A human-machine collaborative digital twin system for scene resource management

By introducing a human-computer collaboration module into the digital twin system, the calculation of the abnormality index of human-computer data synchronization detection and the decision-making support effectiveness evaluation index is solved, and the problem of digital twin technology lacks intelligent interaction is achieved, and more efficient decision-making support and operational efficiency is achieved. Improve the intelligent interaction capabilities and overall efficiency of the system.

CN118747263BActive Publication Date: 2024-11-22JIANGSU ELECTRIC POWER INFORMATION TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411230336.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-04
Publication Date
2024-11-22
Estimated Expiration
2044-09-04

AI Technical Summary

Technical Problem

The existing digital twin technology lacks intelligent human-computer interaction capabilities and is unable to collaborate and interact with operators at a deep level, limiting its decision-making and optimization application efficiency in complex or uncertain situations.

Method used

A human-machine collaboration digital twin system for scene resource management is designed, including data collection module, data analysis module and human-machine collaboration module. Data is collected through sensors and user interfaces, and abnormality index is calculated for human-machine data synchronization detection, and decision-making support effectiveness evaluation. Index and interaction efficiency scores, automatic adjustment of parameters and user interface design, and optimize the human-computer collaboration process.

Benefits of technology

It improves the decision-making support capabilities and operational efficiency of the digital twin system, enhances the flexibility and intelligent interaction capabilities of the system, and ensures that optimized solutions and efficient user experience are provided in complex scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118747263B_ABST
    Figure CN118747263B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of artificial intelligence technology, and discloses a human-machine collaborative digital twin system for scene resource management, a data collection module, a data analysis module and a human-machine collaborative module. The data collection module includes a robot model unit, a human body model unit, a collaborative environment model unit and a collaborative relationship model unit. The data analysis module calculates a human-machine data synchronization detection anomaly index #imgabs0#, a decision support effectiveness evaluation index #imgabs1# and a human-machine interaction efficiency score #imgabs2#. By calculating the decision support effectiveness evaluation index #imgabs3#, it helps the system to comprehensively evaluate the effectiveness of decision support. The index not only helps monitor the real-time performance of the system, but also can evaluate the real-time performance of the system, thereby providing a direction for the improvement of the system, so as to enhance the intelligent interaction capability and overall effectiveness of the digital twin system in practical applications, ensure that the system can effectively support complex human-machine collaborative scenarios, and thus solve the problem that the existing digital twin technology lacks intelligent human-machine interaction capabilities.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and specifically to a human-machine collaborative digital twin system for scene resource management. Background Art

[0002] At present, digital twin technology shows great application potential and value, but its development still faces some key challenges. A significant problem is that the existing digital twin technology lacks intelligent human-computer interaction capabilities. Although digital twin systems can monitor and predict the status of physical entities in real time, they are usually unable to collaborate and interact with operators at a deep level, which limits their application efficiency in decision-making and optimization operations. This limitation is mainly because existing technologies rely mainly on automated data processing and analysis algorithms without fully considering the intuitive judgment and experiential knowledge of human experts. This leads to the situation that in complex or uncertain situations, the system may not provide the optimal solution, or its recommended strategy may be difficult for human operators to understand and accept.

[0003] Introducing intelligent human-computer interaction technology into digital twin systems will greatly enhance the decision-making support capabilities and operational efficiency of these systems. Through this human-computer collaboration, the experience and intuition of human experts can be used to make up for the shortcomings of existing algorithms, while supporting human decision-making through real-time data and predictive models, thereby optimizing operations and improving the flexibility of system responses. Summary of the invention

[0004] In view of the shortcomings of the existing technology, the present invention provides a human-computer collaborative digital twin system for scene resource management, which has the advantage of intelligent human-computer interaction capability and solves the problem that the existing digital twin technology lacks intelligent human-computer interaction capability.

[0005] To achieve the above-mentioned object, the present invention provides the following technical solutions: a human-machine collaborative digital twin system for scene resource management, comprising a data collection module, a data analysis module and a human-machine collaborative module;

[0006] The data collection module includes a robot model unit, a human body model unit, a collaborative environment model unit and a collaborative relationship model unit. The robot model unit collects robot model data through sensors and user interface interfaces, the human body model unit collects human body model data through interactive input devices and sensors, the collaborative environment model unit collects collaborative environment model data through monitoring devices and sensors, and the collaborative relationship model unit collects collaborative relationship model data through sensors and robot status monitoring. The robot model unit, human body model unit, collaborative environment model unit and collaborative relationship model unit are connected to the data analysis module through a network;

[0007] The data analysis module includes a data synchronization detection anomaly unit, a decision support effectiveness evaluation unit and an interaction efficiency scoring unit. The data synchronization detection anomaly unit calculates the human-machine data synchronization detection anomaly index based on the robot model data and the human body model data. The decision support effectiveness evaluation unit calculates the decision support effectiveness evaluation index according to the collaborative environment model data. The interaction efficiency scoring unit calculates the human-computer interaction efficiency score according to the collaborative relationship model data. The data synchronization anomaly detection unit, the decision support effectiveness evaluation unit and the interaction efficiency scoring unit are connected to the data management module through a network.

[0008] Preferably, the robot model unit numbers all robot model sensor data values ​​counted according to the robot model data characteristics, and the numbers of all robot model sensor data values ​​counted are: , , ,… .

[0009] Preferably, the human body model unit numbers all human body model sensor data values ​​counted according to the human body model data features, and the numbers of all human body model sensor data values ​​counted are: , , ,… .

[0010] Preferably, the data synchronization detection abnormality unit calculates the human-machine data synchronization detection abnormality index according to the robot model data and the human body model data. , and its calculation formula is:

[0011] ;

[0012] In the formula, Indicates the abnormal index of human-machine data synchronization detection, , , ,… Represents the statistical data values ​​of all robot model sensors. Represents the data value of the robot model sensor at a certain moment, Represents the average value of all robot model sensor data statistics, , , ,… Represents the statistical data values ​​of all human body model sensors, Represents the data value of the human body model sensor at a certain moment, Represents the statistical average value of all human body model sensor data.

[0013] Preferably, the collaborative environment model unit numbers the number of user inputs, the average response time of the system and the total interaction time according to the collaborative environment model data characteristics, and the number of user inputs, the average response time of the system and the total interaction time are numbered as follows: , , .

[0014] Preferably, the decision support effectiveness evaluation unit calculates the decision support effectiveness evaluation index according to the collaborative environment model data. , and its calculation formula is:

[0015] ;

[0016] In the formula, represents the decision support effectiveness evaluation index, , , They represent the number of user inputs, the average response time of the system, and the total interaction time respectively.

[0017] Preferably, the collaborative relationship model unit numbers the number of decisions correctly supported by the system and the total number of decisions according to the collaborative relationship model data characteristics, and the number of decisions correctly supported by the system and the total number of decisions are numbered as follows: , .

[0018] Preferably, the interaction efficiency scoring unit calculates the human-computer interaction efficiency score according to the collaborative relationship model data. , and its calculation formula is:

[0019] ;

[0020] In the formula, represents the human-computer interaction efficiency score, , They represent the number of decisions correctly supported by the system and the total number of decisions, respectively.

[0021] Preferably, the human-machine collaboration module synchronously detects anomaly index based on human-machine data The robot model unit and the human model unit are automatically guided to adjust the gain control, speed and acceleration limit parameters respectively based on the abnormal values.

[0022] Preferably, the human-machine collaboration module is based on the decision support effectiveness evaluation index To guide the collaborative environment model unit to adjust the user interface design, reduce the number of steps required for user operations, and then design smart prompts and automatic completion functions;

[0023] The human-computer interaction efficiency score To guide the collaborative relationship model unit to adjust and simplify the decision-making process, reduce the number of steps required by users in the decision-making process, and automate the processing of repetitive or standardized decisions.

[0024] Compared with the prior art, the present invention provides a human-machine collaborative digital twin system for scene resource management, which has the following beneficial effects:

[0025] 1. The data synchronization detection anomaly unit of the present invention calculates the human-machine data synchronization detection anomaly index by comparing the deviation of the robot and human sensor data from their respective average values. , this index can reflect the consistency and accuracy of data synchronization between the two in the process of human-machine collaboration. When low, it means that the data synchronization accuracy is high and the human-machine data synchronization detection abnormality index is It helps to evaluate the human-computer interaction capabilities of the digital twin system and thus optimize the system design.

[0026] 2. The present invention calculates the decision support effectiveness evaluation index , integrating the number of user inputs, the average response time of the system and the total interaction time into the calculation formula will help the system to comprehensively evaluate the effectiveness of decision support. This index not only helps monitor the real-time performance of the system, but also can evaluate the real-time performance of the system, thereby providing direction for system improvement, so as to enhance the intelligent interaction capabilities and overall effectiveness of the digital twin system in practical applications, and ensure that the system can effectively support complex human-computer collaboration scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic diagram of the structure of the present invention; DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] See also Figure 1 , a human-machine collaborative digital twin system for scene resource management, including a data collection module, a data analysis module and a human-machine collaborative module;

[0030] The data collection module includes a robot model unit, a human body model unit, a collaborative environment model unit and a collaborative relationship model unit. The robot model unit collects robot model data through sensors and user interface interfaces. The human body model unit collects human body model data through interactive input devices and sensors. The collaborative environment model unit collects collaborative environment model data through monitoring devices and sensors. The collaborative relationship model unit collects collaborative relationship model data through sensors and robot status monitoring. The robot model unit, the human body model unit, the collaborative environment model unit and the collaborative relationship model unit are connected to the data analysis module through a network. The corresponding model data of each unit is collected through sensors and user interface interfaces, which can ensure that the system can comprehensively obtain various types of data and provide a rich source of information for subsequent data analysis.

[0031] The data analysis module includes a data synchronization detection anomaly unit, a decision support effectiveness evaluation unit, and an interaction efficiency scoring unit. The data synchronization detection anomaly unit calculates the human-machine data synchronization detection anomaly index based on the robot model data and the human body model data. , the decision support effectiveness evaluation unit calculates the decision support effectiveness evaluation index based on the collaborative environment model data The interaction efficiency scoring unit calculates the human-computer interaction efficiency score based on the collaborative relationship model data. ,The synchronous abnormal detection unit, the decision support effectiveness evaluation unit and the interaction efficiency scoring unit are connected to the data management module through the network, and special analysis and processing are performed according to different types of data, so as to effectively identify and solve various problems in the human-machine collaboration process;

[0032] The robot model unit numbers all robot model sensor data values ​​according to the robot model data characteristics. The numbers of all robot model sensor data values ​​are , , ,… .

[0033] The human body model unit numbers all human body model sensor data values ​​counted according to the human body model data features, and the numbers of all human body model sensor data values ​​counted are , , ,… .

[0034] The data synchronization detection anomaly unit calculates the human-machine data synchronization detection anomaly index based on the robot model data and the human body model data. , and its calculation formula is:

[0035] ;

[0036] In the formula, Indicates the abnormal index of human-machine data synchronization detection, , , ,… Represents the statistical data values ​​of all robot model sensors. Represents the data value of the robot model sensor at a certain moment, Represents the average value of all robot model sensor data statistics, , , ,… Represents the statistical data values ​​of all human body model sensors, Represents the data value of the human body model sensor at a certain moment, Indicates the average value of all human model sensor data, and the abnormal index of human-machine data synchronization detection It can help the system determine whether there are data synchronization problems in the human-computer collaboration process, so as to take timely measures to adjust and optimize. At the same time, this calculation method can accurately reflect the actual situation of human-computer data synchronization and provide a reliable basis for anomaly detection.

[0037] The advantage is that the data synchronization detection anomaly unit calculates the human-machine data synchronization detection anomaly index by comparing the deviation of the robot and human sensor data from their respective average values. , this index can reflect the consistency and accuracy of data synchronization between the two in the process of human-machine collaboration. When low, it means that the data synchronization accuracy is high and the human-machine data synchronization detection abnormality index is It helps to evaluate the human-computer interaction capabilities of the digital twin system and thus optimize the system design.

[0038] The collaborative environment model unit numbers the number of user inputs, the average response time of the system, and the total interaction time according to the collaborative environment model data characteristics. The number of user inputs, the average response time of the system, and the total interaction time are numbered as , , .

[0039] The decision support effectiveness evaluation unit calculates the decision support effectiveness evaluation index based on the collaborative environment model data , and its calculation formula is:

[0040] ;

[0041] In the formula, represents the decision support effectiveness evaluation index, , , Respectively represent the number of user inputs, the average response time of the system and the total interaction time, and the decision support effectiveness evaluation index It can help the system evaluate whether the current decision support strategy is effective and provide a basis for subsequent decision adjustments.

[0042] Advantages: By calculating the decision support effectiveness evaluation index , integrating the number of user inputs, the average response time of the system and the total interaction time into the calculation formula will help the system to comprehensively evaluate the effectiveness of decision support. This index not only helps monitor the real-time performance of the system, but also can evaluate the real-time performance of the system, thereby providing direction for system improvement (increasing user-friendliness, improving system response speed and optimizing the interaction process) to enhance the intelligent interaction capabilities and overall effectiveness of the digital twin system in practical applications, and ensure that the system can effectively support complex human-computer collaboration scenarios.

[0043] The collaborative relationship model unit numbers the number of decisions correctly supported by the system and the total number of decisions according to the collaborative relationship model data characteristics. The number of decisions correctly supported by the system and the total number of decisions are numbered as follows: , .

[0044] The interaction efficiency scoring unit calculates the human-computer interaction efficiency score based on the collaborative relationship model data. , and its calculation formula is:

[0045] ;

[0046] In the formula, represents the human-computer interaction efficiency score, , Respectively represent the number of decisions correctly supported by the system and the total number of decisions, and the human-computer interaction efficiency score It can help the system understand the efficiency level of human-machine collaboration, so as to optimize and improve the collaborative relationship model unit in a targeted manner.

[0047] Advantages: By calculating the human-computer interaction efficiency score , to compare the ratio of the number of decisions correctly supported by the system to the total number of decisions, and obtain a comprehensive score of the efficiency and accuracy of the interaction between the system and people. The higher the value, the higher the effectiveness of the system's human-computer interaction, the stronger the system's intelligent support capabilities, and the better the user experience. At the same time, in this way, the calculation formula of the interaction efficiency scoring unit helps users understand the performance of the system in actual operation, and can also provide a specific basis for optimizing the system's decision support mechanism and improving the quality of human-computer interaction, making it an important tool for system evaluation of human-computer collaboration efficiency in digital twin technology.

[0048] The human-machine collaboration module synchronously detects abnormal index based on human-machine data The robot model unit and the human model unit are automatically guided to adjust the gain control, speed and acceleration limit parameters respectively based on the abnormal values.

[0049] Human-machine collaboration module based on decision support effectiveness evaluation index To guide the collaborative environment model unit to adjust the user interface design, reduce the number of steps required for user operations, reduce the probability of errors, improve the efficiency of data input, and redesign smart prompts and automatic completion functions to reduce the user's cognitive load and accelerate the decision-making process;

[0050] Human-computer interaction efficiency score To guide the collaborative relationship model unit to adjust and simplify the decision-making process, reduce the number of steps required by users in the decision-making process, reduce the response time of the system, enable users to make decisions faster, and realize automated processing for repetitive or standardized decisions, reduce the burden on users, and improve overall decision-making efficiency.

[0051] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A human-machine collaborative digital twin system for scene resource management, characterized by: Including data collection module, data analysis module and human-computer collaboration module; The data collection module includes a robot model unit, a human body model unit, a collaborative environment model unit and a collaborative relationship model unit, the robot model unit collects robot model data through sensors and a user interface, the human body model unit collects human body model data through an interactive input device and a sensor, the collaborative environment model unit collects collaborative environment model data through a monitoring device and a sensor, the collaborative relationship model unit collects collaborative relationship model data through sensors and robot status monitoring, and the robot model unit, the human body model unit, the collaborative environment model unit and the collaborative relationship model unit are connected to the data analysis module through a network; The data analysis module includes a data synchronization detection anomaly unit, a decision support effectiveness evaluation unit and an interaction efficiency scoring unit. The data synchronization detection anomaly unit calculates the human-machine data synchronization detection anomaly index Ep based on the robot model data and the human body model data. The decision support effectiveness evaluation unit calculates the decision support effectiveness evaluation index Vp based on the collaborative environment model data. The interaction efficiency scoring unit calculates the human-machine interaction efficiency score Sp based on the collaborative relationship model data. The data synchronization detection anomaly unit, the decision support effectiveness evaluation unit and the interaction efficiency scoring unit are connected to the data management module via a network. The robot model unit numbers all robot model sensor data values ​​according to the robot model data characteristics, and the robot model sensor data values ​​are numbered as R1, R2, R3, ..., R n; The human body model unit numbers all human body model sensor data values ​​counted according to the human body model data features, and the numbers of all human body model sensor data values ​​counted are Rp1, Rp2, Rp3, ..., Rp n; The data synchronization detection anomaly unit calculates the human-machine data synchronization detection anomaly index Ep based on the robot model data and the human body model data, and its calculation formula is: In the formula, Ep represents the human-machine data synchronization detection anomaly index, R1, R2, R3, ... R n Represents the statistical data values ​​of all robot model sensors, R i Represents the data value of the robot model sensor at a certain moment, Represents the average value of all robot model sensor data, Rp1, Rp2, Rp3, ... Rp n Represents the statistical data values ​​of all human body model sensors, Rp i Represents the data value of the human body model sensor at a certain moment, Represents the statistical average value of all human body model sensor data; The collaborative environment model unit numbers the number of user inputs, the average response time of the system and the total interaction time according to the collaborative environment model data characteristics. The number of user inputs, the average response time of the system and the total interaction time are numbered as M, T1, T2, T3 and T4. 2; The decision support effectiveness evaluation unit calculates the decision support effectiveness evaluation index Vp based on the collaborative environment model data, and its calculation formula is: In the formula, Vp represents the decision support effectiveness evaluation index, M, T1, and T2 represent the number of user inputs, the average response time of the system, and the total interaction time, respectively; The collaborative relationship model unit numbers the number of decisions correctly supported by the system and the total number of decisions according to the collaborative relationship model data characteristics. The number of decisions correctly supported by the system and the total number of decisions are numbered as C, C 1; The interaction efficiency scoring unit calculates the human-computer interaction efficiency score Sp according to the collaborative relationship model data, and its calculation formula is: In the formula, Sp represents the human-computer interaction efficiency score, C and C1 represent the number of decisions correctly supported by the system and the total number of decisions, respectively.

2. The human-machine collaborative digital twin system for scene resource management according to claim 1, characterized in that: The human-machine collaboration module synchronously detects abnormal values ​​of the abnormality index Ep based on human-machine data, and automatically guides the robot model unit and the human body model unit to adjust the gain control, speed and acceleration limit parameters respectively.

3. The human-machine collaborative digital twin system for scene resource management according to claim 1 is characterized in that: The human-machine collaboration module guides the collaborative environment model unit to adjust the user interface design based on the decision support effectiveness evaluation index Vp, reduce the number of steps required for user operations, and then design intelligent prompts and automatic completion functions; The human-computer interaction efficiency score Sp is used to guide the collaborative relationship model unit to adjust and simplify the decision-making process, reduce the number of steps required by the user in the decision-making process, and realize automated processing for repetitive or standardized decisions.