CN115620888A

CN115620888A - Digital twin-based surgical robot monitoring method, device and system

Info

Publication number: CN115620888A
Application number: CN202211387536.4A
Authority: CN
Inventors: 请求不公布姓名; 朱祥
Original assignee: Shanghai Microport Medbot Group Co Ltd
Current assignee: Shanghai Microport Medbot Group Co Ltd
Priority date: 2022-11-07
Filing date: 2022-11-07
Publication date: 2023-01-17

Abstract

The specification relates to the technical field of medical robots, and particularly discloses a digital twin-based surgical robot monitoring method, device and system, wherein the method is applied to a hospital monitoring system and comprises the following steps: acquiring robot part operation data of a robot system; analyzing the robot part operation data, and fusing the robot part operation data into a corresponding robot part model to perform digital twin operation processing to obtain a part simulation operation result; and integrating the simulation operation result of the part into a complete robot model to perform digital twin operation processing so as to perform early warning monitoring on a robot system. In the embodiment of the specification, the robot part and the whole machine model data are managed in the hospital monitoring system, and the whole robot system can be monitored and early warned only by acquiring the part operation data in the monitoring process, so that the accuracy of a digital model can be improved, and the monitoring reliability is guaranteed.

Description

Digital twin-based surgical robot monitoring method, device and system

Technical Field

The present disclosure relates to the field of surgical robot technologies, and in particular, to a method, an apparatus, and a system for monitoring a surgical robot based on digital twins.

Background

At present, the operation data of the surgical robot is generally collected locally, the collected operation data is transmitted to a cloud server through a network for data analysis, and data modeling and digital twin body simulation operation are performed through cloud computing so as to monitor the operation state of a virtual model, and further realize monitoring and early warning of the surgical robot. Generally, a whole operation and maintenance model is constructed by taking a surgical robot as a main body, and when a new surgical robot appears or a large version of the surgical robot is iterated, the surgical robot model needs to be adjusted greatly. When the surgical robot is monitored, efficient data acquisition and transmission are needed, so that the equipment monitoring and early warning can be better realized, and the stable and safe operation can be ensured.

However, because the operating room is relatively closed, the network is delayed or even disconnected, and the requirement of high-efficiency data transmission cannot be met frequently; the operation data of the whole equipment is transmitted through the network in the operation, so that the safety risk exists, and once the operation data of the equipment is hijacked, the operation also has the safety risk. The existing early warning mechanism of the robot depends on experience and algorithm calculation at a certain stage, and inaccuracy may exist in a digital twin body data model of the robot in actual operation. A large amount of data calculation is completed on the cloud platform, which undoubtedly increases the operation pressure of the server, and the requirement for server configuration is increased, thereby causing the maintenance cost of the server to be increased. Moreover, after a new robot product is updated, the digital model mainly comprising the complete robot needs complex verification tests and operation parameter adjustment and optimization, and time and cost are needed for adjusting the digital twin model of the robot. In addition, the monitoring and analyzing report of the robot is often an analysis demonstration for a certain stage, and the early warning analysis for the whole life cycle is lacked.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The embodiment of the specification provides a digital twin-based surgical robot monitoring method, device and system, and aims to solve the problem that model adjustment is difficult after part updating iteration when a whole operation and maintenance model is built by taking a surgical robot as a main body in the prior art.

The embodiment of the specification provides a surgical robot monitoring method based on digital twins, which is applied to a hospital monitoring system and comprises the following steps: acquiring robot part operation data of a robot system; analyzing the robot part operation data, and fusing the robot part operation data into a corresponding robot part model to perform digital twin operation processing to obtain a part simulation operation result; and integrating the simulation operation result of the part into a complete robot model to perform digital twin operation processing so as to perform early warning monitoring on a robot system.

In one embodiment, acquiring robot component operational data for a robotic system comprises: and acquiring the robot component operation data of the robot system through the local area network.

In one embodiment, before acquiring the robot component operation data of the robot system, the method further comprises: splitting the components of the robot system to obtain a plurality of robot components; acquiring component operation data and component parameters corresponding to each of the plurality of robot components; performing digital twin model training based on the component operation data and the component parameters corresponding to each robot component to obtain a robot component model corresponding to each robot component; and storing the robot part models corresponding to the robot parts into a local part model library corresponding to the robot parts.

In one embodiment, before acquiring the robot component operation data of the robot system, the method further comprises: the method comprises the steps of splitting a robot system to obtain a plurality of robot part operation data; matching the robot component operation data in the robot component operation data with robot component models in a local component model library to obtain robot component models corresponding to the robot component operation data; constructing a complete machine digital twin model based on the robot part model corresponding to the operation data of each robot part to obtain a robot complete machine model corresponding to the surgical robot; and storing the robot complete machine model to a local complete machine model library corresponding to the robot system.

In one embodiment, the step of merging the simulation operation result of the part into a complete robot model to perform digital twin operation processing so as to perform early warning monitoring on a robot system includes: integrating the part simulation operation result into a robot complete machine model to perform digital twin operation processing to obtain a complete machine simulation operation result; and generating early warning information under the condition that the complete machine simulation operation result meets a preset condition.

In one embodiment, after generating the warning information, the method further comprises: inquiring decision feedback information corresponding to the early warning information; and returning the decision feedback information and the early warning information to the robot system.

In one embodiment, after analyzing the robot component operating data and integrating the robot component operating data into a robot component model to perform digital twin operation processing to obtain a component simulation operation result, the method further includes: model derivation is carried out based on the part simulation operation result to obtain an updated robot part model and a robot complete machine model; and storing the updated robot part model and the updated robot complete machine model into a corresponding local part model library and a corresponding local complete machine model library.

In one embodiment, after model derivation is performed based on the result of the part simulation operation to obtain an updated robot part model and a robot complete machine model, the method further includes: constructing a data-driven model based on the robot component operating data; and early warning and monitoring the robot system by using the data driving model, the updated robot part model and the updated robot complete machine model.

In one embodiment, after model derivation is performed based on the result of the part simulation operation to obtain an updated robot part model and a robot complete machine model, the method further includes: and uploading the updated robot part model and the updated robot complete machine model to a cloud server platform, so that the cloud server platform performs fusion processing on the robot part model and the robot complete machine model to obtain a robot part total model and a robot complete machine total model.

In one embodiment, before analyzing the robot component operating data and integrating the analyzed data into a corresponding robot component model to perform digital twin operation processing, and obtaining a component simulation operation result, the method further includes: querying a robot part total model and a robot complete machine total model corresponding to the robot system from a cloud part model library of the cloud server platform to determine whether the robot part total model and/or the robot complete machine total model corresponding to the robot system is updated;

and under the condition that the total robot part model and/or the total robot whole model corresponding to the robot system are/is determined to be updated, acquiring the updated total robot part model and storing the updated total robot part model into a local part model library, and acquiring the updated total robot whole model and storing the updated total robot whole model into the local whole model library.

In one embodiment, the cloud server platform performs fusion processing on the robot part model and the robot complete machine model to obtain a robot part total model and a robot complete machine total model, and the method includes: the cloud server platform performs fusion processing on the received robot component models uploaded by the plurality of hospital monitoring systems to obtain a first fusion component total model; fusing the first fusion part total model with a corresponding robot part total model stored in the cloud server platform to obtain and store a target robot part total model; the cloud server platform performs fusion processing on the received robot complete machine models uploaded by the plurality of hospital monitoring systems to obtain a first fusion complete machine total model; and carrying out fusion processing on the first overall fusion model and the corresponding overall robot model stored in the cloud server platform to obtain and store a target overall robot model.

In one embodiment, after the cloud server platform performs fusion processing on the robot part model and the robot complete machine model to obtain a robot part total model and a robot complete machine total model, the method further includes: the cloud server platform generates a model analysis report corresponding to the robot part model and the robot complete machine model based on the fusion processing process information; and the cloud server platform returns the model analysis report to the hospital monitoring system.

The embodiment of the specification further provides a surgical robot monitoring device based on digital twins, which is applied to a hospital monitoring system and comprises: the acquisition module is used for acquiring robot component operation data of the robot system; the simulation module is used for analyzing the robot part operation data and integrating the robot part operation data into a corresponding robot part model to perform digital twin operation processing to obtain a part simulation operation result; and the monitoring module is used for fusing the simulation operation result of the part into a complete machine model of the robot to perform digital twin operation processing so as to perform early warning monitoring on the robot system.

The embodiment of the specification further provides a digital twin-based surgical robot monitoring system, which comprises a robot system, a hospital monitoring system and a cloud server platform; the robot system is used for collecting robot part operation data of the surgical robot and sending the robot part operation data to the hospital monitoring system through a local area network; the hospital monitoring system is used for analyzing the robot component operation data and integrating the robot component operation data into a corresponding robot component model to perform digital twin operation processing to obtain a component simulation operation result; the system is also used for integrating the simulation operation result of the part into a complete machine model of the robot to carry out digital twin operation processing so as to carry out early warning monitoring on a robot system; the cloud server platform is used for receiving a robot part model and a robot complete machine model uploaded by a hospital monitoring system; and the method is also used for carrying out fusion processing on the robot part model and the robot complete machine model to obtain a robot part total model and a robot complete machine total model.

Embodiments of the present specification further provide a medical device comprising a processor and a memory for storing processor-executable instructions, which when executed by the processor implement the steps of the digital twin-based surgical robot monitoring method described in any of the above embodiments.

Embodiments of the present specification further provide a computer readable storage medium having stored thereon computer instructions which, when executed, implement the steps of the digital twinning-based surgical robot monitoring method described in any of the embodiments above.

In the embodiment of the specification, a digital twin-based surgical robot monitoring method is provided, and a hospital monitoring system can acquire robot component operation data of a robot system; analyzing the robot part operation data, and fusing the robot part operation data into a corresponding robot part model to perform digital twin operation processing to obtain a part simulation operation result; and integrating the simulation operation result of the part into a complete robot model to perform digital twin operation processing so as to perform early warning monitoring on a robot system. According to the scheme, the robot parts and the whole machine model data are managed in the hospital monitoring system, the whole machine of the robot system can be monitored and early warned only by acquiring the part operation data in the monitoring process, the accuracy of the digital twin model can be improved, and the monitoring reliability is guaranteed. In addition, the robot part and the whole machine model data are stored in the hospital monitoring system, so that when the robot part is updated and iterated, the updated robot system can be early-warned and monitored only by adding a new part model, and the hospital monitoring system is convenient to operate and low in cost. In addition, by establishing the internal monitoring system of the hospital, the local network resources and the edge computing capacity of the hospital can be fully utilized, the high efficiency of data transmission is improved, and the efficiency and the real-time performance of robot monitoring are further improved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the specification, are incorporated in and constitute a part of this specification, and are not intended to limit the specification. In the drawings:

FIG. 1 illustrates a flow chart of a digital twin based surgical robot monitoring method in one embodiment of the present description;

FIG. 2 shows a schematic diagram of the results of the robotic system in one embodiment of the present description;

FIG. 3 illustrates an operational scenario diagram of a hospital monitoring system in one embodiment of the present description;

FIG. 4 illustrates a robot digital twin monitoring interaction diagram in an embodiment of the present description;

FIG. 5 illustrates a schematic diagram of a local robot component model generation in one embodiment of the present description;

FIG. 6 is a schematic diagram illustrating a local robot complete machine model generation in an embodiment of the present disclosure;

FIG. 7 illustrates a hospital monitoring system decision feedback flow diagram in one embodiment of the present description;

FIG. 8 illustrates a schematic diagram of a robot digital twin monitoring in one embodiment of the present description;

FIG. 9 illustrates a flow diagram for simulation of a robotic component in one embodiment of the present description;

FIG. 10 is a flow diagram illustrating the derivation of a local parts model in one embodiment of the subject specification;

FIG. 11 illustrates a robot simulation queue diagram in one embodiment of the present description;

FIG. 12 is a flowchart illustrating the whole machine model simulation evolution process in one embodiment of the specification;

FIG. 13 is a flow chart illustrating the development of a hospital complete machine model according to an embodiment of the present disclosure;

FIG. 14 is a diagram illustrating an overall data flow process in one embodiment of the present description;

FIG. 15 is a diagram illustrating an overall data flow process in one embodiment of the subject specification;

FIG. 16 is a schematic diagram illustrating cloud model fusion in one embodiment of the present disclosure;

fig. 17 is a flow diagram illustrating cloud component model data processing in one embodiment of the present description;

fig. 18 is a data processing flow diagram of a cloud whole machine model in an embodiment of the present specification;

figure 19 illustrates a flow diagram of a hospital monitoring system download synchronization cloud model in one embodiment of the present description;

FIG. 20 illustrates an overall flow diagram of the hospital monitoring system in one embodiment of the present description;

FIG. 21 is a flow diagram illustrating cloud-based intelligent report analysis in one embodiment of the present description;

FIG. 22 shows a schematic view of a digital twin based surgical robotic monitoring device in one embodiment of the present description;

FIG. 23 shows a schematic view of a digital twin based surgical robotic monitoring system in one embodiment of the present description;

FIG. 24 illustrates an overall system architecture diagram of a digital twinning based surgical robotic monitoring system in one embodiment of the present description;

FIG. 25 is a diagram showing a system configuration of a twin hospital server in one embodiment of the present specification;

FIG. 26 is a diagram illustrating a cloud twin server system architecture in one embodiment of the present description;

fig. 27 shows a schematic view of a medical device in an embodiment of the present description.

Detailed Description

The principles and spirit of the present description will be described with reference to a number of exemplary embodiments. It is understood that these embodiments are given solely to enable those skilled in the art to better understand and to implement the present description, and are not intended to limit the scope of the present description in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

As will be appreciated by one skilled in the art, embodiments of the present description may be embodied as a system, apparatus, device, method, or computer program product. Accordingly, the present disclosure may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.

The embodiment of the specification provides a digital twinning-based surgical robot monitoring method. Fig. 1 shows a flow chart of a digital twin-based surgical robot monitoring method in one embodiment of the present description. Although the present specification provides method steps or apparatus structures as shown in the following examples or figures, more or fewer steps or modules may be included in the method or apparatus based on conventional or non-inventive efforts. In the step or structure in which the necessary cause and effect relationship does not logically exist, the execution sequence of the steps or the module structure of the apparatus is not limited to the execution sequence or the module structure described in the embodiment of the present specification and shown in the drawings. When the described methods or modular structures are applied in a practical device or end product, they can be executed sequentially or in parallel according to the embodiments or the methods or modular structures shown in the figures (for example, in the environment of parallel processors or multi-thread processing, or even in the environment of distributed processing).

Specifically, as shown in fig. 1, a digital twin-based surgical robot monitoring method provided by an embodiment of the present specification may include the following steps:

and step S101, acquiring robot component operation data of the robot system.

The method in this embodiment may be applied to a hospital monitoring system. The hospital monitoring system can monitor and early warn various surgical robot systems in the local of a hospital. The hospital monitoring system may include a local digital twin server that may perform digital twin calculations.

The hospital monitoring system may acquire robot component operational data of the robotic system. The robot system may include a surgical robot system, and may also include other robot systems in a hospital, which is not limited in this specification.

Referring to fig. 2, a schematic diagram of the result of the robotic system involved in the embodiments of the present description is shown. As shown in fig. 2, the robot system in the present embodiment is a surgical robotic surgeon console, including: the system comprises a collecting terminal device 201, an endoscope three-dimensional image display 202, a robot operating arm 203, a robot system operating touch screen 204 and a robot pedal 205. The acquisition terminal device 201 of the robot is used for acquiring operation data of robot parts and directly transmitting the operation data to a hospital monitoring system in a network cable direct connection mode.

In this embodiment, the robotic component may include multiple components in a robotic system. When the robot component is a master control arm, the operation data of the master control arm may include: the motion track data of the main control arm, the joint use time of the main control arm, the motion distance of the guide rail, the gear rotation time, the joint stress data and other various operation data. When the robot component is a pedal, the running data of the pedal can comprise data such as the using times and the using duration of the pedal. Where the robotic component is an endoscope, the operational data of the endoscope may include a length of time the endoscope is in use. The above robot parts are merely exemplary, and the present specification is not limited thereto.

And S102, analyzing the operation data of the robot part, and integrating the operation data into a corresponding robot part model to perform digital twin operation processing to obtain a part simulation operation result.

After obtaining the robotic component operational data, the hospital inspection system may parse the robotic component operational data. In particular, the hospital detection system may parse the robotic component operational data into a form that can be processed by digital twinning. The robot part operational data may include operational data of each of the plurality of robot parts. Each robot component operation data may also include a component identifier. The hospital monitoring system may extract the robot component models from the corresponding component model library according to the component identifications in the operational data of each robot component. And then, the hospital monitoring system can fuse the analyzed operation data of each robot component into the corresponding robot component model to perform digital twin operation processing, so as to obtain a component simulation operation result corresponding to the operation data of each robot component.

And S103, integrating the simulation operation result of the part into a complete robot model to perform digital twin operation processing so as to perform early warning monitoring on a robot system.

The hospital monitoring system locally comprises a local complete machine model library. The robot component operating data may also include a robot system identification. The hospital monitoring system can obtain a robot complete machine model corresponding to the system identification. After the part simulation operation results corresponding to the operation data of each robot part are obtained, the part simulation operation results corresponding to each robot part can be merged into the corresponding robot complete machine model to obtain the robot complete machine simulation operation results. The robot system can be early-warned and monitored based on the simulation operation result of the whole robot.

Referring to fig. 3, an operation scenario diagram of the hospital monitoring system involved in the embodiment of the present specification is shown. As shown in fig. 3, the hospital monitoring system may include a local digital twin server and a model operation visualization device. The local digital twin server is deployed in a hospital operation informatization computer room and is used for receiving operation data information and equipment parameter information uploaded by different robot equipment in a hospital; and carrying out local digital twin operation to obtain a model operation result, and carrying out monitoring and early warning on the equipment according to the result. The model operation visualization device can be provided for robot operation and maintenance personnel for terminal display of the operation result of the digital twin model. The method in the embodiment can be applied to a local digital twin server in a hospital monitoring system.

Referring to fig. 4, a robot digital twin monitoring interaction diagram in the present embodiment is shown. As shown in fig. 4, a data interaction diagram between the real physical device and the digital twin is shown, the robot physical device uploads device parameters and operation data to the digital twin server, and model data are fed back to the robot digital twin through simulation operation processing, so that the monitoring effect of the real physical device is achieved.

In the embodiment, the robot parts and the whole machine model data are managed in the hospital monitoring system, and the whole robot system can be monitored and early warned only by acquiring the part operation data in the monitoring process, so that the accuracy of the digital twin model can be improved, and the monitoring reliability is guaranteed. In addition, the robot part and the whole machine model data are stored in the hospital monitoring system, so that when the robot part is updated and iterated, the updated robot system can be early-warned and monitored only by adding a new part model, and the hospital monitoring system is convenient to operate and low in cost. In addition, by establishing the internal monitoring system of the hospital, the local network resources and the edge computing capacity of the hospital can be fully utilized, the high efficiency of data transmission is improved, and the monitoring efficiency and the real-time performance of the robot are further improved.

In view of the need for efficient data acquisition and transmission when monitoring a surgical robot, in some embodiments of the present disclosure, acquiring robot component operating data of a robot system may include: and acquiring the robot component operation data of the robot system through a local area network. By establishing the internal monitoring system of the hospital, the local network resources and the edge computing capability of the hospital can be fully utilized, the high efficiency of data transmission is improved, and the monitoring efficiency and the real-time performance of the robot are further improved.

In some embodiments of the present description, before acquiring the robot component operation data of the robot system, the method may further include: splitting the components of the robot system to obtain a plurality of robot components; acquiring component operation data and component parameters corresponding to each of the plurality of robot components; performing digital twin model training based on the component operation data and the component parameters corresponding to each robot component to obtain a robot component model corresponding to each robot component; and storing the robot part models corresponding to the robot parts into a local part model library corresponding to the robot parts.

Referring to fig. 5, a schematic diagram of local robot part model generation in the present embodiment is shown. As shown in fig. 5, the part can be separated in the a-type robot system No.1, and the robot system can be separated into different parts to obtain a robot part 01, a robot part 02, \ 8230 \ 8230;, and a robot part n. The splitting refers to splitting of a concept level in a monitoring process, and multi-level splitting is required for multi-level component information, and only the highest-level component model construction is explained and explained in the specification. And then, acquiring part operation data and parameter data, training a part model, developing a single part model library by using an AI algorithm and machine learning through the part operation data and the part parameter information of the robot part to obtain a model corresponding to each part, and updating the model of each part to the model library corresponding to each part, such as a part 01 model library, a part 02 model library, \\ 8230, an 8230and a part n model library. By the mode, the robot can be split in multiple levels to obtain multiple parts, and part models are trained to obtain models corresponding to the parts.

In some embodiments of the present description, before acquiring the robot component operation data of the robot system, the method may further include: the method comprises the steps of splitting a robot system to obtain a plurality of robot part operation data; matching the robot component operation data in the robot component operation data with robot component models in a local component model library to obtain robot component models corresponding to the robot component operation data; constructing a complete machine digital twin model based on the robot part model corresponding to the operation data of each robot part to obtain a robot complete machine model corresponding to the surgical robot; and storing the robot complete machine model to a local complete machine model library corresponding to the robot system.

Referring to fig. 6, a schematic diagram of generating a local robot complete machine model in this embodiment is shown. As shown in fig. 6, the part can be separated in the a-type robot system No.2, and the robot system can be separated into different parts to obtain a robot part 01, robot parts 02, \8230 \ and a robot part n. And then matching the component module library, matching the split component data in the local model database according to the type of the split component data, finding the component model data with the highest matching degree, and transmitting the component model data to the whole machine model building module. And aiming at the matched part model data, splicing and combining the whole machine model data, configuring the personalized parameters of the robot to construct the whole machine model data of the robot of the same type, and obtaining a No.2 whole machine model. And then, the data of the complete machine model can be fed back to the robot system for reference, and the complete machine model can be stored in a complete machine model library corresponding to the robot system. Through the method, a local complete machine model library can be established.

In some embodiments of the present specification, the merging the simulation operation result of the component into the complete robot model to perform digital twin operation processing to perform early warning monitoring on the robot system may include: integrating the part simulation operation result into a robot complete machine model to perform digital twin operation processing to obtain a complete machine simulation operation result; and generating early warning information under the condition that the complete machine simulation operation result meets a preset condition.

Specifically, the hospital monitoring system can fuse the part simulation operation result into the robot complete machine model to perform digital twin operation processing, so as to obtain a complete machine simulation operation result. Whether the early warning information is generated can be determined according to the operation result of the complete machine simulation. In one embodiment, the operation result of the complete machine simulation may include the using time of the endoscope, and when the using time of the endoscope exceeds the preset time, the corresponding early warning information may be generated. In another embodiment, the simulation operation result of the whole machine may include the number of times of pedaling, and when the number of times of pedaling exceeds a preset number, corresponding warning information may be generated. In another embodiment, the operation result of the complete machine simulation may include a rotation angle of the main control arm, and when the rotation angle of the main control arm exceeds a preset angle range, corresponding warning information may be generated. By the mode, the robot system can be monitored and early warned based on the result of the complete machine simulation operation.

In some embodiments of the present specification, after generating the warning information, the method may further include: inquiring decision feedback information corresponding to the early warning information; and returning the decision feedback information and the early warning information to the robot system. Specifically, a corresponding relation table between the early warning information and the decision feedback information can be stored in the hospital monitoring system. After the early warning information is generated, the hospital monitoring system can inquire decision feedback information corresponding to the early warning information. The decision feedback information may be a recommendation for an early warning. The hospital monitoring system can return decision feedback information and early warning information to the robotic system. Under the condition that the decision feedback information corresponding to the early warning information is not found, the hospital monitoring system can feed the early warning information back to the operation and maintenance personnel, and the operation and maintenance personnel can customize the decision feedback information corresponding to the early warning information and return the early warning information and the corresponding decision feedback information to the robot system. The hospital monitoring system can also store the newly added decision feedback information into the corresponding relation table for real-time updating. By the mode, the early warning information and the decision feedback information can be fed back to the robot system.

Referring to fig. 7, a decision feedback flow chart of the hospital monitoring system in the embodiment of the present specification is shown. As shown in fig. 7, by acquiring the operation data of the whole machine model and the total model information of the local component, and taking the calculation result of the component model as a standard, the whole machine model is subjected to machine learning training, so as to acquire the latest training result of the whole machine model, and store the latest training result of the whole machine model in the local database. And generating early warning information under the condition that the operation result of the whole machine model is abnormal, inquiring corresponding processing measures and suggestions, and if the corresponding processing measures and suggestions are inquired, informing and feeding back the robot system. If the query is received, the information is sent to operation and maintenance personnel, and notification feedback is carried out on the robot system after the processing measures are customized. And then, locally storing the complete machine model data.

Referring to fig. 8, a schematic diagram of robot digital twin monitoring in an embodiment of the present description is shown. As shown in FIG. 8, a component pre-warning condition of a component foot switch apparatus is shown. The model of the foot switch can feed back the running state of the current component through three different color transformations; the yellow representative part has early warning information and does not influence the overall operation of the equipment; red represents that the parts have major problems at present, and has risks for the complete machine operation of the equipment and the implementation of the operation; green represents the normal state of the part; the operation and maintenance personnel move to check the running state information of different parts on the 3D visual platform through a mouse, and if the running state information is displayed on the right side as a running log of a foot switch, the service life of the foot switch and the like; the operation and maintenance personnel are helped to better know the operation condition information of the current equipment.

In some embodiments of this specification, after analyzing the robot component operation data and merging the analyzed robot component operation data into a robot component model to perform digital twin operation processing to obtain a component simulation operation result, the method may further include: model derivation is carried out based on the part simulation operation result to obtain an updated robot part model and a robot complete machine model; and storing the updated robot part model and the updated robot complete machine model into a corresponding local part model library and a corresponding local complete machine model library.

Referring to fig. 9, a flow chart of a simulation development of a robot component in an embodiment of the present disclosure is shown. As shown in fig. 9, the hospital monitoring system may receive robot component operation data reported by the robot system, and the robot component operation data is preprocessed for subsequent component model operation. And (4) simulating the component model, namely performing simulation operation on the received component operation data information, and adding an operation result into a queue for processing. And (4) carrying out simulation result queue processing, namely carrying out queue processing on the simulation results, and waiting for part development and whole machine model simulation operation. The part model derivation refers to the derivation updating of the part module according to the part simulation result. Referring to FIG. 10, a flow chart of the local part model derivation according to the present invention is shown. As shown in fig. 10, data is received from the component model simulation queue, and parameters in the component model are adjusted according to abnormal simulation result data, or parameters can be adjusted manually, so as to obtain better component module data; when the part simulation queue is not empty, the process is repeatedly executed, and the evolution updating of the part model is completed. The abnormal result refers to the abnormal result which is the abnormal result of the operation result of the part but does not influence the use of the whole machine. Referring to fig. 11, a schematic diagram of a robot simulation queue according to an embodiment of the present invention is shown. As shown in FIG. 11, the results of the simulation operations may be queued to wait for the development of the complete machine simulation operations and part models. After the part model is developed, the model parameters may be adjusted. The model parameters may include the lifetime, number of uses, or other similar parameters of the component.

Referring to FIG. 12, a flowchart of the simulation derivation of the complete machine model according to the embodiment of the present invention is shown. As shown in fig. 12, the operation processing of the whole model can be completed by obtaining the derived part model data simulation operation result; respectively carrying out an AI evolution process and an anomaly monitoring process of the whole machine model after obtaining a simulation operation result of the whole machine; and judging and analyzing the operation result of the whole machine model, sending an abnormal result to the robot system to complete monitoring and alarming, and simultaneously transmitting the abnormal result to the decision feedback module to make a solution. Referring to fig. 13, a flowchart of developing a complete hospital model according to an embodiment of the present invention is shown. As shown in fig. 13, by acquiring the operation data of the whole machine model and the total model information of the local component, the whole machine model is subjected to machine learning training with the result of the component model operation as the standard, so as to acquire the latest training result of the whole machine model, and store the latest training result in the local database. By the method, the component model and the complete machine model can be developed, the accuracy of the models can be ensured, and the precision of early warning monitoring is further improved.

In some embodiments of the present specification, after performing model derivation based on the result of the part simulation operation to obtain an updated robot part model and a robot complete machine model, the method may further include: constructing a data-driven model based on the robot component operating data; and early warning and monitoring the robot system by using the data driving model, the updated robot part model and the updated robot complete machine model.

Specifically, after the model is developed, a more complete robot part model and a complete robot model can be obtained. After obtaining the quantity of component operational data, a data driven model may be constructed based on the quantity of component operational data. The data-driven model can realize the mapping between the physical entity object and the digital world model object, including the state change caused by model, behavior logic, business process and parameter adjustment, and the like, and realizes the comprehensive presentation, accurate expression and dynamic monitoring of the state and behavior of the physical entity in the digital world. And performing data analysis based on a large amount of component operation data to obtain state changes caused by operation logics, business processes and the like of the components so as to construct a data driving model. After the data driving model is built, even if the operation data of the component cannot be acquired in real time, the operation data of the component can still be predicted according to behavior logic operation rules and the like in the data driving model, so that real-time early warning and monitoring can be carried out on the robot system. For example, the running time, running times and the like of the components can be monitored and early warned more accurately. By the mode, the robot system can be early-warned and monitored under the condition that the operation data of the components cannot be acquired in real time.

In some embodiments of the present specification, after performing model derivation based on the result of the part simulation operation to obtain an updated robot part model and a robot complete machine model, the method may further include: and uploading the updated robot part model and the updated robot complete machine model to a cloud server platform, so that the cloud server platform performs fusion processing on the robot part model and the robot complete machine model to obtain a robot part total model and a robot complete machine total model.

Referring to fig. 14, a schematic diagram of an overall data flow process in the embodiment of the present specification is shown. As shown in fig. 14, the robot system uploads the collected component operation data and parameter information to the hospital local digital twin server in a network cable direct connection manner, and receives decision feedback information of the local digital twin server. And a local digital twin server in the hospital monitoring system synchronously updates data of the component model and the whole machine model, and uploads the local component model and the whole machine model data to a cloud server platform. And the cloud digital twin server in the cloud server platform is used for analyzing, fusing and receiving the data information of the component models and the whole machine models of all hospitals. The hospital monitoring system can upload the developed and updated robot part model and the robot complete machine model to the cloud server platform. The cloud server platform can receive the component models and the complete machine models uploaded by hospital monitoring systems of multiple hospitals. For the same type or the same component model or the whole machine model, the cloud server can perform fusion processing on model data uploaded by a plurality of hospital monitoring systems to obtain a robot component total model and a robot whole machine total model so as to further improve the accuracy of the models.

Further, in some embodiments of the present description, the cloud server platform performs fusion processing on the robot part model and the robot complete machine model to obtain a robot part total model and a robot complete machine total model, which may include: the cloud server platform performs fusion processing on the received robot component models uploaded by the plurality of hospital monitoring systems to obtain a first fusion component total model; fusing the first fusion part total model with a corresponding robot part total model stored in the cloud server platform to obtain a target robot part total model and storing the target robot part total model; the cloud server platform performs fusion processing on the received robot complete machine models uploaded by the plurality of hospital monitoring systems to obtain a first fusion complete machine total model; and carrying out fusion processing on the first overall fusion overall model and the corresponding overall robot model stored in the cloud server platform to obtain and store a target overall robot model.

Referring to fig. 15, an overall flowchart of the cloud server platform in the embodiment of the present disclosure is shown. As shown in fig. 15, the cloud server platform may establish network communication with the hospital, and is mainly used for establishing network transmission services between the cloud server and the hospital monitoring system. The method can acquire hospital model data, hospital part model data and whole machine model data information. And then, carrying out overall model data processing: and carrying out model data fusion processing on the whole machine model data uploaded by different hospitals to generate a whole machine total model, and finishing data cloud storage. And (3) processing component model data: and carrying out component model data fusion processing on component model data of the same type robot products uploaded by different hospitals to generate a component total model, and finishing data cloud storage.

Referring to fig. 16, a schematic diagram of cloud model fusion in an embodiment of the present invention is shown. As shown in fig. 16, the cloud server platform may perform component model fusion, perform fusion processing on similar component model information uploaded by different hospitals, and update the total component model to the model database for storage. Referring to fig. 17, a flowchart of cloud component model data processing in an embodiment of the present invention is shown. As shown in fig. 17, receiving hospital component model data refers to uploading component model data by a different hospital. And (3) component model fusion calculation: firstly, comparing and analyzing acquired hospital component model data, and performing model fusion AI calculation to obtain a group of total model data P1. Specifically, the linear weighted fusion variance calculation of the component models of different hospitals can be performed according to the weight proportion of different life cycle stages, and the optimal model data is fed back as the total model data P1 according to the corresponding result. Acquiring total model data P0 of the components of the same type through a cloud database, and then performing fusion calculation on the P1 model and the P0 model again to obtain final total model data of the components; and storing the data in a cloud database.

As shown in fig. 15, the cloud server platform may perform whole machine model fusion, perform fusion processing on whole machine model data of similar robot products uploaded by different hospitals, and update a whole machine total model to the model database for storage. Referring to fig. 18, a data processing flow chart of the cloud whole machine model in the embodiment of the present specification is shown. As shown in fig. 18, hospital whole machine model data is received: refers to uploading whole machine model data on different hospitals. And (3) fusion calculation of the whole machine model: firstly, carrying out contrastive analysis on acquired data of the hospital whole model, and carrying out model fusion AI calculation to obtain a group of total model data M1; acquiring total model data M0 of the current robot product type through a cloud database, and then performing fusion calculation on the M1 model and the M0 model again to obtain final total model data of the whole robot; and storing the data in a cloud database.

In some embodiments of this specification, before analyzing the robot component operation data and merging the analyzed robot component operation data into a corresponding robot component model to perform digital twin operation processing to obtain a component simulation operation result, the method may further include: inquiring a robot part total model and a robot complete machine total model corresponding to the robot system from a cloud part model library of the cloud server platform so as to determine whether the robot part total model and/or the robot complete machine total model corresponding to the robot system are updated; and under the condition that the total robot part model and/or the total robot whole model corresponding to the robot system are/is determined to be updated, acquiring the updated total robot part model and storing the updated total robot part model into a local part model library, and acquiring the updated total robot whole model and storing the updated total robot whole model into the local whole model library.

With continued reference to fig. 14, the cloud digital twin server in the cloud platform server may update the total robot component model and the total robot complete machine model in the cloud component model library to the local digital twin server in the hospital monitoring system synchronously. Specifically, please refer to fig. 19, which illustrates a flowchart of downloading a synchronized cloud model by a hospital monitoring system in an embodiment of the present specification. As shown in fig. 19, the hospital monitoring system performs a cloud communication connection service probe at regular time by means of network heartbeat monitoring; after network communication is established, regularly inquiring a cloud component model library, and synchronizing updated component model information to a hospital monitoring system database; meanwhile, the whole machine part model library is inquired at regular time, and updated whole machine model data is synchronized to a local database of the hospital monitoring system.

Referring to fig. 20, an overall flow chart of the hospital monitoring system in the embodiment of the present specification is shown. As shown in fig. 20, a local network service may be run, establishing a network transport service for the hospital local and cloud servers. And synchronizing the cloud model data to a hospital, and synchronizing the latest total model data of the cloud to a local database, so that the accuracy of the component model and the whole model is ensured. And receiving the robot component operation data, namely the operation data uploaded to the hospital monitoring system by the real physical equipment. And (4) carrying out simulation development on the part model, and fusing the operation data of the robot part into the part model for operation processing to obtain a part simulation operation result. And performing simulation derivation on the whole machine model, and performing component alarm feedback to the robot system aiming at an abnormal result by judging a component simulation operation result. And decision feedback, namely, making a solution scheme according to the simulation operation result and the monitoring result of the whole robot, and feeding the solution scheme back to the robot system through system notification. And (4) displaying a complete machine model, namely visually displaying the simulation operation process of the part and the simulation operation process of the complete machine.

In some embodiments of this specification, after the cloud server platform performs fusion processing on the robot part model and the robot complete machine model to obtain the robot part total model and the robot complete machine total model, the method may further include: the cloud server platform generates a model analysis report corresponding to the robot part model and the robot complete machine model based on the fusion processing process information; and the cloud server platform returns the model analysis report to the hospital monitoring system.

Referring to fig. 21, a flowchart of cloud-based intelligent report analysis in an embodiment of the present description is shown. As shown in fig. 21, the component model fusion record can be analyzed: and finding out a fusion data record of the current component model through data analysis capacity, and carrying out intelligent analysis in a full life cycle, wherein the analysis content is not limited to the service life of the component, possible alarm risks, influence on the whole model, replaceable component model selection and the like. Specifically, the process of component model fusion may be weight calculation of different stages of the component model, and based on the similar component models of different life cycles, data such as the life of the component and error reporting are predicted for the component (the life is 80% -100%) in the initialization stage, so as to achieve the purpose of intelligent analysis.

The complete machine model fusion record can also be analyzed: and through data analysis capability, finding out a fusion data record of the current complete machine model, and carrying out intelligent analysis in the whole life cycle, wherein the analysis content is not limited to the service life of the complete machine, possible alarm risks, influences on the component model, replaceable complete machine model selection and the like. Specifically, the process of the whole machine model fusion is actually the weight calculation of different stages of the whole machine model, and for the whole machine in the initialization stage, data such as the service life of the whole machine, error reporting and the like are predicted on the basis of the same whole machine models with different life cycles, so that the purpose of intelligent analysis is achieved.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. For details, reference may be made to the description of the related embodiments of the related processing, and details are not repeated herein.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

Based on the same inventive concept, the embodiment of the present specification further provides a digital twin-based surgical robot monitoring device, which is applied to a hospital monitoring system, as described in the following embodiments. Because the problem solving principle of the digital twin-based surgical robot monitoring device is similar to that of the digital twin-based surgical robot monitoring method, the implementation of the digital twin-based surgical robot monitoring device can be referred to the implementation of the digital twin-based surgical robot monitoring method, and repeated parts are not described again. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated. Fig. 22 is a block diagram of a digital twin-based surgical robot monitoring device according to an embodiment of the present disclosure, and as shown in fig. 22, the device includes: an acquisition module 2201, a simulation module 2202, and a monitoring module 2203, the structure of which is described below.

The acquiring module 2201 is configured to acquire robot component operating data of the robot system.

The simulation module 2202 is configured to analyze the robot component operation data, and integrate the robot component operation data into a corresponding robot component model to perform digital twin operation processing, so as to obtain a component simulation operation result.

The monitoring module 2203 is configured to merge the simulation operation result of the component into a complete robot model to perform digital twinning operation processing, so as to perform early warning and monitoring on the robot system.

In some embodiments of the present description, the obtaining module may be specifically configured to: and acquiring the robot component operation data of the robot system through the local area network.

In some embodiments of the present description, the simulation module may be further configured to: before acquiring the robot component operation data of the robot system, splitting the robot system to obtain a plurality of robot components; acquiring component operation data and component parameters corresponding to each of the plurality of robot components; performing digital twin model training based on the component operation data and the component parameters corresponding to each robot component to obtain a robot component model corresponding to each robot component; and storing the robot part models corresponding to the robot parts into a local part model library corresponding to the robot parts.

In some embodiments of the present description, the simulation module may be further configured to: before acquiring robot component operation data of a robot system, splitting the robot system to obtain a plurality of robot component operation data; matching the robot component operation data in the robot component operation data with robot component models in a local component model library to obtain robot component models corresponding to the robot component operation data; constructing a complete machine digital twin model based on the robot part model corresponding to the operation data of each robot part to obtain a robot complete machine model corresponding to the surgical robot; and storing the robot complete machine model to a local complete machine model library corresponding to the robot system.

In some embodiments of the present description, the monitoring module may be specifically configured to: integrating the part simulation operation result into a robot complete machine model to perform digital twin operation processing to obtain a complete machine simulation operation result; and generating early warning information under the condition that the complete machine simulation operation result meets a preset condition.

In some embodiments of the present description, the monitoring module may be further configured to: inquiring decision feedback information corresponding to the early warning information; and returning the decision feedback information and the early warning information to the robot system.

In some embodiments of the present description, the simulation module may be further configured to: analyzing the robot part operation data, merging the robot part operation data into a robot part model for digital twin operation processing to obtain a part simulation operation result, and performing model derivation based on the part simulation operation result to obtain an updated robot part model and a robot complete machine model; and storing the updated robot part model and the updated robot complete machine model into a corresponding local part model library and a corresponding local complete machine model library.

In some embodiments of the present description, the monitoring module may be further configured to: after the simulation module obtains the updated robot part model and the robot complete machine model, a data driving model is constructed based on the robot part operation data; and early warning and monitoring the robot system by using the data driving model, the updated robot part model and the updated robot complete machine model.

In some embodiments of the present description, the obtaining module may be further configured to: inquiring a robot part total model and a robot complete machine total model corresponding to the robot system from a cloud part model library of the cloud server platform so as to determine whether the robot part total model and/or the robot complete machine total model corresponding to the robot system are updated; and under the condition that the total robot part model and/or the total robot whole model corresponding to the robot system are/is determined to be updated, acquiring the updated total robot part model and storing the updated total robot part model into a local part model library, and acquiring the updated total robot whole model and storing the updated total robot whole model into the local whole model library.

In some embodiments of the present description, the cloud server platform performs fusion processing on the robot part model and the robot complete machine model to obtain a robot part total model and a robot complete machine total model, which may include: the cloud server platform performs fusion processing on the received robot component models uploaded by the plurality of hospital monitoring systems to obtain a first fusion component total model; fusing the first fusion part total model with a corresponding robot part total model stored in the cloud server platform to obtain and store a target robot part total model; the cloud server platform performs fusion processing on the received robot complete machine models uploaded by the plurality of hospital monitoring systems to obtain a first fusion complete machine total model; and carrying out fusion processing on the first overall fusion model and the corresponding overall robot model stored in the cloud server platform to obtain and store a target overall robot model.

The embodiment of the specification further provides a digital twin-based surgical robot monitoring system. Referring to fig. 23, a schematic structural diagram of a digital twin-based surgical robot monitoring system in the present embodiment is shown. As shown in fig. 23, the surgical robot monitoring system may include a robot system 231, a hospital monitoring system 232, and a cloud server platform 233.

The robot system 231 is used for collecting robot part operation data of the surgical robot and sending the robot part operation data to a hospital monitoring system through a local area network.

The hospital monitoring system 232 is used for analyzing the robot component operation data, and integrating the robot component operation data into a corresponding robot component model to perform digital twin operation processing to obtain a component simulation operation result; and the simulation operation result of the part is fused into a complete robot model to carry out digital twin operation processing so as to carry out early warning monitoring on the robot system.

The cloud server platform 232 is used for receiving the robot part model and the robot complete machine model uploaded by the hospital monitoring system; and the method is also used for carrying out fusion processing on the robot part model and the robot complete machine model to obtain a robot part total model and a robot complete machine total model.

The embodiment provides a monitoring system based on digital twin intelligent medical robot, which comprises: the system comprises a robot system, a hospital monitoring system and a cloud monitoring system. The robot system includes: a robot system: the system is used for collecting and uploading the robot part operation data and receiving the decision feedback message notice of the hospital monitoring system.

The hospital monitoring system includes: the model management module is used for managing the component model and the robot model, realizing synchronization of uploading of model data by a cloud server and local downloading and updating of a hospital and improving the accuracy of the digital twin model; the database storage module is used for storing component digital twin model information of different types of robot products in the hospital and complete machine digital twin model information; the local model simulation operation server is used for solving the acquired part operation data, performing part simulation operation, transmitting a simulation result to the whole machine digital twin model to perform whole machine system simulation operation, and realizing early warning and monitoring on the whole robot; the notification module is used for sending abnormal monitoring alarm and feedback decision scheme measures to the robot system; and the model AI evolution module is used for self-learning of the hospital part digital twin and the robot digital twin, and continuously improves the accuracy of the digital twin model.

The cloud monitoring comprises: the cloud server is established, and different servers of different products are used for receiving the locally uploaded component model data and the locally uploaded robot model data and providing service for downloading and updating models for other equipment; the database storage module is used for storing a component digital twin general model and a whole machine digital twin general model of the similar robot; the model operation module is used for analyzing and operating parts and whole model data of products of the same type from different hospitals, and updating the part total module and the robot total module through configuration parameter debugging; and the intelligent analysis report module is used for carrying out full life cycle operation statistics and early warning on all the networking components and the robot system, and outputting a report and recommending a replacement component list and information.

In the embodiment, by establishing the internal monitoring system of the hospital, the local network resources and the edge computing capability of the hospital are fully utilized, the high efficiency of data transmission is improved, and meanwhile, the computing pressure of the cloud platform is dispersed; the management of the parts and the robot model data is locally carried out, and the intelligent AI machine training learning is matched, so that the individuation problem of the hospital model data can be solved, the accuracy of a digital model is improved, and the monitoring reliability is guaranteed; the cloud carries out data analysis on the parts and the robot total model, can solve the universality problem of model data, promotes the evolution and the update of the model, and has positive effects on operation and maintenance monitoring of equipment and production of new equipment; the cloud carries out intelligent analysis of the parts and the whole robot, carries out analysis of the whole life cycle of the parts and the whole robot on the basis of the parts total model and the whole robot total model of the same type, and simultaneously carries out intelligent selectable recommendation of part replacement, so that trial and error cost of part replacement is reduced, and efficiency is improved.

In the embodiment, a hospital and cloud two-stage monitoring system is established, and a hospital operation and maintenance system realizes terminal data collection, model training, digital simulation and operation and maintenance monitoring, realizes distributed model training and distributed operation and maintenance, and finally converges into a cloud part and a robot twin system model; and the cloud system can synchronize more accurate model data into the hospital system, so that a complementary multi-layer operation and maintenance system is realized. The courtyard system carries out component level decomposition on the whole machine on a logic level, establishes a component model at a component level, and finally converges the component model into a main part of a digital twin model of the robot, so that the automatic construction of the model is realized; in the system monitoring process, the monitoring result of the component model is used as the input of the digital twin system of the robot, the current system state of the robot is simulated and calculated, and the impending component and system problems are predicted. And the relation and the rule between the component problem and the system problem can be obtained through machine learning, so that intelligent analysis and report can be realized. The hospital system operates in the local area network, and can implement operation and maintenance monitoring activities more efficiently, more safely and more in real time.

In the embodiment, the internal monitoring system of the hospital is established based on the network service in the hospital, and the equipment data is acquired and transmitted in the operation and is communicated through the local area network, so that the transmission risk caused by network fluctuation and network disconnection is reduced. The operation service is established in the hospital internal monitoring system, the part needing a large amount of calculation consumption is locally carried out in the hospital, and the pressure of the traditional cloud service centralized calculation is shared. In the local hospital monitoring system, a robot component model library and a robot complete machine equipment model library which take a hospital as a unit are established, and the latest model information of the cloud platform is synchronized to the model library in the hospital under the condition of smooth network, so that the accuracy of digital twin models of components and robots used by the monitoring operation service is guaranteed. An AI machine learning mode is adopted in a hospital internal monitoring system, and a robot part model and an equipment complete machine model in an operation are self-trained and corrected. The cloud robot monitoring system is established and used for sorting part digital twin model data and whole machine digital twin model data from different hospitals in the same type of robot products, carrying out model derivation and fusion, and establishing a cloud part digital twin model library and a robot whole machine equipment digital twin model library for data storage, so that a reusable mature part model is provided for the new type of robot equipment, the part model does not need to be trained from scratch, the model training time is reduced, and the model accuracy is guaranteed. And the cloud monitoring system is used for carrying out intelligent monitoring report analysis in the whole life cycle according to the component model information and the whole machine model information uploaded by the hospital and by combining the components of the same type of products in different stages and the whole machine total model information.

Referring to fig. 24, an overall system architecture diagram of a digital twin based surgical robotic monitoring system in an embodiment of the present description is shown. As shown in fig. 24, the cloud server platform: the system mainly comprises a cloud digital twin server and a model storage database. The robot system refers to physical robot equipment and is used for collecting data and uploading and receiving feedback decision suggestions of the hospital monitoring system. The hospital monitoring system is deployed in a hospital information machine room and mainly covers a local digital twin server and a model storage database.

Referring to fig. 25, a diagram of a hospital twin server system in the embodiment of the present specification is shown. As shown in fig. 25, the hospital twin server includes the following. The equipment data analysis module: and the device is used for analyzing the collected device operation data and device parameters, and analyzing and formatting the data. A model management module: the system is used for synchronizing the cloud model data information to a local database for storage, and uploading the model information derived from the AI to the cloud monitoring system. A model simulation operation module: carrying out model simulation operation on the analyzed data information and the synchronized model information; sequentially carrying out simulation operation of the component model and simulation operation of the whole machine model according to the sequence; and monitoring and early warning aiming at abnormal simulation operation of the parts in the operation process of the whole machine model. Model AI is derived: AI derivation of the part module and the whole machine module is carried out according to the simulation operation result of the model, and the model is used for improving the accuracy of the model. A decision feedback module: and performing corresponding correction suggestion analysis according to monitoring alarm information generated by model simulation operation, and feeding back the correction suggestion to the robot system. A system notification module: the method is the same as the notification of the robot monitoring early warning information and the decision feedback information. And the whole machine 3D model display module is terminal equipment used for an operation and maintenance engineer to check the running state of the model.

Referring to fig. 26, a cloud twin server system architecture diagram in an embodiment of the present specification is shown. As shown in fig. 26, the cloud twin server includes the following. A model management module: the model data updating system is used for acquiring model data information uploaded by hospital monitoring system model management and updating the model data to a model operation processing server; and acquiring the latest total model information generated by the model operation processing module, and updating the total model information into the hospital monitoring system. Model operation processing: model fusion processing analysis is carried out on model data uploaded by the hospital monitoring system, information of a component total model and a complete machine total model is generated, and the information is stored in a cloud database. And (3) intelligent report analysis of the model: and generating an analysis report about the component module and the whole machine model based on the process information of model fusion.

From the above description, it can be seen that the embodiments of the present specification achieve the following technical effects: the robot part and the whole machine model data are managed in the hospital monitoring system, and the whole robot system can be monitored and early warned only by acquiring the part operation data in the monitoring process, so that the accuracy of the digital model can be improved, and the monitoring reliability is guaranteed. By establishing the internal monitoring system of the hospital, the local network resources and the edge computing capability of the hospital can be fully utilized, the high efficiency of data transmission is improved, and the efficiency and the real-time performance of robot monitoring are further improved.

The embodiment of the present specification further provides a medical device, which may specifically refer to fig. 27, which is a schematic structural diagram of a medical device based on the digital twin-based surgical robot monitoring method provided in the embodiment of the present specification, and the medical device may specifically include an input device 271, a processor 272, and a memory 273. The memory 273 is used for storing processor-executable instructions. The processor 272, when executing the instructions, performs the steps of the digital twinning based surgical robot monitoring method described in any of the embodiments above.

In this embodiment, the input device may be one of the main apparatuses for information exchange between a user and a computer system. The input device may include a keyboard, a mouse, a camera, a scanner, a light pen, a handwriting input board, a voice input device, etc.; the input device is used to input raw data and a program for processing these numbers into the computer. The input device can also acquire and receive data transmitted by other modules, units and devices. The processor may be implemented in any suitable way. For example, the processor may take the form of, for example, a microprocessor or processor and a computer-readable medium that stores computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, an embedded microcontroller, and so forth. The memory may in particular be a memory device used in modern information technology for storing information. The memory may comprise multiple levels, and in a digital system, it may be memory as long as it can hold binary data; in an integrated circuit, a circuit without a physical form and with a storage function is also called a memory, such as a RAM, a FIFO and the like; in the system, the storage device in physical form is also called a memory, such as a memory bank, a TF card and the like.

In this embodiment, the functions and effects of the medical device can be explained in comparison with other embodiments, and are not described herein.

There is also provided in an embodiment of the present specification a computer storage medium of a digital twin-based surgical robot monitoring method, the computer storage medium storing computer program instructions which, when executed, implement the steps of the digital twin-based surgical robot monitoring method according to any of the above embodiments.

In this embodiment, the storage medium includes, but is not limited to, a Random Access Memory (RAM), a Read-Only Memory (ROM), a Cache (Cache), a Hard Disk Drive (HDD), or a Memory Card (Memory Card). The memory may be used to store computer program instructions. The network communication unit may be an interface for performing network connection communication, which is set in accordance with a standard prescribed by a communication protocol.

In this embodiment, the functions and effects specifically realized by the program instructions stored in the computer storage medium can be explained by comparing with other embodiments, and are not described herein again.

It will be apparent to those skilled in the art that the modules or steps of the embodiments of the present specification described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed over a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different from that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, embodiments of the present description are not limited to any specific combination of hardware and software.

It is to be understood that the above description is intended to be illustrative, and not restrictive. Many embodiments and many applications other than the examples provided will be apparent to those of skill in the art upon reading the above description. The scope of the description should, therefore, be determined not with reference to the above description, but should instead be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.

The above description is only a preferred embodiment of the present disclosure, and is not intended to limit the present disclosure, and it will be apparent to those skilled in the art that various modifications and variations can be made in the embodiment of the present disclosure. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present specification shall be included in the protection scope of the present specification.

Claims

1. A surgical robot monitoring method based on digital twinning is characterized in that the method is applied to a hospital monitoring system and comprises the following steps:

acquiring robot part operation data of a robot system;

analyzing the robot part operation data, and fusing the robot part operation data into a corresponding robot part model to perform digital twin operation processing to obtain a part simulation operation result;

and integrating the simulation operation result of the part into a complete robot model to perform digital twin operation processing so as to perform early warning monitoring on a robot system.

2. A digital twinning based surgical robot monitoring method as claimed in claim 1, wherein acquiring robot component operational data of a robotic system includes:

and acquiring the robot component operation data of the robot system through the local area network.

3. A digital twinning-based surgical robot monitoring method as in claim 1, further comprising, prior to acquiring robot component operational data of the robotic system:

splitting the components of the robot system to obtain a plurality of robot components;

acquiring component operation data and component parameters corresponding to each of the plurality of robot components;

performing digital twin model training based on the component operation data and the component parameters corresponding to each robot component to obtain a robot component model corresponding to each robot component;

and storing the robot part model corresponding to each robot part into a local part model library corresponding to each robot part.

4. A digital twin based surgical robot monitoring method as claimed in claim 3, further comprising, prior to acquiring robot component operational data of a robotic system:

splitting the components of the robot system to obtain operation data of a plurality of robot components;

matching the robot component operation data in the robot component operation data with robot component models in a local component model library to obtain robot component models corresponding to the robot component operation data;

constructing a complete machine digital twin model based on the robot part model corresponding to the operation data of each robot part to obtain a robot complete machine model corresponding to the surgical robot;

and storing the robot complete machine model to a local complete machine model library corresponding to the robot system.

5. The digital twin-based surgical robot monitoring method according to claim 1, wherein the step of integrating the part simulation operation result into a robot complete machine model to perform digital twin operation processing so as to perform early warning monitoring on a robot system comprises the steps of:

integrating the part simulation operation result into a robot complete machine model to perform digital twin operation processing to obtain a complete machine simulation operation result;

and generating early warning information under the condition that the complete machine simulation operation result meets a preset condition.

6. The digital twin-based surgical robot monitoring method according to claim 5, further comprising, after generating the early warning information:

inquiring decision feedback information corresponding to the early warning information;

and returning the decision feedback information and the early warning information to the robot system.

7. The digital twinning-based surgical robot monitoring method as claimed in claim 1, further comprising the steps of, after analyzing the robot component operation data, integrating the robot component operation data into a robot component model for digital twinning operation processing, and obtaining a component simulation operation result:

model derivation is carried out based on the part simulation operation result to obtain an updated robot part model and a robot complete machine model;

and storing the updated robot part model and the updated robot complete machine model into a corresponding local part model library and a corresponding local complete machine model library.

8. The digital twinning-based surgical robot monitoring method of claim 7, further comprising, after performing model derivation based on the part simulation calculation result to obtain an updated robot part model and a robot complete machine model:

constructing a data-driven model based on the robot component operating data;

and early warning and monitoring the robot system by using the data driving model, the updated robot part model and the updated robot complete machine model.

9. The digital twin-based surgical robot monitoring method according to claim 7, further comprising, after performing model derivation based on the result of the part simulation operation to obtain an updated robot part model and a robot complete machine model:

and uploading the updated robot part model and the updated robot complete machine model to a cloud server platform, so that the cloud server platform performs fusion processing on the robot part model and the robot complete machine model to obtain a robot part total model and a robot complete machine total model.

10. The digital twinning-based surgical robot monitoring method of claim 9, wherein before analyzing the robot component operating data and integrating the analyzed data into a corresponding robot component model for digital twinning operation processing to obtain a component simulation operation result, the method further comprises:

inquiring a robot part total model and a robot complete machine total model corresponding to the robot system from a cloud part model library of the cloud server platform so as to determine whether the robot part total model and/or the robot complete machine total model corresponding to the robot system are updated;

11. The digital twin-based surgical robot monitoring method according to claim 9, wherein the cloud server platform performs fusion processing on the robot part model and the robot complete machine model to obtain a robot part total model and a robot complete machine total model, and the method comprises the following steps:

the cloud server platform performs fusion processing on the received robot component models uploaded by the plurality of hospital monitoring systems to obtain a first fusion component total model; fusing the first fusion part total model with a corresponding robot part total model stored in the cloud server platform to obtain and store a target robot part total model;

the cloud server platform performs fusion processing on the received robot complete machine models uploaded by the plurality of hospital monitoring systems to obtain a first fusion complete machine total model; and carrying out fusion processing on the first overall fusion model and the corresponding overall robot model stored in the cloud server platform to obtain and store a target overall robot model.

12. The digital twin-based surgical robot monitoring method according to claim 9, wherein after the cloud server platform performs fusion processing on the robot part model and the robot complete machine model to obtain the robot part total model and the robot complete machine total model, the method further comprises:

the cloud server platform generates a model analysis report corresponding to the robot part model and the robot complete machine model based on the fusion processing process information;

and the cloud server platform returns the model analysis report to the hospital monitoring system.

13. A surgical robot monitoring device based on digital twinning, which is applied to a hospital monitoring system, comprises:

the acquisition module is used for acquiring the robot component operation data of the robot system;

the simulation module is used for analyzing the robot part operation data and integrating the robot part operation data into a corresponding robot part model to perform digital twin operation processing to obtain a part simulation operation result;

and the monitoring module is used for fusing the simulation operation result of the part into a complete machine model of the robot to perform digital twin operation processing so as to perform early warning monitoring on the robot system.

14. A digital twin-based surgical robot monitoring system is characterized by comprising a robot system, a hospital monitoring system and a cloud server platform; wherein the content of the first and second substances,

the robot system is used for acquiring robot part operation data of the surgical robot and sending the robot part operation data to the hospital monitoring system through the local area network;

the hospital monitoring system is used for analyzing the robot component operation data and integrating the robot component operation data into a corresponding robot component model to perform digital twin operation processing to obtain a component simulation operation result; the system is also used for integrating the simulation operation result of the part into a complete machine model of the robot to carry out digital twin operation processing so as to carry out early warning monitoring on a robot system;

the cloud server platform is used for receiving a robot part model and a robot complete machine model uploaded by a hospital monitoring system; and the method is also used for carrying out fusion processing on the robot part model and the robot complete machine model to obtain a robot part total model and a robot complete machine total model.

15. A medical device comprising a processor and a memory for storing processor-executable instructions that, when executed by the processor, implement the steps of the method of any one of claims 1 to 12.

16. A computer-readable storage medium having stored thereon computer instructions, which when executed by a processor, carry out the steps of the method of any one of claims 1 to 12.