection density of the task network; a larger number of nodes and connections generally indicates more task units to be processed and more complex information flow paths, providing the most basic quantitative basis for subsequent quantification of the network size.

[0097] Next, after identifying all these leaf nodes, semantic analysis techniques are used to analyze them, parsing the core attributes of each leaf node's task, including its final execution goal, the specific object of its operation, and the form of the output result. Based on this, the leaf nodes are classified according to these semantic attributes, grouping tasks with the same execution goal, operating on the same type of object, or producing the same type of output into the same category, and then counting the total number of all different categories. The core function of this step is to evaluate the diversity of tasks in the task network. The more categories there are, the richer the task types, the higher the degree of specialization, and the wider the task dimensions that the system needs to handle. It is a key indicator for measuring the complexity of the network scale.

[0098] Ultimately, the total number of nodes and connected edges obtained in the first step, along with the total number of task categories obtained in the second step, provide core data support for objectively assessing the macroscopic scale and complexity of different task networks.

[0099] Through step S203, this embodiment successfully extracted the network scale characteristics of the task network, which is an important foundation for subsequent analysis of the network structure.

[0100] In one embodiment of the collaborative task complexity analysis method based on task network features of this application, the method may further include the following: Step S301: Construct the adjacency matrix of the task network model, traverse each task node in the adjacency matrix, count the number of non-zero elements in its corresponding row or column, and obtain the degree of the task node. Step S302: Count the number of nodes with the same degree value in the task network model, and calculate the probability distribution of each degree value based on the total number of nodes to determine the corresponding degree distribution; Step S303: Quantify the network structure relationship complexity of the task network model based on the degree and the degree distribution, and determine the corresponding structural relationship features.

[0101] Optionally, in this embodiment, this step is a structural relationship feature extraction process. It aims to quantify the "morphology" and "orderliness" of connections within the task network, focusing on how connections are distributed, rather than just their total number.

[0102] First, calculate the node degree. The algorithm traverses each node (u_i) in the task network. For each node, the algorithm checks the set of connections (C) and counts the number of edges that start from or end at that node (in an undirected graph, this is the number of all edges connected to that node). This value is the "degree" (k_i) of that node.

[0103] The degree of a node is a direct measure of its connectivity: a high-degree node (such as a command and decision node) may connect a large number of information input and command output tasks, while a low-degree node (such as a single data record task) has very few connections.

[0104] Secondly, the statistical degree distribution. After obtaining the degree values ​​of all nodes in the network, the next step is to perform a statistical aggregation operation. This calculates the number of nodes in the network with the same degree value k, denoted as n(k). For example, it counts how many nodes have a degree of 1, how many nodes have a degree of 2, and so on. Then, each n(k) is divided by the total number of nodes N in the network to obtain the probability p(k) = n(k) / N for each degree value. This probability distribution p(k) describes the distribution of the number of connections between nodes in the network.

[0105] Through step S303, this embodiment successfully extracted structural relationship features, transforming the macroscopic structure of the network into microscopic, analyzable degree distribution data, providing direct data support for subsequent task optimization and resource allocation.

[0106] In one embodiment of the collaborative task complexity analysis method based on task network features of this application, the method may further include the following: Step S401: Construct fuzzy evaluation indicators from three dimensions: the clarity of the execution standards, the clarity of the execution methods, and the clarity of the execution plan; Step S402: Evaluate the fuzziness level of each task node in the task network model according to the fuzziness evaluation index, and determine the corresponding uncertainty features, wherein the uncertainty features include the three-dimensional index.

[0107] Optionally, in this embodiment, this step is an uncertainty feature extraction process. It aims to quantify the "fuzziness" or "unpredictability" of each task node in the task network at the execution level, focusing on the cognitive challenges during task execution.

[0108] First, a predefined multi-dimensional fuzzy evaluation framework is used. This framework includes three core dimensions: execution criteria (whether there are clear and measurable output quality standards), execution methods (whether there are clear and followable operating procedures or algorithms), and execution plans (whether the execution order and timing are clear and whether they are susceptible to external interference).

[0109] Next, each task node in the network needs to be evaluated across the three dimensions (X_i, Y_i, Z_i). The evaluation uses a Likert scale or similar format, assigning a rating from 1 (very vague) to 5 (very specific) to each dimension. This process is a crucial step in transforming qualitative judgments about the nature of the task into quantitative data.

[0110] For each node, the scores across its three dimensions are summed to obtain the task uncertainty value a(i) = X_i + Y_i + Z_i for that node. This value reflects the degree of ambiguity of a single task node. Subsequently, the weighted summation of the a(i) values ​​for all nodes yields the raw data for the overall task uncertainty characteristic (TaskUncertainty) of the entire task network.

[0111] Through step S402, this embodiment successfully extracted uncertainty features, and the process can accurately depict the uncertainty distribution of different links in the task network.

[0112] In one embodiment of the collaborative task complexity analysis method based on task network features of this application, the method may further include the following: Step S501: Use the total number of nodes and the total number of connecting edges as quantity parameters, and the total number of categories as diversity parameters; Step S502: Input the quantity parameter and the diversity parameter into the preset network scale complexity calculation model to calculate the complexity and determine the complexity quantification result of the corresponding network scale feature.

[0113] Optionally, in this embodiment, this step is a complex quantification process of network scale characteristics.

[0114] The network size measurement method for command and control system tasks uses network size-related characteristics as dependent variables and parameters such as the total number and diversity of all task nodes and connection edges in the network as independent variables to establish a quantitative expression of network size characteristics. This calculation mainly evaluates the "volume" and "diversity" of the task network.

[0115] Construct a network scale complexity model:

[0116] Where M and N represent the total number of task nodes and connecting edges, respectively, representing the scale; m represents the target object category of the leaf node task, i.e. the diversity of tasks.

[0117] The design logic of this formula is as follows: the number of nodes and edges (M+N) directly reflects the scale of the network, while the diversity of task types (m) reflects the amount of information and organizational difficulty brought about by the logarithmic function. The output is a scalar value representing the complexity of the network scale. The higher the value, the more task units and relationships that personnel or systems need to process and coordinate, and the greater the cognitive load and coordination cost will be.

[0118] Through step S502, this embodiment successfully measured the task complexity of network scale characteristics, laying a data foundation for subsequent optimization of the task network.

[0119] In one embodiment of the collaborative task complexity analysis method based on task network features of this application, the method may further include the following: Step S601: Construct the information entropy formula, wherein the information entropy formula is as follows: , where k is the degree of the node, and p(k) is the degree distribution of the node; Step S602: Substitute the degree distribution into the information entropy formula to calculate the complex quantification result of the structural relationship features.

[0120] Optionally, in this embodiment, this step is a complex quantification process of structural relationship features.

[0121] The structural relationship measurement method for command and control tasks uses structural relationship features as dependent variables and parameters such as edge paths and connections between nodes in the network (i.e., logical relationships between nodes) as independent variables to establish a quantitative expression of network structural relationship features. Considering the scale-free nature of the command and control system, i.e., the uneven distribution of node degree, this step measures structural relationships through node degree and degree distribution.

[0122] node The degree is defined as the number of edges connected to that node. The node degree distribution indicates that the node degree is... Node number distribution probability .by Indicates node degree as The number of nodes, This represents the total number of nodes in the entire network. The node is represented by its degree. The probability is expressed as:

[0123] The above steps counted the number of nodes with different degrees k in the network and calculated the probability p(k) of each degree value. Then, these probability values ​​were substituted into the entropy calculation formula: The entropy value directly reflects the uniformity of the node degree distribution: a highly ordered, clearly centralized network (e.g., a few nodes have many connections, while most nodes have few connections) has a concentrated degree distribution and a low entropy value; conversely, a network with chaotic and uniform connections has a dispersed degree distribution and a high entropy value. The output is an entropy value, which quantifies the uncertainty or disorder of the network structure. The higher the entropy value, the more complex the structure, the more unpredictable the information flow path, and the higher the requirements for system coordination.

[0124] Specifically, as illustrated in Table 2 below, which is a table for calculating the complexity of task structure relationships:

[0125] Table 2 Through step S602, this embodiment successfully measured the task complexity of the task structure features, laying a data foundation for subsequent optimization of the task network.

[0126] In one embodiment of the collaborative task complexity analysis method based on task network features of this application, the method may further include the following: Step S701: Add the three dimensions of uncertainty features of each task node to determine the local uncertainty value of that node; Step S702: Integrate the local uncertainties of all task nodes and perform batch summation to determine the complex quantification result of the overall uncertainty characteristics of the task network.

[0127] Optionally, in this embodiment, this step is a complex quantification process of uncertainty features.

[0128] The uncertainty measurement method for command and control tasks uses uncertainty-related characteristics as the dependent variable and the predictability or certainty of sub-task nodes in the command and control system network (i.e., the uncertainty of sub-task nodes in the command and control system network regarding execution standards, methods, and plans) as independent variables to establish a quantitative expression of uncertainty characteristics. The higher the uncertainty of the execution standards, methods, and plans of each node in the task network, the higher the complexity of the command and control task network.

[0129] The input to the uncertainty complexity calculation is the subjective evaluation results of each task node in the network in three dimensions: execution standard fuzziness (X_i) (whether there is a clear and measurable output standard), execution method fuzziness (Y_i) (whether there is a clear and repeatable operating procedure), and execution plan fuzziness (Z_i) (whether the execution process is stable and whether it will be frequently interrupted by unexpected events).

[0130] Each dimension was evaluated by experts using a Likert scale (5-point rating). The process involved summing the scores of each task node across its three dimensions (a(i) = X_i + Y_i + Z_i) to obtain the local uncertainty of that node. Then, the uncertainty scores of all task nodes (or all leaf nodes) in the network were summed (Σ a(i)). The output was a total score, representing the total uncertainty faced by the entire task network. A higher score indicates more potential ambiguity, judgment, and adaptive adjustments required during task execution, and thus higher demands on personnel skills and adaptability. ,in,

[0131] Specifically, as illustrated in Table 3 below, the fuzzy evaluation indicators for the control task unit are as follows:

[0132] Table 3 Through step S702, this embodiment successfully measured the task complexity of uncertainty features, laying a data foundation for subsequent optimization of the task network.

[0133] To improve the accuracy and efficiency of task complexity measurement, this application provides an embodiment of a collaborative task complexity analysis system based on task network features, which implements all or part of the aforementioned collaborative task complexity analysis method based on task network features. See [link to implementation details]. Figure 2 The collaborative task complexity analysis system based on task network characteristics specifically includes the following: The task network model construction module 10 is used to hierarchically decompose the command and control task according to four dimensions: observation, judgment, decision and action, until it is decomposed into atomic tasks, and to construct the corresponding task network model based on the set of decomposed task nodes and the set of connection relationships between nodes. The task network feature determination module 20 is used to traverse the task network model, extract the total number of nodes in the task node set, the total number of connection edges in the connection relationship set, and the total number of different target object categories targeted by all leaf node tasks, and determine the corresponding network scale features based on the extracted data; calculate the degree of each task node in the task network model, determine the corresponding degree distribution based on the number of nodes with the same degree value in the network, and determine the corresponding structural relationship features based on the degree and the degree distribution, wherein the degree is used to characterize the number of connection edges directly connected to the node; and perform fuzziness level evaluation on each task node in the task network model to determine the corresponding uncertainty features. The task network complexity calculation module 30 is used to calculate the complexity of the network size feature, the structural relationship feature and the uncertainty feature respectively, determine the corresponding complexity quantification result, and optimize and adjust the task network model according to the complexity quantification result so as to reduce the task network complexity of the task network model.

[0134] As can be seen from the above description, the collaborative task complexity analysis system based on task network features provided in this application can construct a task network model by hierarchically decomposing the command and control task into atomic tasks according to four dimensions, traversing the task network model, extracting network scale features, structural relationship features, and uncertainty features, calculating the complexity of the network scale features, structural relationship features, and uncertainty features respectively, determining the corresponding complexity quantification results, and optimizing and adjusting the task network model according to the complexity quantification results, so as to reduce the task network complexity of the task network model, thereby improving the accuracy and efficiency of command and control task complexity measurement.

[0135] To further illustrate this solution, this application also provides specific embodiments.

[0136] The application scenario is to analyze two simulated tasks: "target identification" and "surface early warning" for ships.

[0137] Both simulation tasks consist of two parts: independent operation and team collaboration to complete the task.

[0138] (1) Team collaboration main task: includes two types of tasks, which are triggered in a random order.

[0139] ① Target identification task: refers to a series of tasks triggered by the detection of an unknown target, such as detection and monitoring, target identification, situation assessment, comprehensive decision-making, avoidance / dialogue, etc. ② Surface early warning mission: refers to a series of simulated tasks such as threat detection calculation, hazard assessment, situation judgment, comprehensive decision-making, and route execution triggered by the detection of abnormal dangers on the water surface.

[0140] (2) Team collaboration auxiliary task: includes an alarm prompt task. While completing the main team collaboration task, an alarm prompt window will pop up randomly to observe or record the reaction of the instructing personnel and explore the cognitive status of relevant personnel regarding the collaboration information.

[0141] (3) Individual tasks: While completing the main and auxiliary tasks of team collaboration, each position needs to take care of completing their own independent individual tasks.

[0142] The simulation calculation process for the task network complexity is as follows.

[0143] Table 4 below is the network feature calculation table for the "target judgment task".

[0144]

[0145] Table 4 Table 5 below is a calculation table of network characteristics for "water surface early warning".

[0146]

[0147] Table 5 The calculation results are as follows: Network size of network features for target identification and surface early warning tasks ( ), structural relationship ( ), uncertainty ( The calculation and standardization results are shown in Table 6:

[0148] Table 6 The calculation results show that the network size, structural relationship, and uncertainty characteristics of the target judgment task are higher than those of the surface early warning task. In particular, the differences in network size and uncertainty between the two tasks are not obvious, which fully reflects that the target judgment task is more complex.

[0149] Therefore, for designing for command and control tasks, the following suggestions can be made from the perspective of the three characteristics of the task network: (1) Network size: Minimize the network size of the command and control task, that is, reduce the number of sub-task nodes and edge size that the command and control personnel or equipment need to complete, and reduce the numerous interactive processes in the task size by relying on automation and intelligent technology, thereby reducing the workload of human-computer interaction tasks and thus reducing the complexity characteristic value of the command and control task network.

[0150] (2) Structural relationship: Minimize the uniformity of degree distribution of task nodes, that is, highlight the centrality of key nodes in the task and reduce the centrality of unimportant nodes, simplify the structural relationship of node network in the task network, thereby reducing the structural complexity feature value of the command and control task network.

[0151] (3) Uncertainty: On the one hand, minimize the uncertainty of each task node of the command and control system. On the other hand, allocate human-machine functions based on the uncertainty state of the node tasks. Functions with low uncertainty are completed by machine automation and intelligence technologies, while functions with high uncertainty are completed by humans, so as to improve the reliability of the tasks.

[0152] From a hardware perspective, in order to improve the accuracy and efficiency of the measurement of the complexity of command and control tasks, this application provides an embodiment of an electronic device for implementing all or part of the aforementioned collaborative task complexity analysis method based on task network features. The electronic device specifically includes the following components: The system comprises a processor, memory, a communications interface, and a bus; wherein the processor, memory, and communications interface communicate with each other via the bus; the communications interface is used to realize information transmission between the collaborative task complexity analysis method based on task network characteristics and core business systems, user terminals, and related databases and other related devices; the logic controller can be a desktop computer, tablet computer, or mobile terminal, etc., and this embodiment is not limited to these. In this embodiment, the logic controller can be implemented with reference to the embodiments of the collaborative task complexity analysis method based on task network characteristics in the embodiments, and the contents of the embodiments of the collaborative task complexity analysis method based on task network characteristics are incorporated herein, and repeated parts will not be described again.

[0153] It is understood that the user terminal may include smartphones, tablet computers, network set-top boxes, portable computers, desktop computers, personal digital assistants (PDAs), in-vehicle devices, smart wearable devices, etc. Among these, the smart wearable devices may include smart glasses, smartwatches, smart bracelets, etc.

[0154] In practical applications, the collaborative task complexity analysis method based on task network characteristics can be partially executed on the electronic device side as described above, or all operations can be completed on the client device. The choice can be made based on the processing power of the client device and the limitations of the user's usage scenario. This application does not impose any limitations on this. If all operations are completed on the client device, the client device may further include a processor.

[0155] The aforementioned client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission. The server may include a server on the task scheduling center side; in other implementation scenarios, it may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, a server cluster consisting of multiple servers, or a distributed system server structure.

[0156] Figure 3 This is a schematic block diagram illustrating the system configuration of the electronic device 9600 according to an embodiment of this application. Figure 3As shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It is worth noting that... Figure 3 This is an example; other types of structures can also be used to supplement or replace this structure to achieve telecommunications functions or other functions.

[0157] In one embodiment, the collaborative task complexity analysis method based on task network characteristics can be integrated into the central processing unit 9100. The central processing unit 9100 can be configured to perform the following control: Step S101: Decompose the command and control task hierarchically according to the four dimensions of observation, judgment, decision-making and action until it is decomposed into atomic tasks. Construct the corresponding task network model based on the set of task nodes after decomposition and the set of connection relationships between nodes. Step S102: Traverse the task network model, extract the total number of nodes in the task node set, the total number of connection edges in the connection relationship set, and the total number of different target object categories targeted by all leaf node tasks, and determine the corresponding network scale features based on the extracted data; calculate the degree of each task node in the task network model, determine the corresponding degree distribution based on the number of nodes with the same degree value in the network, and determine the corresponding structural relationship features based on the degree and the degree distribution, wherein the degree is used to characterize the number of connection edges directly connected to the node; perform fuzziness level evaluation on each task node in the task network model to determine the corresponding uncertainty features; Step S103: Calculate the complexity of the network size feature, the structural relationship feature, and the uncertainty feature respectively, determine the corresponding complexity quantification results, and optimize and adjust the task network model according to the complexity quantification results to reduce the task network complexity of the task network model.

[0158] As can be seen from the above description, the electronic device provided in this application constructs a task network model by hierarchically decomposing the command and control task into atomic tasks according to four dimensions, traversing the task network model, extracting network scale features, structural relationship features, and uncertainty features, calculating the complexity of the network scale features, structural relationship features, and uncertainty features respectively, determining the corresponding complexity quantification results, and optimizing and adjusting the task network model according to the complexity quantification results, so as to reduce the task network complexity of the task network model, thereby improving the accuracy and efficiency of command and control task complexity measurement.

[0159] In another embodiment, the collaborative task complexity analysis method based on task network characteristics can be configured separately from the central processing unit 9100. For example, the collaborative task complexity analysis method based on task network characteristics can be configured as a chip connected to the central processing unit 9100, and the function of the collaborative task complexity analysis method based on task network characteristics can be realized through the control of the central processing unit.

[0160] like Figure 3 As shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily need to include these components. Figure 3 All components shown; in addition, the electronic device 9600 may also include Figure 3 For components not shown, please refer to existing technologies.

[0161] like Figure 3 As shown, the central processing unit 9100, sometimes also referred to as a controller or operating control, may include a microprocessor or other processor system and / or logic system, which receives inputs and controls the operation of various components of the electronic device 9600.

[0162] The memory 9140 may be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable systems. It may store the aforementioned failure-related information, and also store a program for executing that information. The central processing unit 9100 may execute the program stored in the memory 9140 to perform information storage or processing, etc.

[0163] Input unit 9120 provides input to central processing unit 9100. Input unit 9120 may be, for example, a keypad or touch input system. Power supply 9170 provides power to electronic device 9600. Display 9160 displays images and text. Display may be, for example, an LCD display, but is not limited thereto.

[0164] The memory 9140 can be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of this type of memory are sometimes referred to as EPROMs, etc. The memory 9140 can also be some other type of system. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142 for storing application programs and function programs or processes for executing the operation of the electronic device 9600 via the central processing unit 9100.

[0165] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for the electronic device for communication functions and / or for performing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0166] The communication module 9110 is a transmitter / receiver that sends and receives signals via the antenna 9111. The communication module 9110 is coupled to the central processing unit 9100 to provide input signals and receive output signals, which is the same as in a conventional mobile communication terminal.

[0167] Based on different communication technologies, multiple communication modules 9110 can be configured in the same electronic device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication module 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby realizing typical telecommunications functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. Furthermore, the audio processor 9130 is also coupled to a central processing unit 9100, enabling on-device recording via the microphone 9132 and on-device playback of stored audio via the speaker 9131.

[0168] Embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the collaborative task complexity analysis method based on task network characteristics, where the execution subject is a server or client, as described in the above embodiments. The computer-readable storage medium stores a computer program that, when executed by a processor, implements all steps of the collaborative task complexity analysis method based on task network characteristics, where the execution subject is a server or client, as described in the above embodiments. For example, when the processor executes the computer program, it implements the following steps: Step S101: Decompose the command and control task hierarchically according to the four dimensions of observation, judgment, decision-making and action until it is decomposed into atomic tasks. Construct the corresponding task network model based on the set of task nodes after decomposition and the set of connection relationships between nodes. Step S102: Traverse the task network model, extract the total number of nodes in the task node set, the total number of connection edges in the connection relationship set, and the total number of different target object categories targeted by all leaf node tasks, and determine the corresponding network scale features based on the extracted data; calculate the degree of each task node in the task network model, determine the corresponding degree distribution based on the number of nodes with the same degree value in the network, and determine the corresponding structural relationship features based on the degree and the degree distribution, wherein the degree is used to characterize the number of connection edges directly connected to the node; perform fuzziness level evaluation on each task node in the task network model to determine the corresponding uncertainty features; Step S103: Calculate the complexity of the network size feature, the structural relationship feature, and the uncertainty feature respectively, determine the corresponding complexity quantification results, and optimize and adjust the task network model according to the complexity quantification results to reduce the task network complexity of the task network model.

[0169] As can be seen from the above description, the computer-readable storage medium provided in this application provides a task network model by hierarchically decomposing the command and control task into atomic tasks according to four dimensions, traversing the task network model, extracting network size features, structural relationship features, and uncertainty features, calculating the complexity of the network size features, structural relationship features, and uncertainty features respectively, determining the corresponding complexity quantification results, and optimizing and adjusting the task network model according to the complexity quantification results, so as to reduce the task network complexity of the task network model, thereby improving the accuracy and efficiency of command and control task complexity measurement.

[0170] Embodiments of this application also provide a computer program product capable of implementing all steps of the collaborative task complexity analysis method based on task network characteristics, where the execution subject is a server or client, as described in the above embodiments. When executed by a processor, this computer program / instruction implements the steps of the collaborative task complexity analysis method based on task network characteristics. For example, the computer program / instruction implements the following steps: Step S101: Decompose the command and control task hierarchically according to the four dimensions of observation, judgment, decision-making and action until it is decomposed into atomic tasks. Construct the corresponding task network model based on the set of task nodes after decomposition and the set of connection relationships between nodes. Step S102: Traverse the task network model, extract the total number of nodes in the task node set, the total number of connection edges in the connection relationship set, and the total number of different target object categories targeted by all leaf node tasks, and determine the corresponding network scale features based on the extracted data; calculate the degree of each task node in the task network model, determine the corresponding degree distribution based on the number of nodes with the same degree value in the network, and determine the corresponding structural relationship features based on the degree and the degree distribution, wherein the degree is used to characterize the number of connection edges directly connected to the node; perform fuzziness level evaluation on each task node in the task network model to determine the corresponding uncertainty features; Step S103: Calculate the complexity of the network size feature, the structural relationship feature, and the uncertainty feature respectively, determine the corresponding complexity quantification results, and optimize and adjust the task network model according to the complexity quantification results to reduce the task network complexity of the task network model.

[0171] As described above, the computer program product provided in this application decomposes the command and control task into atomic tasks in a hierarchical manner according to four dimensions, constructs a task network model, traverses the task network model, extracts network size features, structural relationship features, and uncertainty features, calculates the complexity of the network size features, structural relationship features, and uncertainty features respectively, determines the corresponding complexity quantification results, and optimizes and adjusts the task network model according to the complexity quantification results to reduce the task network complexity of the task network model, thereby improving the accuracy and efficiency of command and control task complexity measurement.

[0172] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0173] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.

[0174] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction set implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0175] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0176] Specific embodiments have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. A method for analyzing complexity of collaborative tasks based on features of task networks, characterized in that, The method comprises: The accused task is hierarchically decomposed in four dimensions of observation, judgment, decision and action until it is decomposed into atomic tasks, a task network model is constructed according to the decomposed task node set and the connection relationship set between nodes; Traverse the task network model, extract the total number of nodes in the task node set, the total number of connection edges in the connection relationship set, and the total number of different target object categories of all leaf node tasks, determine the corresponding network size feature according to the extracted data; calculate the degree of each task node in the task network model, determine the corresponding degree distribution according to the number of nodes with the same degree value in the network, and determine the corresponding structure relationship feature according to the degree and the degree distribution, wherein the degree is used to represent the number of connection edges directly connected with the node; fuzzy level evaluation is performed on each task node in the task network model to determine the corresponding uncertainty feature; The network size feature, the structure relationship feature and the uncertainty feature are calculated respectively to determine the complexity quantization result, and the task network model is optimized and adjusted according to the complexity quantization result to reduce the complexity of the task network model.

2. The method of claim 1, wherein, The traversal of the task network model, the extraction of the total number of nodes in the task node set, the total number of connection edges in the connection relationship set, and the total number of different target object categories of all leaf node tasks, and the determination of the corresponding network size feature according to the extracted data, comprises: Traverse the task node set and the connection relationship set of the task network model to determine the total number of nodes and the total number of connection edges; Identify all leaf node tasks in the task network model, perform semantic analysis on the leaf node tasks, determine the execution target, operation object and output result of each leaf node, and merge tasks with the same category into the same category according to the execution target, operation object or output result, and determine the total number of categories; Determine the network size feature according to the total number of nodes, the total number of connection edges and the total number of categories. 3.The task network feature based collaborative task complexity analysis method of claim 1, wherein, The calculation of the degree of each task node in the task network model, the determination of the corresponding degree distribution according to the number of nodes with the same degree value in the network, and the determination of the corresponding structure relationship feature according to the degree and the degree distribution, comprises: Build the adjacency matrix of the task network model, traverse each task node of the adjacency matrix, and count the number of non-zero elements in its corresponding row or column to obtain the degree of the task node; Count the number of nodes with the same degree value in the task network model, and calculate the probability distribution of each degree value based on the total number of nodes to determine the corresponding degree distribution; Quantify the network structure relationship complexity of the task network model according to the degree and the degree distribution to determine the corresponding structure relationship feature.

4. The method of claim 1, wherein, The fuzzy level evaluation of each task node in the task network model to determine the corresponding uncertainty feature, comprises: Fuzzy evaluation index is constructed from three dimensions of execution standard explicitness, execution method explicitness and execution plan explicitness; According to the ambiguity evaluation index, the ambiguity level of each task node in the task network model is evaluated, and corresponding uncertainty features are determined, wherein the uncertainty features include the three dimension indicators.

5. The method of claim 2, wherein the method further comprises: The complexity of the network size feature is calculated, and corresponding complexity quantization results are determined, including: The total number of nodes and the total number of connection edges are taken as quantity parameters, and the total number of categories is taken as a diversity parameter; The quantity parameters and the diversity parameters are input into a preset network size complexity calculation model for complexity calculation, and the complexity quantization results of the network size feature are determined.

6. The method of claim 3, wherein the method further comprises: The complexity of the structure relationship feature is calculated, and corresponding complexity quantization results are determined, including: The information entropy formula is constructed, and the information entropy formula is wherein k is the degree of the node, and p(k) is the degree distribution of the node. The degree distribution is substituted into the information entropy formula, and the complexity quantization results of the structure relationship feature are calculated.

7. The method of claim 4, wherein the method further comprises: The complexity of the uncertainty feature is calculated, and corresponding complexity quantization results are determined, including: The three dimension uncertainty features of each task node are added to determine the local uncertainty value of the node; The local uncertainty values of all task nodes are integrated for batch summation calculation to determine the complexity quantization results of the overall uncertainty feature of the task network.

8. A system for analyzing complexity of collaborative tasks based on features of task networks, characterized by, The system includes: A task network model construction module is configured to hierarchically decompose the control tasks according to four dimensions of observation, judgment, decision, and action until the atomic tasks are obtained, and to construct a corresponding task network model according to the decomposed atomic task node set and the connection relationship set between the nodes; A task network feature determination module is configured to traverse the task network model, extract the total number of nodes in the task node set, the total number of connection edges in the connection relationship set, and the total number of different target object categories corresponding to all leaf node tasks, and determine the network size feature according to the extracted data; calculate the degree of each task node in the task network model, determine the degree distribution according to the number of nodes with the same degree in the network, and determine the structure relationship feature according to the degree and the degree distribution, wherein the degree represents the number of connection edges directly connected to the node; evaluate the ambiguity level of each task node in the task network model, and determine the uncertainty feature; A task network complexity calculation module is configured to calculate the complexity of the network size feature, the structure relationship feature, and the uncertainty feature respectively, determine the complexity quantization results, and optimize and adjust the task network model according to the complexity quantization results to reduce the complexity of the task network model.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the steps of the task network feature-based collaborative task complexity analysis method of any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the task network feature-based collaborative task complexity analysis method of any one of claims 1 to 7.

Images