Energy storage operation and maintenance work auditing method, device and equipment and storage medium

Abstract

The invention discloses an energy storage operation and maintenance work auditing method and device, equipment and a storage medium. The method comprises the following steps: acquiring a maintenance operation log and a maintenance operation standard about the maintenance operation of the energy storage equipment; according to the maintenance job log, the maintenance operation standard and a target semantic matching model obtained through pre-training, determining an obtained comprehensive confidence score of the maintenance job log; and determining an operation auditing result of the energy storage operation and maintenance operation according to the comprehensive confidence score. And under the condition that the audit result is that the maintenance operation is abnormal, generating a maintenance rectification suggestion for performing maintenance operation on the energy storage equipment, thereby realizing full-process intelligentization from automatic audit, deep logic verification to suggestion generation, and greatly improving accuracy, efficiency and automation level of compliance audit.

Description

Technical Field

[0001] This invention relates to the field of energy storage equipment maintenance technology, and in particular to a method, apparatus, equipment and storage medium for energy storage operation and maintenance audit. Background Technology

[0002] Energy storage systems are a crucial component in building new power systems. Regular and standardized maintenance of energy storage devices is essential for ensuring their safe and stable operation. Detailed information on each maintenance operation must be systematically and accurately recorded in the maintenance log. Maintenance procedures are critical for tracing the work process, assessing equipment status, and clarifying safety responsibilities. Therefore, ensuring the standardization and compliance of maintenance operations recorded in the maintenance log is an indispensable part of the safety management of energy storage power stations.

[0003] Currently, the review of maintenance logs relies primarily on manual work. Reviewers must use their personal experience and memory to compare log entries against complex standard operating procedures and safety protocols. This method is not only inefficient and time-consuming, but its strong subjectivity also leads to inconsistent review standards. Different personnel may interpret the same record item differently, making it difficult to effectively detect semantic errors. Existing automated rule validation tools can only identify superficial issues such as missing fields and formatting errors, and are completely incapable of handling logical omissions that require deep semantic understanding to identify.

[0004] Therefore, there is an urgent need in this field for a technical solution that can deeply understand the connotation of maintenance specifications and realize intelligent semantic analysis of job logs, so as to overcome the limitations of manual review and the superficial defects of traditional automation tools. Summary of the Invention

[0005] This invention provides a method, apparatus, equipment, and storage medium for auditing energy storage operation and maintenance, enabling intelligent operation throughout the entire process from automated review and in-depth logical verification to suggestion generation, thereby significantly improving the accuracy, efficiency, and automation level of compliance review.

[0006] According to one aspect of the present invention, a method for auditing energy storage operation and maintenance is provided. The method includes:

[0007] Obtain maintenance logs and maintenance operation standards for energy storage equipment;

[0008] Based on the maintenance operation log and the maintenance operation standards, as well as the pre-trained target semantic matching model, the comprehensive confidence score of the maintenance operation log is determined.

[0009] Based on the comprehensive confidence score, the operation review result of the energy storage operation and maintenance is determined, wherein the operation review result is normal maintenance operation and abnormal maintenance operation, and the abnormal maintenance operation includes missing operation and maintenance operation and maintenance log conflict.

[0010] If the audit result indicates an abnormal maintenance operation, a maintenance and rectification suggestion is generated to perform maintenance work on the energy storage device.

[0011] According to another aspect of the present invention, an energy storage operation and maintenance work auditing device is provided. The device includes:

[0012] The maintenance data acquisition module is used to acquire maintenance logs and maintenance operation standards related to the maintenance of energy storage equipment.

[0013] The confidence score determination module is used to determine the comprehensive confidence score of the maintenance operation log based on the maintenance operation log, the maintenance operation standard, and the pre-trained target semantic matching model.

[0014] The operation and maintenance operation review module is used to determine the operation review result of the energy storage operation and maintenance operation based on the comprehensive confidence score. The operation review result is either normal or abnormal. The abnormal operation includes missing operation and maintenance operation and maintenance log conflict.

[0015] The maintenance and rectification suggestion module is used to generate maintenance and rectification suggestions for the energy storage equipment when the audit result indicates that the maintenance operation is abnormal.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the energy storage operation and maintenance audit method according to any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the energy storage operation and maintenance audit method according to any embodiment of the present invention.

[0021] The technical solution of this invention involves acquiring maintenance operation logs and standards for energy storage equipment maintenance. Based on these logs and standards, and a pre-trained target semantic matching model, a comprehensive confidence score is determined for the maintenance operation logs. The operation review result is then determined based on this score. If the review result indicates an abnormal maintenance operation, maintenance rectification suggestions are generated for the energy storage equipment maintenance. This overcomes the limitations of manual review and the superficiality of traditional automated tools, achieving end-to-end intelligent processing from automated review and deep logic verification to action suggestion generation, significantly improving the accuracy, efficiency, and automation level of compliance review.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of an energy storage operation and maintenance review method provided by an embodiment of the present invention;

[0025] Figure 2 This is a flowchart of an energy storage operation and maintenance review method provided by an embodiment of the present invention;

[0026] Figure 3 This is a structural diagram of an energy storage operation and maintenance auditing device according to an embodiment of the present invention;

[0027] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the energy storage operation and maintenance audit method of this invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Figure 1 This is a flowchart illustrating a method for auditing energy storage operation and maintenance (O&M) procedures, provided by an embodiment of the present invention. This embodiment is applicable to situations requiring standardized auditing of energy storage equipment maintenance operations. The method can be executed by an energy storage O&M operation auditing device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0031] S101. Obtain maintenance logs and maintenance operation standards for energy storage equipment.

[0032] Maintenance operation logs can refer to documents that record the execution of specific maintenance operations for energy storage equipment, including operation time, personnel, equipment, execution steps, observation data, and abnormal situations. Maintenance operation standards can refer to documents that define the specifications, processes, and requirements that must be followed when performing maintenance operations on specific energy storage equipment, including Standard Operating Procedures (SOP) document libraries, equipment manufacturer's technical manuals, internal EHS (Environment, Health, and Safety) specifications, and industry standards (such as NFPA and IEC standards).

[0033] Specifically, maintenance job logs awaiting review are retrieved from the CMMS database or file server via API interfaces, and maintenance operation standards are retrieved and extracted from the standard document library.

[0034] S102. Based on the maintenance operation log and the maintenance operation standard, as well as the pre-trained target semantic matching model, determine the comprehensive confidence score of the maintenance operation log.

[0035] For example, the target semantic matching model can be a deep neural network model. In one embodiment, depending on actual needs, the target semantic matching model is trained to predict a comprehensive confidence score. The comprehensive confidence score can refer to the similarity score between the maintenance job log and the maintenance operation standard.

[0036] Specifically, in one embodiment, maintenance operation logs and maintenance operation standards are input into a target semantic matching model to determine the similarity score between the maintenance operation logs and maintenance operation standards. Based on the output of the target semantic matching model, a comprehensive confidence score can be obtained.

[0037] S103. Determine the operation review result of the energy storage operation and maintenance work based on the comprehensive confidence score.

[0038] The job review results are categorized as normal maintenance operation and abnormal maintenance operation. Abnormal maintenance operation includes missing maintenance jobs and conflicting maintenance logs.

[0039] Specifically, by comparing the comprehensive confidence score with a pre-set threshold score, the operation review result of energy storage operation and maintenance can be determined based on the relationship between the comprehensive confidence score and the pre-set threshold score.

[0040] For example, determining the operation review result of the energy storage operation and maintenance task based on the comprehensive confidence score includes: for any log splitting statement in the maintenance operation log, if the comprehensive confidence score of the log splitting statement is less than a preset missing threshold, then the operation review result of the energy storage operation and maintenance task is determined to be a missing operation and maintenance task; if any log splitting statement is semantically mutually exclusive with other log splitting statements, and the comprehensive confidence scores of both are not less than the missing threshold, then the operation review result of the energy storage operation and maintenance task is determined to be a maintenance log conflict; otherwise, the operation review result of the energy storage operation and maintenance task is determined to be a normal maintenance operation.

[0041] It should be noted that the maintenance log consists of multiple log splitting statements, and each log splitting statement has a corresponding comprehensive confidence score. The missing value threshold can be set according to the actual situation. Preferably, in this invention, the missing value threshold can be set to 0.75.

[0042] Specifically, if the overall confidence score of any log splitting statement is less than the missing value threshold, it indicates that a critical maintenance operation is highly likely to have not been executed or recorded, and is directly judged as a missing maintenance task. When the confidence scores of all log splitting statements meet the threshold, the semantic mutual exclusion relationship between the log splitting statements will be checked.

[0043] If any log splitting statement is found to be semantically mutually exclusive with other log splitting statements, and both of their confidence scores are not less than the missing judgment threshold, it indicates that there is a logical contradiction in the content of the maintenance job log, which may be due to a typo or false record. It is judged as a maintenance log conflict. For example, statement A records "the equipment has been shut down for maintenance", while statement B records "the equipment is running for testing at rated power".

[0044] When all statements meet the confidence level and there are no semantically mutually exclusive situations, the job review result is determined to be a normal maintenance operation.

[0045] S104. If the audit result indicates that the maintenance operation is abnormal, generate maintenance and rectification suggestions for the energy storage equipment.

[0046] Specifically, if the audit result indicates an abnormal maintenance operation, maintenance and rectification suggestions for the energy storage equipment are generated based on the content of the abnormal maintenance operation and by analyzing the standard clauses related to the abnormal content.

[0047] For example, if the original sentence of the maintenance operation abnormality is "the battery room ventilator was not tested monthly", and the related clause is SOP-A.3.5 "the ventilator should be tested for no less than 5 minutes every month", then the maintenance rectification suggestions can be: 1) supplement the test running time; 2) record the speed and current; 3) attach the test run date.

[0048] The step of generating maintenance and rectification suggestions for the energy storage equipment includes: determining target related clauses and maintenance anomaly information associated with the maintenance operation anomaly from the maintenance operation standards; inputting the target related clauses and maintenance anomaly information into a pre-trained target rectification suggestion model for analysis; and obtaining maintenance and rectification suggestions based on the output of the target rectification suggestion model.

[0049] The target-related clauses can refer to clauses in the maintenance operation standards that are associated with maintenance operation anomalies. Maintenance anomaly information can refer to abnormal operation content in the maintenance work log, such as "monthly trial run of the battery room ventilator was not performed." The target rectification suggestion model is a neural network model obtained by training on training samples.

[0050] Specifically, the relevant target clauses and maintenance anomaly information are identified and input into the target rectification suggestion model for analysis. The model deeply understands the logical relationship between anomalies and clauses, and based on its learned knowledge, generates professional suggestions that conform to safety standards and technical terminology. After necessary formatting, the output of the target rectification suggestion model is presented as the final maintenance rectification suggestion and passed to the user interface or work order system.

[0051] For example, the training process of the target rectification suggestion model includes: acquiring sample training information and label rectification suggestions corresponding to the sample training information; inputting the sample training information into a preset rectification suggestion model for suggestion decision-making, and obtaining output rectification suggestions based on the output of the preset rectification suggestion model; determining the training error based on the output rectification suggestions and the label rectification suggestions, and backpropagating the training error to the preset rectification suggestion model to adjust the network parameters in the preset rectification suggestion model; when a preset convergence condition is met, determining that the training of the preset rectification suggestion model has ended, and obtaining the target rectification suggestion model.

[0052] The sample training information may include sample anomaly information and the sample operation standards corresponding to the sample anomaly information.

[0053] Specifically, based on the training function, the training error can be determined according to the output rectification suggestions and labeled rectification suggestions of the preset rectification suggestion model. This training error is then backpropagated to the preset rectification suggestion model, and the network parameters are adjusted until a preset convergence condition is met, such as the number of iterations reaching a preset number or the training error converging. At this point, the training of the preset rectification suggestion model is considered complete, and the trained model can be used as the target decision network model. By utilizing sample anomaly information, sample operation standards, and corresponding labeled rectification suggestions for model training, the accuracy of the rectification suggestions from the target rectification suggestion model can be guaranteed.

[0054] The technical solution of this invention involves acquiring maintenance operation logs and standards for energy storage equipment maintenance. Based on these logs and standards, and a pre-trained target semantic matching model, a comprehensive confidence score is determined for the maintenance operation logs. The operation review result is then determined based on this score. If the review result indicates an abnormal maintenance operation, maintenance rectification suggestions are generated for the energy storage equipment maintenance. This overcomes the limitations of manual review and the superficiality of traditional automated tools, achieving end-to-end intelligent processing from automated review and deep logic verification to action suggestion generation, significantly improving the accuracy, efficiency, and automation level of compliance review.

[0055] Figure 2 This is a flowchart illustrating a method for auditing energy storage operation and maintenance tasks according to an embodiment of the present invention. Based on the aforementioned embodiments, this embodiment further refines the determination of the comprehensive confidence score for the maintenance operation log. For example... Figure 2 As shown, the method includes:

[0056] S201. Obtain maintenance logs and maintenance operation standards for energy storage equipment.

[0057] S202. Perform statement splitting on the maintenance operation log to obtain log splitting statements, and perform statement splitting on the maintenance operation standard to obtain maintenance standard clauses.

[0058] Specifically, the maintenance job log and maintenance operation standards are separated into log split statements and maintenance standard clauses, respectively.

[0059] S203. For each log segmentation statement, determine the comprehensive confidence score of the maintenance operation log based on the log segmentation statement, the maintenance standard clause of each statement, and the target semantic matching model.

[0060] Specifically, in another embodiment, for each log split statement, the log split statement and each maintenance standard clause are input into the target semantic matching model to determine the similarity score between the log split statement and each maintenance standard clause. Based on the output of the target semantic matching model, the statement confidence score of the log split statement is determined. Then, the statement confidence scores of each log split statement are weighted to obtain a comprehensive confidence score.

[0061] For example, determining the overall confidence score of the maintenance operation log based on the log splitting statement, each maintenance standard clause, and the target semantic matching model includes: inputting the log splitting statement and the maintenance standard clause into a pre-trained target semantic matching model for semantic matching processing to obtain a semantic matching score; performing vector transformation on the log splitting statement and the maintenance standard clause respectively to obtain the log statement vector corresponding to the log splitting statement and the maintenance clause vector corresponding to the maintenance standard clause, and determining the cosine similarity score between the log statement vector and the maintenance clause vector; and determining the overall confidence score of the maintenance operation log based on the semantic matching score and the cosine similarity score.

[0062] The semantic matching score can refer to the semantic similarity score between the log splitting statement and the maintenance standard clause. It is worth noting that, in this invention, the target semantic matching model is preferably trained to predict the semantic matching score between the log splitting statement and the maintenance standard clause.

[0063] Specifically, a semantic matching score is determined between log splitting statements and maintenance standard clauses using a target semantic matching model. A cosine similarity algorithm is used to calculate the cosine similarity score between the log statement vector of the log splitting statements and the maintenance clause vector of the maintenance standard clauses. Then, the overall confidence score for the maintenance operation log is determined using both the semantic matching score and the cosine similarity score.

[0064] For example, determining the overall confidence score of the maintenance operation log based on the semantic matching score and the cosine similarity score includes: determining a first confidence score based on the semantic matching score and a pre-set first preset weight; determining a second confidence score based on the cosine similarity score and a pre-set second preset weight; and determining the overall confidence score based on the first confidence score and the second confidence score.

[0065] Wherein, the sum of the first preset weight and the second preset weight is 1. For example, if the first preset weight is 0.65, then the second preset weight is 0.35.

[0066] Specifically, the product of the semantic matching score and the first preset weight is determined as the first confidence score, and the product of the cosine similarity score and the second preset weight is determined as the second confidence score. The sum of the first confidence score and the second confidence score is determined as the comprehensive confidence score of the log splitting statement. Then, based on the comprehensive confidence score of each log splitting statement, the comprehensive confidence score for maintaining the job log is determined.

[0067] Specifically, the overall confidence score of the log splitting statement is determined as follows:

[0068]

[0069] in, This refers to the overall confidence score of the log splitting statement. This refers to the first preset weight. This refers to the semantic matching score. This refers to the second preset weight. This refers to the second confidence score.

[0070] S204. Based on the comprehensive confidence score, determine the operation review result of the energy storage operation and maintenance, wherein the operation review result is normal maintenance operation and abnormal maintenance operation, and the abnormal maintenance operation includes missing operation and maintenance operation and maintenance log conflict.

[0071] S205. If the audit result indicates that the maintenance operation is abnormal, generate maintenance and rectification suggestions for the energy storage equipment.

[0072] The technical solution of this invention, by splitting maintenance operation logs and maintenance operation standards into independent log splitting statements and maintenance standard clauses, can accurately match and analyze the smallest log splitting statements and maintenance standard clauses through a target semantic matching model. This avoids information mixing and noise interference when analyzing long documents as a whole, allowing the analysis focus to be on each specific operation and specification. In addition, all log splitting statements are scored using the same model and algorithm, completely eliminating human subjectivity, ensuring the consistency of audit results, and thus improving the accuracy and efficiency of compliance review.

[0073] Figure 3 This is a schematic diagram of a storage operation and maintenance review device provided in an embodiment of the present invention. Figure 3 As shown, the device includes:

[0074] The maintenance data acquisition module 301 is used to acquire maintenance operation logs and maintenance operation standards related to the maintenance of energy storage equipment.

[0075] The confidence score determination module 302 is used to determine the comprehensive confidence score of the maintenance operation log based on the maintenance operation log, the maintenance operation standard, and the pre-trained target semantic matching model.

[0076] The operation and maintenance operation review module 303 is used to determine the operation review result of the energy storage operation and maintenance operation based on the comprehensive confidence score. The operation review result is either normal maintenance operation or abnormal maintenance operation. The abnormal maintenance operation includes missing operation and maintenance operation and maintenance log conflict.

[0077] The maintenance and rectification suggestion module 304 is used to generate maintenance and rectification suggestions for the energy storage equipment when the audit result indicates that the maintenance operation is abnormal.

[0078] The technical solution of this invention involves acquiring maintenance operation logs and standards for energy storage equipment maintenance. Based on these logs and standards, and a pre-trained target semantic matching model, a comprehensive confidence score is determined for the maintenance operation logs. The operation review result is then determined based on this score. If the review result indicates an abnormal maintenance operation, maintenance rectification suggestions are generated for the energy storage equipment maintenance. This overcomes the limitations of manual review and the superficiality of traditional automated tools, achieving end-to-end intelligent processing from automated review and deep logic verification to action suggestion generation, significantly improving the accuracy, efficiency, and automation level of compliance review.

[0079] Optionally, the confidence score determination module 302 includes:

[0080] The maintenance statement splitting unit is used to split the maintenance operation log into statements to obtain log split statements, and to split the maintenance operation standard into statements to obtain maintenance standard clauses.

[0081] The confidence score determination unit is used to determine the overall confidence score of the maintenance operation log for each log segmentation statement, based on the log segmentation statement, the maintenance standard clauses for each statement, and the target semantic matching model.

[0082] Optionally, the confidence score determination unit includes:

[0083] The matching score determination subunit is used to input the log splitting statements and the maintenance standard terms into a pre-trained target semantic matching model to perform semantic matching processing and obtain a semantic matching score.

[0084] The similarity score determination subunit is used to perform vector transformation on the log splitting statement and the maintenance standard clause respectively to obtain the log statement vector corresponding to the log splitting statement and the maintenance clause vector corresponding to the maintenance standard clause, and to determine the cosine similarity score between the log statement vector and the maintenance clause vector.

[0085] The confidence score determination subunit is used to determine the overall confidence score of the maintenance operation log based on the semantic matching score and the cosine similarity score.

[0086] Optionally, the confidence score determines the sub-unit, specifically for:

[0087] A first confidence score is determined based on the semantic matching score and a pre-set first preset weight;

[0088] The second confidence score is determined based on the cosine similarity score and the pre-set second preset weight;

[0089] A comprehensive confidence score is determined based on the first confidence score and the second confidence score, wherein the sum of the first preset weight and the second preset weight is 1.

[0090] Optionally, the operation and maintenance job review module 303 is specifically used for:

[0091] For any log splitting statement in the maintenance operation log, if the overall confidence score of the log splitting statement is less than the preset missing judgment threshold, then the operation review result of the energy storage operation and maintenance operation is determined to be a missing operation and maintenance operation.

[0092] If any log splitting statement is semantically mutually exclusive with other log splitting statements, and the combined confidence scores of both are not less than the missing judgment threshold, then the operation review result of the energy storage operation and maintenance operation is determined to be a maintenance log conflict.

[0093] Otherwise, the operation review result of the energy storage operation and maintenance is determined to be that the maintenance operation is normal.

[0094] Optionally, the maintenance and rectification suggestion module 304 is used for:

[0095] Identify the target associated clauses and maintenance anomaly information associated with the maintenance operation anomaly from the maintenance operation standards.

[0096] The target-related clauses and maintenance anomaly information are input into a pre-trained target rectification suggestion model for analysis, and maintenance rectification suggestions are obtained based on the output of the target rectification suggestion model.

[0097] Optionally, the maintenance rectification suggestion module 304 includes a rectification suggestion training unit.

[0098] The rectification suggestion training unit is used for:

[0099] Obtain sample training information and corresponding label rectification suggestions, wherein the sample training information includes sample anomaly information and sample operation standards corresponding to the sample anomaly information;

[0100] The sample training information is input into a preset rectification suggestion model for suggestion decision-making, and the output rectification suggestion is obtained based on the output of the preset rectification suggestion model;

[0101] The training error is determined based on the output rectification suggestions and the label rectification suggestions, and the training error is backpropagated to the preset rectification suggestion model to adjust the network parameters in the preset rectification suggestion model.

[0102] When the preset convergence condition is met, the training of the preset rectification suggestion model is considered complete, and the target rectification suggestion model is obtained.

[0103] The energy storage operation and maintenance operation auditing device provided in the embodiments of the present invention can execute the energy storage operation and maintenance operation auditing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0104] Figure 4A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0105] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0106] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0107] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as energy storage operation and maintenance job auditing methods.

[0108] In some embodiments, the energy storage operation and maintenance (O&M) auditing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded into and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the energy storage O&M auditing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the energy storage O&M auditing method by any other suitable means (e.g., by means of firmware).

[0109] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0110] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0111] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0112] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0113] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0114] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0115] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0116] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for auditing energy storage operation and maintenance, characterized in that, include: Obtain maintenance logs and maintenance operation standards for energy storage equipment; Based on the maintenance operation log and the maintenance operation standards, as well as the pre-trained target semantic matching model, the comprehensive confidence score of the maintenance operation log is determined. Based on the comprehensive confidence score, the operation review result of the energy storage operation and maintenance is determined, wherein the operation review result is normal maintenance operation and abnormal maintenance operation, and the abnormal maintenance operation includes missing operation and maintenance operation and maintenance log conflict. If the audit result indicates an abnormal maintenance operation, a maintenance and rectification suggestion is generated to perform maintenance work on the energy storage device.

2. The method according to claim 1, characterized in that, The step of determining the comprehensive confidence score of the maintenance operation log based on the maintenance operation log, the maintenance operation standards, and a pre-trained target semantic matching model includes: The maintenance job log is split into statements to obtain log split statements; The maintenance operation standards are broken down into statements to obtain maintenance standard clauses; For each log segmentation statement, the overall confidence score of the maintenance job log is determined based on the log segmentation statement, the maintenance standard clauses for each statement, and the target semantic matching model.

3. The method according to claim 2, characterized in that, The step of determining the overall confidence score of the maintenance job log based on the log splitting statements and the maintenance standard clauses in each statement, as well as the target semantic matching model, includes: The log splitting statements and the maintenance standard clauses are input into a pre-trained target semantic matching model for semantic matching processing to obtain a semantic matching score. The log splitting statement and the maintenance standard clause are respectively vectorized to obtain the log statement vector corresponding to the log splitting statement and the maintenance clause vector corresponding to the maintenance standard clause, and the cosine similarity score between the log statement vector and the maintenance clause vector is determined. The overall confidence score for the maintenance operation log is determined based on the semantic matching score and the cosine similarity score.

4. The method according to claim 3, characterized in that, The step of determining the overall confidence score of the maintenance operation log based on the semantic matching score and the cosine similarity score includes: A first confidence score is determined based on the semantic matching score and a pre-set first preset weight; The second confidence score is determined based on the cosine similarity score and the pre-set second preset weight; A comprehensive confidence score is determined based on the first confidence score and the second confidence score, wherein the sum of the first preset weight and the second preset weight is 1.

5. The method according to claim 1, characterized in that, The process of determining the operation review result of the energy storage operation and maintenance work based on the comprehensive confidence score includes: For any log splitting statement in the maintenance operation log, if the overall confidence score of the log splitting statement is less than the preset missing judgment threshold, then the operation review result of the energy storage operation and maintenance operation is determined to be a missing operation and maintenance operation. If any log splitting statement is semantically mutually exclusive with other log splitting statements, and the combined confidence scores of both are not less than the missing judgment threshold, then the operation review result of the energy storage operation and maintenance operation is determined to be a maintenance log conflict. Otherwise, the operation review result of the energy storage operation and maintenance is determined to be that the maintenance operation is normal.

6. The method according to claim 1, characterized in that, The generation of maintenance and rectification suggestions for the energy storage equipment includes: Identify the target associated clauses and maintenance anomaly information associated with the maintenance operation anomaly from the maintenance operation standards. The target-related clauses and maintenance anomaly information are input into a pre-trained target rectification suggestion model for analysis, and maintenance rectification suggestions are obtained based on the output of the target rectification suggestion model.

7. The method according to claim 6, characterized in that, The training process of the target rectification suggestion model includes: Obtain sample training information and corresponding label rectification suggestions, wherein the sample training information includes sample anomaly information and sample operation standards corresponding to the sample anomaly information; The sample training information is input into a preset rectification suggestion model for suggestion decision-making, and the output rectification suggestion is obtained based on the output of the preset rectification suggestion model; The training error is determined based on the output rectification suggestions and the label rectification suggestions, and the training error is backpropagated to the preset rectification suggestion model to adjust the network parameters in the preset rectification suggestion model. When the preset convergence condition is met, the training of the preset rectification suggestion model is considered complete, and the target rectification suggestion model is obtained.

8. A device for auditing energy storage operation and maintenance, characterized in that, include: The maintenance data acquisition module is used to acquire maintenance logs and maintenance operation standards related to the maintenance of energy storage equipment. The confidence score determination module is used to determine the comprehensive confidence score of the maintenance operation log based on the maintenance operation log, the maintenance operation standard, and the pre-trained target semantic matching model. The operation and maintenance operation review module is used to determine the operation review result of the energy storage operation and maintenance operation based on the comprehensive confidence score. The operation review result is either normal or abnormal. The abnormal operation includes missing operation and maintenance operation and maintenance log conflict. The maintenance and rectification suggestion module is used to generate maintenance and rectification suggestions for the energy storage equipment when the audit result indicates that the maintenance operation is abnormal.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the energy storage operation and maintenance audit method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the energy storage operation and maintenance audit method according to any one of claims 1-7.

Images