Fault solving method and device

Through artificial intelligence generation solutions and instruction sets, the inefficiency of operation and maintenance personnel in troubleshooting is solved, rapid fault resolution and verification is achieved, and the operation and maintenance capabilities of different enterprises are adapted to the operation and maintenance capabilities of different enterprises, improving the operation and maintenance process efficiency and user experience.

CN118890260APending Publication Date: 2024-11-01珠海科创储能科技有限公司
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411299468.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-18
Publication Date
2024-11-01

AI Technical Summary

Technical Problem

When the energy storage equipment or server equipment fails, the operation and maintenance personnel may not be able to arrive at the site in time or need to find a solution, resulting in low maintenance efficiency and additional time is required to judge and monitor after the processing is completed.

Method used

Adopt artificial intelligence-based fault solution, and automatically generates a set of instructions through alarm information generation solutions, including execution instructions and guidance instructions, which are used to repair equipment, improve fault maintenance efficiency, and reduce operation and maintenance through intelligent device interaction and verification. Additional time investment for staff.

Benefits of technology

It improves fault maintenance efficiency, reduces the additional time investment of operation and maintenance personnel, ensures rapid resolution and effective verification of faults, adapts to the operation and maintenance capabilities of different enterprises, and improves operation and maintenance process efficiency and user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118890260A_ABST
    Figure CN118890260A_ABST
Patent Text Reader

Abstract

The invention discloses a fault solution method and device. The method comprises the steps that a second device generates a solution based on artificial intelligence and alarm information of a first device; the second equipment generates an instruction set based on the solution, the instruction set is used for repairing the first equipment, and the instruction set comprises at least one of execution instructions and guidance instructions; and the second device pushes a solution corresponding to the guidance instruction on a third device of the user and / or a fourth device of the expert in response to the guidance instruction included in the instruction set. According to the embodiment of the invention, the problem of low fault maintenance efficiency in related technologies is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of operation and maintenance technology, and in particular, to a fault resolution method and device. Background Art

[0002] When energy storage equipment or server equipment fails, maintenance personnel need to quickly repair and troubleshoot. However, after the failure occurs, maintenance personnel may not be able to arrive at the site immediately or need to find a suitable solution, resulting in delays in processing.

[0003] In addition, after the processing is completed, a period of tracking is required, which requires operation and maintenance personnel to invest extra time in judgment and monitoring. Summary of the invention

[0004] In view of this, the embodiment of the present application provides a fault solution method and device to at least solve the problem of low fault maintenance efficiency in the related art. The fault solution method and device provided in the embodiment of the present application are implemented as follows: In the first aspect, the embodiment of the present application provides a fault resolution method, which is applied to the first device, and the method includes: the second device generates a solution based on artificial intelligence and the alarm information of the first device; the second device generates an instruction set based on the solution, and the instruction set is used to repair the first device, and the instruction set includes at least one of: execution instructions and guidance instructions; the second device responds to the instruction set including guidance instructions, and pushes the solution corresponding to the guidance instruction on the user's third device and / or the expert's fourth device. The above technical solution completely entrusts the fault analysis work to AI. After the analysis is completed, the corresponding instructions can be automatically generated: if it is an execution instruction, it will directly control the operation and maintenance system to solve the fault; if it is a guidance instruction, the user can solve the fault according to the professional solution provided by AI, thereby improving the efficiency of fault maintenance.

[0005] In combination with the first aspect, in some embodiments, the solution corresponding to the guidance instruction includes at least one of the following: the first type of solution, the first type of solution is executed by the user independently; the second type of solution, the second type of solution is executed by the user independently after the online review is passed, and the online review is used to review whether the required operation and maintenance qualification data of the second type of solution matches the actual operation and maintenance qualification data of the user enterprise; the third type of solution, the third type of solution is executed with the participation of experts. It is understandable that different enterprises have different operation and maintenance capabilities, and reasonable delegation of power based on the enterprise operation and maintenance qualifications allows on-site enterprise operation and maintenance personnel to handle faults in a timely manner, thereby improving fault maintenance efficiency.

[0006] In combination with the first aspect, in some embodiments, the second type of solution is initially invisible on the third device and visible on the fourth device; in response to the expert completing the review of the second type of solution on the fourth device and performing a security operation, the second device updates the second type of solution on the third device to a visible state. The above technical solution improves the efficiency of the operation and maintenance process and the user experience through intelligent device interaction.

[0007] In combination with the first aspect, in some embodiments, the second device generates a solution based on artificial intelligence and the alarm information of the first device, including: the second device determines several first fault areas of the first device based on artificial intelligence in response to the alarm information being an unknown area fault alarm information; the second device generates a final solution based on the communication record of requesting the artificial intelligence for a solution to the second fault area, the communication record is issued by the operation and maintenance personnel device, and the second fault area is determined by the on-site operation and maintenance personnel under the instruction of the first fault area. It is understandable that the alarm information is relatively vague, that is, the alarm may be caused by multiple factors. Therefore, artificial intelligence can be used for step-by-step guidance to help operation and maintenance personnel quickly solve the problem.

[0008] In combination with the first aspect, in some embodiments, the method further includes: in response to the first device being repaired, the second device pushes and matches the actual operation status of the repaired target of the first device and the expected operation status generated by artificial intelligence on the third device and / or the fourth device within a preset verification time period; in response to the above matching meeting the preset conditions, the second device pushes the judgment result of successful repair on the third device and / or the fourth device. The above technical solution effectively reduces the extra time investment of operation and maintenance personnel after repairing the fault through intelligent fault verification push.

[0009] In combination with the first aspect, in some embodiments, the method further includes: the second device performs AI push based on the after-sales communication records of the communication group.

[0010] In the second aspect, an embodiment of the present application provides a fault-solving device, which is applied to a second device, and the device includes: a first generation module, which is used to generate a solution based on artificial intelligence and the alarm information of the first device; a second generation module, which is used to generate an instruction set based on the solution, and the instruction set is used to repair the first device, and the instruction set includes at least one of: execution instructions and guidance instructions; a push module, which is used to push a solution corresponding to the guidance instruction on the user's third device and / or the expert's fourth device in response to the instruction set including the guidance instruction.

[0011] In a third aspect, an embodiment of the present application provides a server, which includes: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by one or more processors, the one or more processors execute any one of the fault resolution methods of the above embodiments.

[0012] In a fourth aspect, an embodiment of the present application provides an energy storage system, which includes: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by one or more processors, the one or more processors execute any one of the fault resolution methods of the above embodiments.

[0013] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, the computer-readable storage medium including a stored program, wherein when the program is running, a processor of the device is controlled to execute any one of the fault resolution methods of the above embodiments.

[0014] It should be understood that the second to fifth aspects of the present application correspond to the technical solutions of the first aspect of the present application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation methods are similar and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0016] Figure 1 It is a flowchart of a fault resolution method provided in an embodiment of the present application.

[0017] Figure 2 It is a flowchart of a generation solution provided in an embodiment of the present application.

[0018] Figure 3 It is a structural block diagram of a fault solving device provided in an embodiment of the present application.

[0019] Figure 4 It is a structural block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the specific technical solution of the present application will be further described in detail below in conjunction with the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0022] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0023] It should be pointed out that the terms "first\second\third" involved in the embodiments of the present application are used to distinguish similar or different objects, and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0024] An embodiment of the present application discloses a fault solving system, which may include: an operation and maintenance system, which is used to automatically obtain alarm information of a first device. The first device is an energy storage device, which may include a battery management system, a power conversion system, a cooling system, a fire protection module, and a battery. The operation and maintenance system may include an energy management system, and may also include an independent control module. A server is used to implement any of the fault solving methods disclosed in the embodiments of the present application. The server (an example of the second device) is coupled to artificial intelligence. An electronic device is used to connect to the server. The electronic device (i.e., the third device and the fourth device) can be a general electronic terminal, such as a mobile phone, a laptop computer, a tablet computer, and a car computer.

[0025] In some other embodiments, the first device may be data center equipment and cooling equipment thereof.

[0026] Figure 1 This is a flowchart of a fault resolution method provided by an embodiment of the present application. Figure 1 As shown, the fault solution is applied to the first device in the above embodiment and may include the following steps: S101. The second device generates a solution based on artificial intelligence and the alarm information of the first device.

[0027] S102. The second device generates an instruction set based on the solution, where the instruction set is used to repair the first device, and the instruction set includes at least one of: an execution instruction and a guidance instruction.

[0028] S103. In response to the instruction set including the guidance instruction, the second device pushes a solution corresponding to the guidance instruction on the user's third device and / or the expert's fourth device.

[0029] In the above embodiment, the first alarm information, such as battery disconnection alarm information, can be obtained through the battery management system, the second alarm information, such as leakage alarm information, can be obtained through the cooling system, and the log data in the energy storage device can be read to obtain the third alarm information (i.e., software operation alarm information).

[0030] In the above embodiments, artificial intelligence may include an LLM model, RAG technology, and an Agent intelligent body. In terms of hierarchical relationships, the LLM model provides basic language understanding and generation capabilities, and the RAG technology uses the knowledge base on this basis to enhance the output accuracy and relevance of the LLM model, while the Agent intelligent body uses the capabilities of LLM and RAG at a higher level and combines its own perception and decision-making capabilities to perform specific tasks, such as log analysis, performance monitoring, and hardware fault analysis. The data fed to the artificial intelligence includes but is not limited to an enterprise knowledge base and / or an external knowledge base. Exemplarily, an enterprise knowledge base may include technical information accumulated by the enterprise during the operation process, such as failure case analysis and response strategies, where the response strategy file may include operation and maintenance qualification configuration, and the external knowledge base may include the content of technical forums, academic papers, and technical specifications.

[0031] Example (1): After receiving hardware alarm information such as battery disconnection or cooling system leakage, the server cluster will analyze and generate specific guidance instructions, which will then be sent to the handheld terminal used by the operation and maintenance personnel to assist the operation and maintenance personnel in responding to hardware problems quickly and accurately.

[0032] As a further example, when the artificial intelligence detects a battery disconnection alarm message that belongs to the first alarm message, it will automatically generate a solution for handling the battery disconnection. For example, this solution will first involve an assessment of the location and cause of the disconnection, and then recommend the best response measures, including reconnecting the battery line or replacing damaged batteries or line components. Next, a set of specific operating instructions will be provided to users and / or experts. In addition, in order to prevent similar problems that may occur in the future, the solution also includes suggestions for adjusting the battery management system settings. The remaining hardware alarm messages are similar and will not be repeated.

[0033] Example (2): For software failures such as system errors or performance degradation, the server cluster will also capture the corresponding alarm information. After analyzing these software alarms, it will generate execution instructions, including but not limited to automatic repair scripts, system updates or restart commands. Subsequently, these execution instructions will be sent directly back to the operation and maintenance system for execution to automatically correct software problems or optimize system performance.

[0034] The above technical solution completely leaves the fault analysis work to AI. After the analysis is completed, the corresponding instructions can be automatically generated: if it is an execution instruction, it will directly control the operation and maintenance system to solve the fault; if it is a guidance instruction, the user can solve the fault according to the professional solution provided by AI, thereby improving the efficiency of fault maintenance.

[0035] Possibly, the operation and maintenance system may further include an operation and maintenance robot, which executes part or all of the guidance instructions of the above embodiments.

[0036] It is understandable that the alarm information is relatively vague, that is, the alarm may be caused by multiple factors. For example, the leakage problem may come from the leakage of different components such as pipes and battery packs. Therefore, artificial intelligence can be used to provide step-by-step guidance to help operation and maintenance personnel quickly solve the problem. Specifically, Figure 2 As shown, the second device generates a solution based on artificial intelligence and the alarm information of the first device, which may include the following steps: S1011. In response to the alarm information being unknown area fault alarm information, the second device determines several first fault areas of the first device based on artificial intelligence.

[0037] S1012. The second device generates a final solution based on the communication record of requesting the artificial intelligence for a solution to the second fault area, the communication record is sent by the operation and maintenance personnel device, and the second fault area is determined by the on-site operation and maintenance personnel under the instruction of the first fault area.

[0038] It can be understood that an unknown area fault is a potential area fault, and its information is set manually or determined by AI.

[0039] In the above embodiment, the second device can determine several first fault areas of the first device based on artificial intelligence and fault data of devices of the same type and / or devices of the same batch. Specifically, artificial intelligence first confirms the type of fault, then traces the fault data of devices of the same type and / or devices of the same batch according to the fault type, and finally uses the historical fault area with a high fault rate as the first fault area, for example, uses the top three historical fault areas with the highest fault rate as the first fault area.

[0040] In some other embodiments, the second device can determine several first fault regions of the first device based on artificial intelligence, device region, and fault data of devices of the same type and / or the same batch. Different from the above embodiments, artificial intelligence traces back the fault data of devices of the same type and / or the same batch in the same or similar device region according to the fault type.

[0041] For example, for leakage problems, AI analyzes historical leakage data to provide the most likely leakage areas on the operator's handheld terminal, such as recommended interfaces. After arriving at the site, the operator can use the above instructions to find the real fault area. When the leakage is found to occur at the battery pack communication interface, the operator can interact deeply with the AI ​​through the handheld terminal. Based on the operator's feedback, AI will push relevant waterproof glue usage points and operating specifications.

[0042] It is understandable that different enterprises have different operation and maintenance capabilities, and reasonable delegation of authority based on the enterprise's operation and maintenance qualifications allows on-site enterprise operation and maintenance personnel to handle faults in a timely manner, thereby improving fault maintenance efficiency. Specifically, the corresponding solutions for the guidance instructions include at least one of the following: (1) The first type of solution: The first type of solution is executed by the user independently and can be sent to the third device and the fourth device, or only to the third device.

[0043] (2) The second type of solution: The second type of solution is executed independently by the user after passing the online review. The online review is used to review whether the required operation and maintenance qualification data of the second type of solution matches the actual operation and maintenance qualification data of the user enterprise, where the actual operation and maintenance qualification data is stored in the second device.

[0044] (3) The third type of solution: The third type of solution is executed by experts and can be sent to the third device and the fourth device, or only to the fourth device.

[0045] In the above embodiment, the online review is an expert review by a third party or the seller.

[0046] Possibly, the online audit is an intelligent model audit.

[0047] In the above embodiment, the operation and maintenance qualification data includes at least one of the following: (a) Qualifications for operation and maintenance equipment.

[0048] (b) Professional certificates and years of experience of operation and maintenance personnel.

[0049] (c) Qualifications acquired by operation and maintenance personnel through training provided by the sales company.

[0050] In the above embodiments, the first type of solution is less professional than the second type of solution, but its operation and maintenance safety is higher. The third type of solution requires the assistance of external technical personnel to implement.

[0051] For example, the solutions for replacing the cabinet rubber strips and handling battery pack communication interface leakage are preset or AI-classified as the first type of solutions because they do not require specific qualifications and are safe to operate. The battery disconnection handling solution involves power testing, poses a risk of electric shock, and requires relevant qualifications, so it is preset or AI-classified as the second type of solution. The solution for replacing core hardware belongs to the third category and requires intervention by external manufacturer technicians for replacement.

[0052] Further, for the second type of solution, it is initially in an invisible state on the third device, but is in a visible state on the fourth device. In response to the expert completing the review of the second type of solution on the fourth device and performing a security operation, the second device automatically updates the second type of solution on the third device to a visible state.

[0053] In the above embodiment, the second device will push the stored actual operation and maintenance qualification data to the fourth device used by the expert. The expert will compare the required qualifications (qualifications subjectively considered by the expert) with the information provided by the second device based on his or her professional experience to complete the solution review. After the review is completed, expert identity verification is required, such as through face recognition to confirm the identity. Once the verification is successful, the corresponding second-category solution on the third device will automatically become visible for the user to use.

[0054] As an optional implementation method, the operation and maintenance qualification data required for the second type of solution is generated by artificial intelligence and displayed on the interface of the fourth device. At the same time, the actual operation and maintenance qualification data will also be pushed to the fourth device. The expert's task is to review these qualifications to improve work efficiency and experience.

[0055] Exemplarily, users and experts can join the same communication group to facilitate direct communication, and information about the second type of solution can also be shared in the group chat.

[0056] In addition, artificial intelligence can provide intelligent push notifications based on after-sales communication records in the communication group, including answering questions and providing solutions.

[0057] In some embodiments, the fault resolution method may also include: in response to the first device being repaired, the second device pushes and matches the actual operation status of the repaired target of the first device and the expected operation status generated by artificial intelligence on the third device and / or the fourth device within a preset verification time period. In response to the above matching meeting the preset conditions, the second device pushes the judgment result of successful repair on the third device and / or the fourth device.

[0058] In the above embodiment, when the number of matches meets the preset number, the judgment result of successful repair is pushed.

[0059] For example, after solving the battery pack communication interface leakage problem, the server cluster will update and push the actual value and expected value of the liquid sensor reading in the cabinet to the group chat interface for one-to-one matching. After the preset verification time period, if the actual value of all sensor readings matches the expected value, the server cluster will notify the group chat interface to confirm that the repair work has been successfully completed.

[0060] Those skilled in the art will appreciate that all or part of the steps in the method for implementing the above embodiments may be completed by instructing related hardware through a program, and the corresponding program may be stored in a computer-readable storage medium.

[0061] It should be noted that although the method operations of the above embodiments are described in a specific order in the embodiments, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps described can change the order of execution. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step for execution, and / or one step can be decomposed into multiple steps for execution.

[0062] Figure 3 is a structural block diagram of a fault resolution device provided in an embodiment of the present application. Figure 3 As shown, the fault solving device, applied to the second device in the above embodiment, may include the following modules: The first generating module 301 is used to generate a solution based on artificial intelligence and the alarm information of the first device.

[0063] The second generating module 302 is used to generate an instruction set based on the solution, where the instruction set is used to repair the first device, and the instruction set includes at least one of: an execution instruction and a guidance instruction.

[0064] The push module 303 is configured to push a solution corresponding to the guidance instruction on the user's third device and / or the expert's fourth device in response to the instruction set including the guidance instruction.

[0065] Figure 4 is a structural block diagram of a computer device provided in an embodiment of the present application. Figure 4 As shown, the computer device, applied to an energy storage system or a server cluster, may include a processor 402 and a memory 403 connected via a system bus 401, the memory 403 stores a computer program, and when the computer program is executed by the processor 402, any one of the fault resolution methods disclosed in the embodiments of the present application is implemented.

[0066] The embodiment of the present application discloses a storage medium. The storage medium is a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, any fault resolution method disclosed in the embodiment of the present application is implemented.

[0067] The above are only preferred embodiments of the present patent application, but the protection scope of the present patent application is not limited thereto. Any technician familiar with the technical field can make equivalent substitutions or changes within the scope disclosed in the present patent application according to the technical solution and inventive concept of the present patent application, which are all within the protection scope of the present patent application.

Claims

1. A fault resolution method, characterized in that: Applied to a first device, comprising: The second device generates a solution based on artificial intelligence and the alarm information of the first device; The second device generates an instruction set based on the solution, the instruction set is used to repair the first device, and the instruction set includes at least one of: an execution instruction and a guidance instruction; In response to the instruction set including the guidance instruction, the second device pushes a solution corresponding to the guidance instruction on the user's third device and / or the expert's fourth device; The corresponding solutions for the guidance instructions include at least one of the following: The first type of solution is implemented by the user independently; The second type of plan is implemented by the user independently after the online review is passed. The online review is used to review whether the operation and maintenance qualification data required for the second type of plan matches the actual operation and maintenance qualification data of the user company. The online review is an expert review; The third type of plan is implemented with the participation of experts.

2. The troubleshooting method according to claim 1, characterized in that: The operation and maintenance qualification data includes at least one of the following: Qualifications for operation and maintenance equipment; Professional certificates and years of experience of operation and maintenance personnel; The qualifications that operation and maintenance personnel obtain through training provided by the sales company.

3. The troubleshooting method according to claim 1, characterized in that: The second type of solution is initially invisible on the third device and visible on the fourth device; In response to the expert completing the review of the second type of solution on the fourth device and performing the security operation, the second device updates the second type of solution on the third device to a visible state.

4. The troubleshooting method according to claim 1, characterized in that: The second device generates a solution based on artificial intelligence and the alarm information of the first device, including: In response to the alarm information being an unknown area fault alarm information, the second device determines a number of first fault areas of the first device based on artificial intelligence and historical fault data of the first device, where the first fault areas are potential fault areas; The second device generates a final solution based on the communication record of requesting the artificial intelligence for a solution to the second fault area. The communication record is sent by the operation and maintenance personnel's device. The second fault area is determined by the on-site operation and maintenance personnel under the indication of the first fault area. The second fault area is the real fault area.

5. The troubleshooting method according to claim 1, characterized in that: Also includes: In response to the first device being repaired, the second device pushes and matches the actual operation status of the repaired target of the first device and the expected operation status generated by the artificial intelligence on the third device and / or the fourth device within a preset verification time period; In response to the above matching meeting the preset condition, the second device pushes a judgment result of successful repair on the third device and / or the fourth device.

6. The troubleshooting method according to claim 1, characterized in that: Also includes: The second device performs AI push based on the after-sales communication records of the communication group.

7. A fault solving device, characterized in that: Applied to the second device, comprising: A first generating module, configured to generate a solution based on artificial intelligence and the alarm information of the first device; A second generating module is used to generate an instruction set based on the solution, the instruction set is used to repair the first device, and the instruction set includes at least one of: an execution instruction and a guidance instruction; a push module, configured to push a solution corresponding to the guidance instruction on a third device of the user and / or a fourth device of the expert in response to the instruction set including the guidance instruction; The corresponding solutions for the guidance instructions include at least one of the following: The first type of solution is implemented by the user independently; The second type of plan is implemented by the user independently after the online review is passed. The online review is used to review whether the operation and maintenance qualification data required for the second type of plan matches the actual operation and maintenance qualification data of the user company. The online review is an expert review; The third type of plan is implemented with the participation of experts.

8. A server, characterized in that: include: one or more processors; A storage device for storing one or more programs; When one or more programs are executed by one or more processors, the one or more processors execute the fault resolution method according to any one of claims 1 to 6.

9. An energy storage system, characterized in that: include: one or more processors; A storage device for storing one or more programs; When one or more programs are executed by one or more processors, the one or more processors execute the fault resolution method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The invention comprises a stored program, wherein when the program is executed, a processor of the device is controlled to execute the fault resolution method according to any one of claims 1 to 6.

Citation Information

Cited By

  • Data center alarm processing method and device based on artificial intelligence, and electronic equipment

    CN119728387A

  • Artificial intelligence-based data center alarm processing method and device, and electronic device

    CN119728387B