An intelligent human-machine collaboration system and method based on E-CARGO model

Abstract

The present invention discloses an intelligent human-machine collaboration system and method based on the E-CARGO model, which belongs to the field of human-machine collaboration technology, and includes: a human-machine task allocation module: used to analyze task attributes and executor capabilities, and to allocate and assign collaboration between humans and machines; a conflict collaboration analysis module: used to detect and resolve potential conflicts and collaborations between humans and machines in terms of tasks, resources, etc., so as to optimize collaboration efficiency and system performance. The present invention adopts the above-mentioned intelligent human-machine collaboration system and method based on the E-CARGO model, which can realize intelligent task allocation and collaboration mechanism, making the collaboration between humans and machines more efficient and intelligent, and can intelligently allocate tasks according to factors such as task requirements, user characteristics and real-time status, optimize collaborative workflows, and enhance overall collaboration effects, thereby improving the overall system performance and user experience, and can be used in various occasions such as emergency response, industrial production, and simulation training.

Description

Technical Field

[0001] The present invention relates to the technical field of human-machine collaboration, and in particular to an intelligent human-machine collaboration system and method based on an E-CARGO model. Background Art

[0002] In modern complex working environments, human-machine collaboration is becoming increasingly important, especially in areas that require efficient collaborative tasks, such as military command, industrial production, and healthcare. In order to optimize human-machine collaboration and improve work efficiency, researchers and engineers have introduced different collaboration models and intelligent technologies. The E-CARGO model is a model of intelligent collaboration that focuses on task allocation, resource management, and communication collaboration to achieve a more efficient workflow. The model takes into account the capabilities of different entities (including humans and machines), the characteristics of tasks, and the dynamic changes in the working environment, and optimizes the overall performance of the collaborative system through intelligent analysis and decision-making. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent human-machine collaboration system and method based on the E-CARGO model, which can realize intelligent task allocation and collaboration mechanism, make the collaboration between man and machine more efficient and intelligent, and can intelligently allocate tasks according to factors such as task requirements, user characteristics and real-time status, optimize the collaborative workflow, and enhance the overall collaboration effect. It improves the overall system performance and user experience, and can be used in various occasions such as emergency response, industrial production, simulation training, etc.

[0004] To achieve the above object, the present invention provides an intelligent human-machine collaboration system and method based on the E-CARGO model, comprising:

[0005] Human-machine task allocation module: used to analyze task attributes and executor capabilities, and to allocate and assign tasks for collaboration between humans and machines;

[0006] Conflict and collaboration analysis module: used to detect and resolve potential conflicts and collaborations between people and machines in terms of tasks, resources, etc., to optimize collaboration efficiency and system performance.

[0007] Preferably, the human-machine task allocation module includes:

[0008] Capability assessment module: used to assess the capability level of each entity, including humans and machines, in order to more accurately allocate tasks, optimize the collaboration process, and ensure the collaboration effect of the system under different conditions;

[0009] Task Assignment Module: Intelligently assign tasks to different entities to maximize the efficiency and performance of the overall system.

[0010] Preferably, the capability assessment module includes:

[0011] Capability information description unit: This unit is used to describe and define the capability information of each entity. It is responsible for collecting, storing and maintaining detailed information about the capabilities of each entity. This information constitutes an entity capability description file, providing the system with a comprehensive understanding of the entity's capabilities.

[0012] Capability information conversion unit: This unit is used to process and convert the collected capability information so that the system can better understand and utilize the information, combining the entity's historical performance with the current capabilities to more accurately reflect the entity's actual status.

[0013] Preferably, the task assignment module includes:

[0014] Model Optimization Unit: Strives to improve the accuracy and intelligence of the task assignment model by continuously adjusting E-CARGO model parameters, updating algorithms, and improving learning capabilities;

[0015] Effectiveness Analysis Unit: Comprehensively analyze the actual effect of task assignment through evaluation of task completion, efficiency and user satisfaction.

[0016] Preferably, the conflict collaboration analysis module includes:

[0017] Information collection module: responsible for collecting relevant information from various entities, tasks and system environments;

[0018] Intelligent analysis module: used to use the data provided by the information collection module to perform intelligent analysis of conflicts and collaborations occurring in the system.

[0019] The present invention provides an intelligent human-machine collaboration method based on the E-CARGO model, which is characterized by comprising the following steps:

[0020] S1: For several tasks, the manager selects many people and machines to perform tasks in human-machine collaboration and sends the request to the intelligent human-machine collaboration system;

[0021] S2: The manager independently chooses whether to consider human-machine conflict and collaboration factors in the system: if the conflict and collaboration analysis module is used, the process proceeds to step S3; if the conflict and collaboration analysis module is not used, the process proceeds to step S5;

[0022] S3: In the conflict collaboration analysis module, the attitudes of all people and machines on different issues or attributes are analyzed and evaluated through the information collection module, and information is collected and given to the conflict collaboration analysis information system;

[0023] S4: In the conflict and collaboration analysis module, the attitude information of all people and machines is summarized through the intelligent analysis module, and the attitude difference function between them is calculated. The conflict and collaboration relationships are divided according to the three-branch decision theory, and then the process goes to step S5;

[0024] S5: In the human-machine task assignment module, the capability data of human operators and machine entities, including information such as skill level, experience, and education, are collected through the capability assessment module, and a human-machine capability assessment matrix for different tasks is generated;

[0025] S6: In the human-machine task allocation module, different optimization models and algorithms are constructed through the task assignment module according to the capability evaluation matrix and the E-CARGO model to obtain the assignment results and simulate and verify the execution performance;

[0026] S7: If the obtained human-machine collaborative task execution result is inconsistent with or unsatisfactory to the general cognition of the manager, the target object or the entire team, then go back to step S2.

[0027] Therefore, the present invention adopts the above-mentioned intelligent human-machine collaboration system and method based on the E-CARGO model, which has the following beneficial effects:

[0028] 1) By introducing the E-CARGO model, the system can more intelligently evaluate the capabilities of human and machine entities, and realize intelligent and dynamic task allocation by combining the characteristics of tasks and real-time working environment information. This helps to improve the efficiency of task execution and ensure that each entity gets the best task, thereby optimizing the overall collaboration process;

[0029] 2) The present invention introduces a conflict collaboration analysis module that can quickly detect potential task conflicts, resource competition and other issues. Through the solutions provided by the intelligent analysis module, the system can resolve conflicts more quickly and effectively, improving the stability and robustness of the collaborative system;

[0030] 3) The capability assessment module based on the E-CARGO model of the present invention supports personalized task allocation, taking into account the individual differences and preferences of each entity, which helps to improve user satisfaction, enables the system to better adapt to the needs of different users, and provides a collaborative experience that is more in line with individual characteristics.

[0031] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of an embodiment system of an intelligent human-machine collaboration system and method based on an E-CARGO model of the present invention;

[0033] Figure 2It is a flow chart of an embodiment method of an intelligent human-machine collaboration system and method based on an E-CARGO model of the present invention;

[0034] Figure 3 This is an application example diagram of an intelligent human-machine collaboration system and method embodiment based on the E-CARGO model of the present invention. DETAILED DESCRIPTION

[0035] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0036] Unless otherwise defined, technical or scientific terms used in the present invention shall have the common meanings understood by one having ordinary skills in the field to which the present invention belongs.

[0037] Example

[0038] like Figure 1 As shown, the present invention provides an intelligent human-machine collaboration system based on the E-CARGO model, comprising:

[0039] Human-machine task allocation module: used to analyze task attributes and executor capabilities, and to allocate and assign tasks for collaboration between humans and machines.

[0040] The human-machine task allocation module includes:

[0041] Capability Assessment Module: It is used to assess the capability level of each entity, including humans and machines, so as to more accurately allocate tasks, optimize the collaboration process, and ensure the collaboration effect of the system under different conditions.

[0042] The competency assessment modules include:

[0043] Capability information description unit: This unit is used to describe and define the capability information of each entity. It is responsible for collecting, storing and maintaining detailed information about each entity's capabilities, which may include data on skills, experience, education, performance history, etc. This information constitutes an entity's capability description file, providing the system with a comprehensive understanding of the entity's capabilities.

[0044] Consider using intuitionistic fuzzy numbers to represent and define the capability information of each entity, where the membership degree indicates the proportion of agreeing to cooperate with a certain person and a certain machine, the hesitant membership degree indicates the degree of hesitation about cooperation, and the non-membership degree indicates the proportion of disagreeing with cooperation. Specifically, this unit is responsible for collecting, storing and maintaining detailed information about the capabilities of each entity, including data on skills S, experience E, education Edu, performance history PH, etc.

[0045] Capability information conversion unit: This unit is used to process and convert the collected capability information so that the system can better understand and utilize this information. Specifically, it may involve standardizing the capability information of different entities and establishing capability evaluation models or indicators so that the system can make intelligent task allocation and decision-making based on this information. The capability information conversion unit can also combine the historical performance of the entity with the current capability to more accurately reflect the actual status of the entity.

[0046] Specifically, it involves the following aspects:

[0047] Standardization: Responsible for standardizing the capability information of different entities to have consistent measurements and scales so that the system can effectively compare and analyze the capabilities of each entity.

[0048] Establish capability assessment model or index: Based on the collected capability information, construct capability assessment model or index. This includes factors such as skills, experience, education, performance history, etc., and uses intuitive fuzzy numbers to quantify and evaluate the capability level of the entity.

[0049] Intelligent task allocation and decision-making: Using the established capability assessment model or indicators, the system is provided with intelligent task allocation and decision-making support. This helps the system to make more reasonable task allocation based on the capability characteristics and historical performance of the entity, and improve the overall collaboration efficiency.

[0050] Combine historical performance: Combine the entity’s historical performance with its current capabilities to more accurately reflect the entity’s actual state. This comprehensive consideration helps the system more fully understand the entity’s potential contributions and limitations.

[0051] Task Assignment Module: Intelligently assign tasks to different entities to maximize the efficiency and performance of the overall system.

[0052] The task assignment module includes:

[0053] Model Optimization Unit: We are committed to improving the accuracy and intelligence of the task assignment model by continuously adjusting E-CARGO model parameters, updating algorithms, and improving learning capabilities. This includes continuous monitoring and feedback loops of the model to adapt to changes in different working environments and task complexity. Through optimization, the model can better adapt to real-time data and feedback, ensuring that it can achieve the best performance in different scenarios.

[0054] Specifically, this includes the following:

[0055] Capacity matrix Q adjustment: By monitoring and adjusting the capacity matrix Q of the E-CARGO model, we ensure that the model can better consider the needs of each machine for people. Dynamic adjustment of Q helps to improve the flexibility and adaptability of task assignment.

[0056] Role weight W update: According to the number of people (L) required for each machine, the role weight W of the task assignment model is continuously optimized to ensure that the role weight W more specifically considers and adapts to the actual needs of each machine, so as to perform task assignment more intelligently.

[0057] Improve learning capabilities: Introduce new training data and continuously monitor the learning process to improve the learning capabilities of the task assignment model. This enables the model to better understand the needs of each machine and continuously improve performance.

[0058] Continuous monitoring and feedback loop: Establish a continuous monitoring and feedback loop mechanism for the task assignment model. By timely monitoring the performance of the model in actual tasks and obtaining feedback information, the model parameters and algorithms can be adjusted to ensure the robustness and adaptability of the model in practice.

[0059] Adapt to different scenarios: Dynamically adjust the E-CARGO model to ensure optimal performance in different scenarios, especially to make corresponding adjustments to the changes in the number of people required by each machine, which helps the model better adapt to diverse work scenarios.

[0060] Effectiveness Analysis Unit: Through the evaluation of task completion, efficiency and user satisfaction, the actual effect of task assignment is comprehensively analyzed. This helps to identify potential improvement points to ensure that the task assignment module achieves the expected effect in actual application. The analysis results provide targeted feedback for system operation and provide guidance for future model optimization and system improvement;

[0061] Through the evaluation of task completion (PD), efficiency (EFF), and user satisfaction (SAT), the actual effect of task assignment is comprehensively analyzed. Specifically:

[0062] Task completion evaluation (PD): Evaluate the accuracy of task assignments by monitoring task completion.

[0063] Efficiency (EEF): Evaluates the work efficiency of the task assignment module, that is, the time and resources required to complete the task.

[0064] User satisfaction (SAT): Evaluate user satisfaction with the task assignment module by collecting user feedback and evaluation.

[0065] The analysis results of these evaluation indicators help identify potential improvement points and ensure that the task assignment module achieves the expected results in practical applications. The work of the effectiveness analysis unit includes comprehensive analysis of the above indicators to form a comprehensive evaluation, which provides targeted feedback for system operation and provides guidance for future model optimization and system improvement.

[0066] Conflict and collaboration analysis module: used to detect and resolve potential conflicts and collaborations between people and machines in terms of tasks, resources, etc., to optimize collaboration efficiency and system performance.

[0067] The conflict collaboration analysis module includes:

[0068] Information collection module: responsible for collecting relevant information from various entities, tasks and system environments; this information may cover the nature of the task, the status of human and machine entities, resource availability, the status of communication channels, etc. The information collection module continuously updates the system status information to ensure that the conflict collaboration analysis module has the latest context information, providing an accurate data basis for intelligent analysis;

[0069] In the description of the conflict analysis information system, we can introduce some symbols to express it more formally:

[0070] Object Set: Indicated by the symbol O, it represents a finite set of entities participating in the task.

[0071] Problem or attribute set (Attribute Set): Indicated by the symbol A, it represents the set of problems or attributes considered by the system.

[0072] Attribute value set (Value Set): Represented by the symbol V, it represents the possible attitude set on each issue or attribute, that is, V = {support, neutral, oppose}.

[0073] Mapping Function: It is represented by the symbol M: O×A→V, which represents the mapping relationship between objects and questions or attributes, where M(o, a) represents the attitude of object o towards the question or attribute α.

[0074] Intelligent Analysis Module: Used to use the data provided by the Information Collection Module to perform intelligent analysis of possible conflicts and collaborations in the system. This includes identifying potential task conflicts, resource competition, communication bottlenecks, and other issues. By using advanced algorithms and models, the Intelligent Analysis Module can quickly and accurately analyze information, identify conflicts, and provide targeted solutions.

[0075] For the user set H in the human-machine collaboration scenario, there are two threshold sets α and β, where α k and β k Is user h k Two thresholds for evaluating the conflict and collaboration between people, machines, and people and machines, satisfying the condition: 0≤β k <α k ≤ 1. The symbol l here emphasizes the length of the threshold set.

[0076] For user hk , a pair of x (representing human or machine) and y (representing human or machine) is defined as:

[0077] (1) If d(x, y) ≥ α k , then it is a conflict;

[0078] (2) If β k <d(x,y)<α k , then it is neutral;

[0079] (3) If d(x, y)≤β k , then it is collaboration.

[0080] Here, d(x, y) represents the distance or difference between objects x and y. The distance metric here can take into account factors such as skill matching and work experience to reflect the synergy potential between humans and machines.

[0081] This definition is based on the three-branch decision theory, which clarifies the user's conflict, neutral and collaborative attitudes towards the relationship between humans and machines under specific threshold conditions. In the context of human-machine collaboration, the introduction of threshold sets helps the system to more flexibly adapt to the user's subjective judgment on cooperation and conflict, thereby improving the adaptability and efficiency of the overall collaborative system.

[0082] like Figure 2 As shown, the present invention provides an intelligent human-machine collaboration method based on the E-CARGO model, comprising the following steps:

[0083] S1: For several tasks, the manager selects many people and machines to perform tasks in human-machine collaboration and sends the request to the intelligent human-machine collaboration system;

[0084] S2: The manager independently chooses whether to consider human-machine conflict and collaboration factors in the system: if the conflict and collaboration analysis module is used, the process proceeds to step S3; if the conflict and collaboration analysis module is not used, the process proceeds to step S5;

[0085] S3: In the conflict collaboration analysis module, the attitudes of all people and machines on different issues or attributes are analyzed and evaluated through the information collection module, and information is collected and given to the conflict collaboration analysis information system;

[0086] S4: In the conflict and collaboration analysis module, the attitude information of all people and machines is summarized through the intelligent analysis module, and the attitude difference function between them is calculated. The conflict and collaboration relationships are divided according to the three-branch decision theory, and then the process goes to step S5;

[0087] S5: In the human-machine task assignment module, the capability data of human operators and machine entities, including information such as skill level, experience, and education, are collected through the capability assessment module, and a human-machine capability assessment matrix for different tasks is generated;

[0088] S6: In the human-machine task allocation module, different optimization models and algorithms are constructed through the task assignment module according to the capability evaluation matrix and the E-CARGO model to obtain the assignment results and simulate and verify the execution performance;

[0089] S7: If the obtained human-machine collaborative task execution result is inconsistent with or unsatisfactory to the general cognition of the manager, the target object or the entire team, then go back to step S2.

[0090] Embodiment 1

[0091] The following uses the application of this specific embodiment in intelligent human-machine collaboration as an example to further illustrate this specific implementation. In an emergency natural disaster rescue mission, the team leader G selects members from a team T consisting of multiple people and multiple machines, including N = 5 professional rescuers P i and M = 3 robots R j The mission involves multiple aspects such as search and rescue, material distribution, etc., which need to be completed efficiently and collaboratively, such as Figure 3 As shown, the specific process is as follows:

[0092] (1) Task dispatch: G sends a task request Task to the intelligent human-machine collaborative system, requiring it to complete the search and rescue and material distribution tasks in the shortest time possible.

[0093] (2) Decision-making autonomy: G has autonomy in decision-making and can choose whether to enable the conflict collaboration analysis module. If the task is urgent and requires a quick decision, G can choose not to enable the conflict collaboration analysis module and directly enter the task allocation step.

[0094] (3) Conflict Collaboration Analysis: If G chooses to enable the conflict collaboration analysis module, the system enters the conflict collaboration analysis step. This module makes full use of the information collection module to analyze all participants P i and R j Conduct in-depth analysis and comprehensive evaluation of attitudes on different issues or attributes, and provide comprehensive conflict collaboration analysis information.

[0095] For example, P1 expressed a positive attitude towards rapid rescue missions, P2 expressed hesitation about using robots, R1 possessed advanced image recognition technology, and R2 was good at olfactory detection.

[0096] (4) Intelligent analysis: Through the intelligent analysis module, P i and R jThe system calculates the attitude difference function, applies the three-branch decision theory to clarify the conflict and cooperation relationship, and provides decision support for task assignment.

[0097] (5) Capability assessment and task allocation: In the human-machine task allocation module, the capability assessment module collects and integrates information about P i and R j capability data to form a comprehensive human-machine capability assessment matrix.

[0098] For example, P1 has professional medical skills, P2 is a communications expert, R1 has advanced image recognition technology, and R2 is a sensitive olfactory robot.

[0099] (6) Task execution and feedback: Team T executes the task and verifies the execution performance through simulation.

[0100] For example, during the search and rescue phase, R1 uses advanced image recognition technology to transmit images of the disaster area in real time, R2 uses its sensitive sense of smell to detect the location of the victims, and P1 provides emergency medical assistance.

[0101] If the task execution results deviate from the expectations of G, the target object or the entire team, G has the right to reconsider whether to use the conflict collaboration analysis module to form a flexible iterative mechanism to optimize the overall collaboration system.

[0102] Therefore, the present invention adopts the above-mentioned intelligent human-machine collaboration system and method based on the E-CARGO model, which can realize intelligent task allocation and collaboration mechanism, making the collaboration between man and machine more efficient and intelligent, and can intelligently allocate tasks according to factors such as task requirements, user characteristics and real-time status, optimize the collaborative workflow, and improve the overall collaboration effect, thereby improving the overall system performance and user experience, and can be used in various occasions such as emergency response, industrial production, simulation training, etc.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. An intelligent human-machine collaboration system based on the E-CARGO model, characterized by: include: Human-machine task allocation module: used to analyze task attributes and executor capabilities, and to allocate and assign tasks for collaboration between humans and machines; The man-machine task allocation module comprises: Capability assessment module: used to assess the capability level of each entity, including humans and machines, in order to more accurately allocate tasks, optimize the collaboration process, and ensure the collaboration effect of the system under different conditions; Task assignment module: intelligently assigns tasks to different entities to maximize the efficiency and performance of the overall system; The task assignment module includes: Model optimization unit: Improve the accuracy and intelligence of the task assignment model by continuously adjusting E-CARGO model parameters, updating algorithms, and improving learning capabilities; Effectiveness Analysis Unit: Comprehensively analyze the actual effect of task assignment through evaluation of task completion, efficiency and user satisfaction; Conflict and collaboration analysis module: used to detect and resolve potential conflicts and collaborations between people and machines in terms of tasks and resources to optimize collaboration efficiency and system performance; The conflict collaboration analysis module includes: Information collection module: responsible for collecting relevant information from various entities, tasks and system environments; Intelligent analysis module: used to use the data provided by the information collection module to perform intelligent analysis on conflicts and collaborations occurring in the system; For the user set H in the human-machine collaboration scenario, there are two threshold sets α and β, where α k and β k Is user h k Two thresholds for evaluating the conflict and collaboration between people, machines, and people and machines, satisfying the condition: 0≤β k <α k ≤1; For user h k , a pair of x and y is defined as: (1) If d(x,y)≥α k , then it is a conflict; (2) If β k <d(x,y)<α k , then it is neutral; (3) If d(x,y)≤β k , then it is collaboration; Where x represents a human or a machine, y represents a human or a machine, and d(x, y) represents the distance or difference between objects x and y; An intelligent human-machine collaboration method based on the E-CARGO model based on the above system includes the following steps: S1: For several tasks, the manager selects multiple people and machines to perform tasks collaboratively, and sends the request to the intelligent human-machine collaboration system; S2: The manager independently chooses whether to consider human-machine conflict and collaboration factors in the system: if the conflict and collaboration analysis module is used, the process proceeds to step S3; if the conflict and collaboration analysis module is not used, the process proceeds to step S5; S3: In the conflict collaboration analysis module, the attitudes of all people and machines on different issues or attributes are analyzed and evaluated through the information collection module, and information is collected and conflict collaboration analysis information is given; S4: In the conflict and collaboration analysis module, the attitude information of all people and machines is summarized through the intelligent analysis module, and the attitude difference function between them is calculated. The conflict and collaboration relationships are divided according to the three-branch decision theory, and then the process goes to step S5; S5: In the human-machine task assignment module, the capability data of human operators and machine entities, including skill level, experience and education information, are collected through the capability assessment module, and a human-machine capability assessment matrix for different tasks is generated; S6: In the human-machine task allocation module, different optimization models and algorithms are constructed through the task assignment module according to the capability evaluation matrix and the E-CARGO model, the assignment results are obtained, and the execution performance is simulated and verified; S7: If the obtained human-machine collaborative task execution result is inconsistent with the general cognition of the manager, the target object or the entire team, then go back to step S2.

2. According to claim 1, an intelligent human-machine collaboration system based on the E-CARGO model is characterized by: The capability assessment modules include: Capability information description unit: This unit is used to describe and define the capability information of each entity. It is responsible for collecting, storing and maintaining detailed information about the capabilities of each entity. This information constitutes an entity capability description file, providing the system with a comprehensive understanding of the entity's capabilities. Capability information conversion unit: This unit is used to process and convert the collected capability information so that the system can better understand and utilize the information, combining the entity's historical performance with the current capabilities to more accurately reflect the entity's actual status.

Images