Robot fault handling method, apparatus, device, and computer-readable storage medium

Abstract

This application relates to the field of robotics technology and discloses a robot fault handling method, apparatus, device, and computer-readable storage medium. The method includes: acquiring a fault log; inputting the fault log into a preset local fault handling model to obtain a first repair solution; and repairing the target fault corresponding to the fault log based on the first repair solution; if the repair solution cannot repair the target fault corresponding to the fault log, then inputting the first repair solution and the fault log into a preset cloud-based fault handling model to obtain a second repair solution; and repairing the target fault based on the second repair solution; if the second repair solution cannot repair the target fault, then creating a maintenance work order based on the second repair solution and the fault log, and notifying maintenance personnel to repair the target fault. When a fault is detected, maintenance personnel are only notified to repair the fault if the repair solution output by the model cannot repair it, thus reducing the cost of robot fault handling.

Description

Technical Field

[0001] This application relates to the field of robotics, and in particular to a method, apparatus, device, and computer-readable storage medium for handling robot faults. Background Technology

[0002] Currently, robots are being used more and more widely in industrial, commercial, and home settings. However, various malfunctions inevitably occur during robot operation.

[0003] In the existing fault handling model, when a fault occurs, users typically need to communicate with the equipment manufacturer's customer service personnel via phone, video, or text message. The diagnosis and repair of many complex faults require experienced professional maintenance personnel. This results in high operational costs for robot fault handling, which constitutes a major obstacle to the large-scale adoption and commercial operation of robots. Summary of the Invention

[0004] In view of this, the purpose of this application is to overcome the shortcomings of the prior art and provide a robot fault handling method, the method comprising:

[0005] Obtain the fault log, input the fault log into a preset local fault handling model to obtain a first repair scheme, and repair the target fault corresponding to the fault log based on the first repair scheme;

[0006] If the target fault corresponding to the fault log cannot be repaired based on the repair scheme, the first repair scheme and the fault log are input into a preset cloud fault handling model to obtain a second repair scheme, and the target fault is repaired based on the second repair scheme.

[0007] If the target fault cannot be repaired based on the second repair solution, a maintenance work order is created based on the second repair solution and the fault log, and maintenance personnel are notified to repair the target fault.

[0008] In one embodiment, the method further includes:

[0009] Obtain the fault log and determine the severity of the fault based on the fault log;

[0010] Based on the severity of the fault, a target fault handling model is determined from the local fault handling model or the cloud-based fault handling model, and the fault log is input into the target fault handling model to obtain a repair solution.

[0011] In one embodiment, the step of obtaining the fault log and determining the severity of the fault based on the fault log includes:

[0012] During robot operation, the operation log is monitored in real time and fault logs in the operation log are identified;

[0013] When a fault log is obtained, the fault log is parsed to determine the target fault, and the severity of the fault is determined based on the target fault and a preset mapping relationship between fault and severity.

[0014] In one embodiment, the step of determining a target fault handling model from the local fault handling model or the cloud-based fault handling model based on the severity of the fault includes:

[0015] If the severity of the fault is less than a preset severity threshold, then the local fault handling model is determined as the target fault handling model.

[0016] If the severity of the fault is greater than a preset severity threshold, then the cloud-based fault handling model is determined as the target fault handling model.

[0017] In one embodiment, the step of repairing the target fault corresponding to the fault log based on the repair scheme includes:

[0018] Based on the repair scheme, a repair instruction is generated, and the target fault corresponding to the fault log is repaired based on the repair instruction; or

[0019] Based on the repair scheme, repair guidance information is generated and sent to the user so that the user can repair the target fault corresponding to the fault log based on the repair guidance information.

[0020] In one embodiment, after the step of repairing the target fault based on the second repair scheme, the following steps are included:

[0021] If the target fault is successfully repaired based on the second repair scheme, the second repair scheme and the target fault are stored as training data for the first model.

[0022] During the update cycle of the local fault handling model, the local fault handling model is updated based on the training data of the first model.

[0023] In one embodiment, after the step of creating a maintenance work order based on the second repair plan and the fault log, and notifying maintenance personnel to repair the target fault, the process includes:

[0024] Obtain the fault handling work order uploaded by the maintenance personnel, and store the target fault and the maintenance plan of the fault handling work order as the second model training data;

[0025] The cloud-based fault handling model is updated based on the training data of the second model during the preset update cycle of the cloud-based fault handling model.

[0026] This application also provides a robot fault handling device, the robot fault handling device comprising:

[0027] The first repair module is used to acquire fault logs, input the fault logs into a preset local fault handling model to obtain a first repair scheme, and repair the target fault corresponding to the fault logs based on the first repair scheme.

[0028] The second repair module is used to, if the target fault corresponding to the fault log cannot be repaired based on the repair scheme, input the first repair scheme and the fault log into a preset cloud fault handling model to obtain the second repair scheme, and repair the target fault based on the second repair scheme;

[0029] The notification module is used to create a maintenance work order based on the second repair plan and the fault log if the target fault cannot be repaired based on the second repair plan, and to notify the maintenance personnel to repair the target fault.

[0030] This application also provides a computer device, which includes a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement the above-described robot fault handling method.

[0031] This application also provides a computer-readable storage medium storing a computer program that, when run on a processor, executes the above-described robot fault handling method.

[0032] The embodiments of this application have the following beneficial effects:

[0033] This application embodiment acquires fault logs, inputs the fault logs into a preset local fault handling model to obtain a first repair solution, and repairs the target fault corresponding to the fault log based on the first repair solution. If the target fault corresponding to the fault log cannot be repaired based on the repair solution, the first repair solution and the fault log are input into a preset cloud fault handling model to obtain a second repair solution, and the target fault is repaired based on the second repair solution. If the target fault cannot be repaired based on the second repair solution, a maintenance work order is created based on the second repair solution and the fault log, and maintenance personnel are notified to repair the target fault. When a fault is detected, repair is performed sequentially, prioritizing the local fault handling model, the cloud fault handling model, and the maintenance personnel. Only when the repair solution fails to repair the fault will maintenance personnel be notified to repair it, reducing the labor costs, training costs, and travel costs of maintenance personnel, and reducing the operation and maintenance costs of robot fault handling. Attached Figure Description

[0034] To more clearly illustrate the technical solutions of this application, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of this application and therefore should not be considered as a limitation on the scope of protection of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 A flowchart illustrating the first embodiment of the robot fault handling method provided in this application;

[0036] Figure 2 A flowchart illustrating a second embodiment of the robot fault handling method provided in this application;

[0037] Figure 3 A flowchart illustrating the third embodiment of the robot fault handling method provided in this application;

[0038] Figure 4 A flowchart illustrating the fourth embodiment of the robot fault handling method provided in this application;

[0039] Figure 5 A flowchart illustrating the fifth embodiment of the robot fault handling method provided in this application;

[0040] Figure 6 This is a schematic diagram of the robot fault handling device provided in this application. Detailed Implementation

[0041] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0042] The components of the embodiments of this application described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0043] In the following, the terms “comprising,” “having,” and their cognates, which may be used in various embodiments of this application, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as excluding, firstly, the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations thereof.

[0044] Furthermore, the terms "first," "second," and "third" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0045] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be construed as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.

[0046] It is understood that the method of this application is applied to a robot fault handling system, which includes a robot and a cloud platform. For ease of explanation, the following embodiments are described in detail using a robot fault handling system as the execution subject.

[0047] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0048] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a first embodiment of the robot fault handling method provided in this application. The method includes:

[0049] Step S101: Obtain the fault log, input the fault log into a preset local fault handling model to obtain a first repair scheme, and repair the target fault corresponding to the fault log based on the first repair scheme.

[0050] In this embodiment, after the robot in the robot fault handling system obtains the fault log, it inputs the fault log into the local fault handling model to obtain a first repair solution, and then repairs the target fault corresponding to the fault log based on the first repair solution. The local fault handling model is a general-purpose, lightweight fault handling model generated by the cloud platform based on the robot's unique identifier and the commonality, severity, and common-sense nature of the faults, and is pre-installed on the robot's local machine.

[0051] In one embodiment, the local fault handling model stores various fault-related repair schemes. The local fault handling model can parse fault logs, thereby determining the target fault corresponding to the fault logs, and then determining the first repair scheme corresponding to the target fault among various fault-related repair schemes.

[0052] Step S102: If the target fault corresponding to the fault log cannot be repaired based on the repair scheme, the first repair scheme and the fault log are input into a preset cloud fault processing model to obtain a second repair scheme, and the target fault is repaired based on the second repair scheme.

[0053] In this embodiment, after determining a first repair plan, the robot in the robot fault handling system performs local autonomous repair on the target fault based on the first repair plan and detects the repair result. If the repair result indicates that the target fault cannot be repaired based on the first repair plan, the first repair plan and the fault log are sent to the cloud-based fault handling model to obtain a second repair plan. The cloud-based fault handling model has more powerful computing power and a more comprehensive knowledge base. The more comprehensive knowledge base includes all records of fault handling since the production of this type of robot, as well as robot product knowledge, including but not limited to all hardware information, structural information, software information, parameter configurations, hardware lifespan, and hardware / software functional boundaries of the robot.

[0054] Understandably, the cloud-based fault handling model resides on the cloud platform of the robot's fault handling system. The robot sends its first repair plan and fault logs to the cloud platform via a private encrypted network. The cloud platform then inputs these materials into the cloud-based fault handling model to obtain a second repair plan. This cloud-based fault handling model possesses more powerful computing capabilities and a more comprehensive knowledge base, enabling it to provide a more advanced second repair plan.

[0055] In this embodiment, after determining the second repair solution, the cloud-based fault handling model sends the second repair solution to the robot in the robot fault handling system through the cloud platform. The robot then performs local autonomous repair on the target fault based on the second repair solution.

[0056] Understandably, the robot fault handling system outputs corresponding repair solutions sequentially through the local fault handling model and the cloud-based fault handling model, and then attempts to repair the target fault twice based on different repair solutions, so as to minimize the involvement of maintenance personnel, reduce the waiting time for maintenance personnel, and help improve fault handling efficiency.

[0057] Step S103: If the target fault cannot be repaired based on the second repair solution, a maintenance work order is created based on the second repair solution and the fault log, and maintenance personnel are notified to repair the target fault.

[0058] In this embodiment, if the robot in the robot fault handling system cannot repair the target fault based on the second repair plan, the second repair plan and the fault log are sent to the cloud platform of the robot fault handling system. The cloud platform creates a maintenance work order based on the repair plan and the fault log, and notifies the maintenance personnel to repair the target fault of the robot.

[0059] It should be noted that a dedicated communication proxy service is integrated into the robot operating system. This service is responsible for building a private encrypted network with the cloud platform through protocols such as HTTPS, WebSocket, and MQTT, ensuring the security and reliability of data transmission between the robot and the cloud platform.

[0060] The robot fault handling system in this embodiment acquires fault logs, inputs the fault logs into a preset local fault handling model to obtain a first repair solution, and repairs the target fault corresponding to the fault log based on the first repair solution. If the target fault corresponding to the fault log cannot be repaired based on the repair solution, the first repair solution and the fault log are input into a preset cloud fault handling model to obtain a second repair solution, and the target fault is repaired based on the second repair solution. If the target fault cannot be repaired based on the second repair solution, a maintenance work order is created based on the second repair solution and the fault log, and maintenance personnel are notified to repair the target fault. When a fault is detected, repair is performed sequentially, prioritizing the local fault handling model, the cloud fault handling model, and the maintenance personnel's fault matching. Only when the repair solution fails to repair the fault will maintenance personnel be notified to repair the fault, thus reducing the labor costs, training costs, and travel costs of maintenance personnel, and reducing the operation and maintenance costs of robot fault handling.

[0061] Please refer to Figure 2 , Figure 2This is a flowchart illustrating a second embodiment of the robot fault handling method provided in this application. The difference between the second embodiment and the first embodiment is that the method further includes:

[0062] Step S201: Obtain the fault log and determine the severity of the fault based on the fault log.

[0063] In this embodiment, the robot fault handling system generates operation logs in real time during operation. The operation logs record the status of various systems or components of the robot. The robot analyzes each operation log and identifies operation logs with abnormal system or component status as fault logs. The robot determines the severity of the fault based on the fault logs.

[0064] In one embodiment, the step of obtaining the fault log and determining the severity of the fault based on the fault log includes:

[0065] Step S2011: During the robot's operation, monitor the operation log in real time and identify the fault log in the operation log.

[0066] Step S2012: When the fault log is obtained, the fault log is parsed to determine the target fault, and the severity of the fault is determined according to the target fault and the preset mapping relationship between fault and severity.

[0067] In this embodiment, the robot in the robot fault handling system generates operation logs in real time during operation. The operation logs record the status of various systems or components of the robot. The robot analyzes each operation log and identifies operation logs with abnormal system or component status as fault logs. The robot parses the fault logs to identify the target fault and determines the severity of the fault based on the target fault and the preset mapping relationship between fault and severity.

[0068] Understandably, the pre-defined mapping relationship between faults and severity is determined by a massive amount of robot fault maintenance data. First, the impact of each fault on the normal operation of the robot, the difficulty of repair, and the prevalence are determined, and the corresponding severity of each fault is determined, thereby generating the pre-defined mapping relationship between faults and severity.

[0069] Step S202: Based on the severity of the fault, determine the target fault handling model, and input the fault log into the target fault handling model to obtain a repair solution.

[0070] In this embodiment, after determining the severity of a fault, the robot in the robot fault handling system determines a target fault handling model based on the severity, and inputs the fault log into the target fault handling model to obtain a repair solution. It should be noted that the robot in the robot fault handling system stores a pre-trained local fault handling model, and the cloud platform of the robot fault handling system stores a pre-trained cloud fault handling model. The robot can choose either the local fault handling model or the cloud fault handling model as the target fault handling model based on the severity of the fault.

[0071] In one embodiment, the step of determining the target fault handling model based on the severity of the fault includes:

[0072] Step S2021: If the severity of the fault is less than a preset severity threshold, then the local fault handling model is determined as the target fault handling model.

[0073] Step S2022: If the severity of the fault is greater than a preset severity threshold, then the cloud-based fault handling model is determined as the target fault handling model.

[0074] In this embodiment, the severity of a fault is categorized into five levels: notification, warning, error, severe, and danger. The severity, from lowest to highest, is: notification, warning, error, severe, and danger. After determining the severity of a fault, the robot in the fault handling system determines the fault severity as either notification, warning, or error. If the severity is determined to be notification, warning, or error, a preset local fault handling model is selected as the target fault handling model, and the fault log is input into the local fault handling model to obtain a repair solution. If the severity is determined to be severe or danger, a preset cloud-based fault handling model is selected as the target fault handling model, and the fault log is input into the cloud-based fault handling model to obtain a repair solution.

[0075] The robot fault handling system in this embodiment monitors the operation log in real time and identifies fault logs within it during robot operation. Upon receiving a fault log, it parses the log to identify the target fault and determines its severity based on a preset mapping between the target fault and its severity. This allows for rapid identification of the robot fault's severity, improving fault location efficiency and consequently, enhancing the efficiency of robot fault repair. Furthermore, based on the fault's severity, it selects either a local fault handling model or a cloud-based fault handling model as the target fault handling model and outputs a repair solution. The system can directly determine the appropriate fault handling model based on the severity, further improving fault handling efficiency.

[0076] Please refer to Figure 3 , Figure 3This is a flowchart illustrating a third embodiment of the robot fault handling method provided in this application. The difference between the third embodiment and the first to second embodiments is that the step of repairing the target fault corresponding to the fault log based on the repair scheme includes:

[0077] Step S301: Based on the repair scheme, generate a repair instruction, and repair the target fault corresponding to the fault log based on the repair instruction.

[0078] In this embodiment, after determining the repair scheme output by the local fault handling model, the robot of the robot fault handling system generates a repair instruction and repairs the target fault corresponding to the fault log based on the repair instruction.

[0079] For example, during robot operation, the motor driver reports an "overcurrent" error, generating a "critical" level fault log. The robot inputs this fault log into its local fault handling model and obtains a repair solution of attempting to send a "motor soft restart" command. At this time, the robot sends the "motor soft restart" command to the motor driver to repair the target fault corresponding to the fault log.

[0080] Step S302: Based on the repair scheme, generate repair guidance information and send the repair guidance information to the user so that the user can repair the target fault corresponding to the fault log based on the repair guidance information.

[0081] In this embodiment, the robot in the robot fault handling system generates repair guidance information based on the repair plan and sends the repair guidance information to the user so that the user can repair the target fault corresponding to the fault log based on the repair guidance information.

[0082] For example, during robot operation, the motor driver reports an "overcurrent" error, generating a "critical" level fault log. The robot inputs this fault log into its local fault handling model, obtaining a repair solution of attempting to send a "motor soft restart" command. At this point, the robot sends the "motor soft restart" command to the motor driver to repair the target fault corresponding to the fault log. After the motor driver restarts, the fault persists. The robot then sends the repair solution (attempting to send the "motor soft restart" command) and the target fault to the cloud-based fault handling model, obtaining a repair solution that suggests a foreign object may be stuck in the robot's right wheel, requiring removal. The robot announces through its speaker: "Hello, my right wheel drive is malfunctioning. Please check if there is a foreign object stuck in the right wheel?" Simultaneously, the same message is sent to the user's mobile phone via SMS / APP. The user follows the prompts, checks, and removes the stuck foreign object. The robot's sensors detect the obstacle has been removed, and normal operation resumes. The user clicks "Fault Resolved" on the APP.

[0083] The robot fault handling system in this embodiment can automatically repair faults via repair commands or generate repair guidance information, enabling users to repair the target fault corresponding to the fault log based on the repair guidance information. By employing diverse fault repair methods, the system aims to complete fault repairs as much as possible, minimizing the need for maintenance personnel and reducing waiting time for them, thereby improving fault handling efficiency.

[0084] Please refer to Figure 4 , Figure 4 The flowchart illustrates a fourth embodiment of the robot fault handling method provided in this application. The difference between the fourth embodiment and the first to third embodiments is that, after the step of repairing the target fault based on the second repair scheme, the method includes:

[0085] Step S401: If the target fault corresponding to the fault log is successfully repaired based on the second repair scheme, then the second repair scheme and the target fault are stored as first model training data.

[0086] Step S402: During the update cycle of the local fault handling model, the local fault handling model is updated based on the training data of the first model.

[0087] In this embodiment, if the robot in the robot fault handling system successfully repairs the target fault corresponding to the fault log based on the second repair scheme, the second repair scheme and the target fault are stored as the first model training data. During the update cycle of the local fault handling model, the local fault handling model is updated based on the first model training data.

[0088] Understandably, the robot can collect multiple cases of successful repairs based on cloud-based fault handling models as training data for the first model. During the local fault handling model's update cycle, the local fault handling model is updated based on the first model training data, resulting in a more powerful fault handling capability. When encountering the same fault again, a repair solution that can fix the fault can be obtained solely through the local fault handling model, which helps to further improve fault handling efficiency.

[0089] Understandably, the robot can collect multiple successful repair cases based on cloud-based fault handling models as training data for the first model. This training data is then uploaded to the cloud platform, which organizes the training data uploaded by robots of the same model. From this training data, the platform selects the most frequently recurring faults and their corresponding repair solutions as target training data. This target training data is then used to update the local fault handling model, which is subsequently distributed to all robots of the same model. This allows fault repair information to be shared among robots of the same model for updating the local fault handling model, improving its fault handling capabilities and ultimately increasing fault handling efficiency.

[0090] Please refer to Figure 5 , Figure 5 This is a flowchart illustrating the fifth embodiment of the robot fault handling method provided in this application. The difference between the fifth embodiment and the first to fourth embodiments is that, after the step of creating a maintenance work order based on the repair plan and the fault log, and notifying maintenance personnel to repair the target fault, the method further includes:

[0091] Step S501: Obtain the fault handling work order uploaded by the maintenance personnel, and store the target fault and the maintenance plan of the fault handling work order as the second model training data.

[0092] Step S502: During the preset update cycle of the cloud fault handling model, the cloud fault handling model is updated based on the training data of the second model.

[0093] In this embodiment, if the robot in the robot fault handling system cannot repair the target fault based on either the local fault handling model or the cloud-based fault handling model, the repair plan and fault logs are sent to the cloud platform of the robot fault handling system. The cloud platform creates a maintenance work order based on the repair plan and fault logs and notifies maintenance personnel to repair the target fault of the robot. After the maintenance personnel complete the repair of the target fault, the cloud platform of the robot fault handling system retrieves the fault handling work order uploaded by the maintenance personnel, stores the target fault and the repair plan of the fault handling work order as training data for the second model, and updates the cloud-based fault handling model based on the second model training data at a preset update cycle.

[0094] The robot fault handling system in this embodiment updates the cloud-based fault handling model by acquiring fault handling work orders uploaded by maintenance personnel and updating the target fault and fault handling work order repair solutions. This allows the cloud-based fault handling model to learn more about fault repair, which helps improve the model's ability to handle faults and thus improves the efficiency of fault handling.

[0095] refer to Figure 6 , Figure 6 This is a schematic diagram of the robot fault handling device provided in this application. The robot fault handling device includes:

[0096] The first repair module 10 is used to acquire fault logs, input the fault logs into a preset local fault handling model to obtain a first repair scheme, and repair the target fault corresponding to the fault logs based on the first repair scheme.

[0097] The second repair module 20 is used to, if the target fault corresponding to the fault log cannot be repaired based on the repair scheme, input the first repair scheme and the fault log into a preset cloud fault handling model to obtain a second repair scheme, and repair the target fault based on the second repair scheme.

[0098] The notification module 30 is used to create a maintenance work order based on the second repair plan and the fault log if the target fault cannot be repaired based on the second repair plan, and to notify the maintenance personnel to repair the target fault.

[0099] It is understood that the robot fault handling device in this embodiment corresponds to the robot fault handling method in the above embodiment, and the options in the above embodiment are also applicable to this embodiment, so they will not be described again here.

[0100] This application also provides a computer device, exemplary of which includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer device to perform the robot fault handling method described above by running the computer program.

[0101] The processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Network Processor (NP), Digital Signal Processor (DSP), Application-Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0102] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory is used to store computer programs, and the processor can execute the computer programs accordingly after receiving execution instructions.

[0103] This application also provides a computer storage medium for storing the computer program used in the aforementioned computer device. The computer storage medium can be a readable storage medium, a non-volatile storage medium, or a volatile storage medium. For example, the computer storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0104] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, in alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0105] In addition, the functional modules or units in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0106] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0107] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A robot fault handling method, characterized in that, The method is applied to a robot fault handling system, which includes a robot and a cloud platform. The robot communicates with the cloud platform via a private encrypted network. The method includes: The robot's fault log is obtained, and the fault log is input into the robot's local fault handling model to obtain a first repair solution. The robot then repairs the target fault corresponding to the fault log based on the first repair solution. The local fault handling model is a general lightweight fault handling model generated by the cloud platform based on the robot's unique identifier and the robot's common, severe, and common-sense faults. If the target fault corresponding to the fault log cannot be repaired based on the first repair solution, the first repair solution and the fault log are input into the cloud fault handling model in the cloud platform to obtain a second repair solution, and the target fault is repaired by the robot based on the second repair solution. The cloud fault handling model has all records of fault handling since the production of the robot, as well as all hardware information, structural information, software information, parameter configuration, hardware lifespan, and hardware / software functional boundaries of the robot. If the target fault cannot be repaired based on the second repair solution, a maintenance work order is created through the cloud platform based on the second repair solution and the fault log, and maintenance personnel are notified to repair the target fault.

2. The robot fault handling method according to claim 1, characterized in that, The method further includes: Obtain the fault log and determine the severity of the fault based on the fault log; Based on the severity of the fault, a target fault handling model is determined from the local fault handling model or the cloud fault handling model, and the fault log is input into the target fault handling model to obtain the first repair solution or the second repair solution.

3. The robot fault handling method according to claim 2, characterized in that, The steps of obtaining fault logs and determining the severity of the fault based on the fault logs include: During robot operation, the operation log is monitored in real time and fault logs in the operation log are identified; When a fault log is obtained, the fault log is parsed to determine the target fault, and the severity of the fault is determined based on the target fault and a preset mapping relationship between fault and severity.

4. The robot fault handling method according to claim 2, characterized in that, The step of determining the target fault handling model from the local fault handling model or the cloud-based fault handling model based on the severity of the fault includes: If the severity of the fault is less than a preset severity threshold, then the local fault handling model is determined as the target fault handling model. If the severity of the fault is greater than a preset severity threshold, then the cloud-based fault handling model is determined as the target fault handling model.

5. The robot fault handling method according to claim 2, characterized in that, The step of repairing the target fault corresponding to the fault log based on the first repair scheme or the second repair scheme includes: Based on the first repair scheme or the second repair scheme, a repair instruction is generated, and the target fault corresponding to the fault log is repaired based on the repair instruction; or Based on the first repair scheme or the second repair scheme, repair guidance information is generated and sent to the user so that the user can repair the target fault corresponding to the fault log based on the repair guidance information.

6. The robot fault handling method according to claim 1, characterized in that, After the step of repairing the target fault based on the second repair scheme, the following steps are included: If the target fault is successfully repaired based on the second repair scheme, the second repair scheme and the target fault are stored as training data for the first model. During the update cycle of the local fault handling model, the local fault handling model is updated based on the training data of the first model.

7. The robot fault handling method according to claim 1, characterized in that, After the step of creating a maintenance work order based on the second repair plan and the fault log, and notifying maintenance personnel to repair the target fault, the following steps are included: Obtain the fault handling work order uploaded by the maintenance personnel, and store the target fault and the maintenance plan of the fault handling work order as the second model training data; The cloud-based fault handling model is updated based on the training data of the second model during the preset update cycle of the cloud-based fault handling model.

8. A robot fault handling device, characterized in that, The robot fault handling device includes: The first repair module is used to obtain the robot's fault logs, input the fault logs into the robot's local fault handling model to obtain a first repair solution, and repair the target faults corresponding to the fault logs by the robot based on the first repair solution. The local fault handling model is a general lightweight fault handling model generated by the cloud platform based on the robot's unique identifier and the robot's common, severe, and common-sense faults. The second repair module is used to input the first repair scheme and the fault log into the cloud fault handling model in the cloud platform to obtain the second repair scheme if the target fault corresponding to the fault log cannot be repaired based on the first repair scheme. The robot then repairs the target fault based on the second repair scheme. The cloud fault handling model has all records of fault handling since the production of the robot, as well as all hardware information, structural information, software information, parameter configuration, hardware lifespan, and hardware / software functional boundaries of the robot. The notification module is used to create a maintenance work order through the cloud platform based on the second repair solution and the fault log if the target fault cannot be repaired based on the second repair solution, and to notify maintenance personnel to repair the target fault.

9. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement the robot fault handling method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when run on a processor, executes the robot fault handling method according to any one of claims 1-7.

Images