Equipment exception handling method and device, equipment, medium and product

Abstract

The invention discloses an equipment exception handling method and device, equipment, a medium and a product. The method comprises the following steps: in response to an exception handling request for target equipment, determining an alarm text sent by a secondary master station system, and extracting exception alarm information in the alarm text to generate corresponding structured data; according to the structured data, performing matching in a preset case library to obtain a target case, and determining a processing effect evaluation value corresponding to the target case; and according to the structured data, the target case, the processing effect evaluation value of the target case and the current operation data, determining an exception handling decision and a decision priority of the target equipment, so as to perform exception handling on the target equipment. According to the technical scheme, intelligent and automatic decision support of the secondary equipment of the converter station can be realized, and related personnel can be helped to make decisions quickly and accurately, so that the reliability and the operation and maintenance efficiency of the equipment and the stability of a power grid are improved.

Description

Technical Field

[0001] The present invention relates to the field of power grid technology, and in particular to a method, device, equipment, medium and product for handling equipment abnormality. Background Art

[0002] With the continuous expansion of power system capacity and the rapid development of new energy, the role of converter stations in power systems is becoming increasingly important, and they undertake key tasks such as optimizing resource allocation, improving transmission efficiency and utilization of new energy. However, the operation of equipment in the power grid is complex, and the technical maturity has not yet fully met the requirements of automated operation and maintenance. Existing fault diagnosis and decision-making systems usually rely on manual experience and rule bases, lack the support of intelligent methods, which makes the operation and maintenance of equipment inefficient and easily affected by human factors. In this case, equipment failures are not handled in time or the best time for handling is missed, which may affect the stable operation of the power system.

[0003] Therefore, how to realize intelligent and automated decision support for converter station secondary equipment to help relevant personnel make decisions quickly and accurately, thereby improving equipment reliability, operation and maintenance efficiency, and grid stability, is an urgent problem to be solved. Summary of the invention

[0004] The present invention provides a method, device, equipment, medium and product for handling equipment abnormality, so as to realize intelligent and automated decision support for secondary equipment of converter stations, help relevant personnel make decisions quickly and accurately, thereby improving equipment reliability, operation and maintenance efficiency and stability of power grid.

[0005] According to one aspect of the present invention, a method for handling device abnormalities is provided, comprising:

[0006] In response to an exception handling request for a target device, determining an alarm text sent by the secondary master station system, and extracting abnormal alarm information in the alarm text to generate corresponding structured data;

[0007] According to the structured data, match the preset case library to obtain the target case, and determine the treatment effect evaluation value corresponding to the target case;

[0008] Based on the structured data, the target case, the processing effect evaluation value of the target case and the current operation data, the exception handling decision and decision priority for the target device are determined to perform exception handling on the target device.

[0009] According to another aspect of the present invention, there is provided a device abnormality processing apparatus, comprising:

[0010] A generating module, for determining the alarm text sent by the secondary master station system in response to an exception handling request for the target device, and extracting the abnormal alarm information in the alarm text to generate corresponding structured data;

[0011] A determination module is used to match the structured data in a preset case library to obtain a target case and determine a treatment effect evaluation value corresponding to the target case;

[0012] The processing module is used to determine the exception handling decision and decision priority for the target device according to the structured data, the target case, the processing effect evaluation value of the target case and the current operation data, so as to perform exception handling on the target device.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the device exception handling method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the device exception handling method described in any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the device exception handling method according to any embodiment of the present invention is implemented.

[0019] The technical solution of the embodiment of the present invention, in response to the abnormal processing request for the target device, determines the alarm text sent by the secondary master station system, and extracts the abnormal alarm information in the alarm text to generate corresponding structured data; according to the structured data, matches in the preset case library to obtain the target case, and determines the processing effect evaluation value corresponding to the target case; according to the structured data, the target case, the processing effect evaluation value of the target case and the current operation data, determines the abnormal processing decision and decision priority for the target device, so as to perform abnormal processing on the target device. In this way, intelligent and automated decision support for the secondary equipment of the converter station can be realized, helping relevant personnel to make decisions quickly and accurately, thereby improving the reliability of the equipment, operation and maintenance efficiency and stability of the power grid.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a flow chart of a device exception handling method provided by Embodiment 1 of the present invention;

[0023] Figure 2A This is a schematic diagram of the process of generating an exception handling decision provided by the second embodiment of the present invention;

[0024] Figure 2B is a schematic diagram of a process for updating a case library provided in the second embodiment of the present invention;

[0025] Figure 3 It is a structural block diagram of a device exception handling apparatus provided by Embodiment 3 of the present invention;

[0026] Figure 4 It is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", "target", "candidate", "alternative", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0029] Embodiment 1

[0030] Figure 1 1 is a flow chart of a device exception handling method provided in the first embodiment of the present invention; this embodiment is applicable to the case where the exception handling system parses the alarm file and detects the exception to perform exception handling on the target device. The method can be executed by a device exception handling device. The device exception handling device can be implemented in the form of hardware and / or software. The device exception handling device can be configured in an electronic device, such as in the exception handling system, such as Figure 1 As shown, the device exception handling method includes:

[0031] S101. In response to an exception handling request for a target device, determine an alarm text sent by a secondary master station system, and extract abnormal alarm information in the alarm text to generate corresponding structured data.

[0032] Among them, the target device can specifically be a secondary device of the converter station, such as a protection device, a monitoring device, etc. The exception handling request refers to a request to parse the alarm text corresponding to the target device to obtain an exception handling decision and perform exception handling on the target device. Different target devices can be configured in the secondary master station system. The alarm text refers to information that can characterize the situation where an abnormality has occurred in the target device. The alarm text can be, for example, "Channel one communication is abnormal, the bit error rate is high", "Channel one communication is lost, serious", real-time sensor signals, fiber channel connection status (represented by Boolean values) and data bit error rate". The data bit error rate can be a numerical feature, represented by a BER value (bit error rate).

[0033] Optionally, abnormal alarm information in the alarm text is extracted to generate corresponding structured data, including: using a preset large language model to perform semantic analysis and keyword extraction on the alarm text to obtain abnormal alarm information; based on preset format requirements, the abnormal alarm information is spliced ​​to generate corresponding structured data.

[0034] Among them, the abnormal alarm information may include at least one of the following: abnormal number, abnormal name, abnormal type, abnormal severity and abnormal characteristics. Structured data refers to data obtained by combining abnormal alarm information according to preset format requirements. Structured data can be, for example: {"number":"C001","name":"channel one communication abnormality","type":"line protection device abnormal alarm","severity":"serious","feature":{"bit error rate":"10^-3","optical fiber connection status":"disconnected"}}. The preset large language model can be a pre-trained GPT (Generative Pre-Trained Transformer) model.

[0035] It should be noted that the powerful natural language processing capabilities of the large language model can automatically extract key data from the alarm description of the converter station secondary system and convert it into structured information. These structured data include alarm number, name, type, severity, etc., which speeds up the processing of alarm information, reduces manual intervention, and improves the efficiency and accuracy of information processing.

[0036] Optionally, a preset large language model is used to perform semantic analysis and keyword extraction on the alarm text to obtain abnormal alarm information, including: based on preset target keywords, keyword extraction on the alarm text to obtain the abnormal number, abnormal name, abnormal type and abnormal severity recorded in the alarm text; using a preset large language model to perform semantic analysis on the alarm text to obtain abnormal features corresponding to the alarm text, and determine the abnormal alarm information based on the abnormal number, abnormal name, abnormal type, abnormal severity and abnormal features.

[0037] Exemplarily, the alarm text and sensor data can be processed through pre-trained large language models and prompt word technology, including: extracting fields from the alarm description, such as alarm number, type and severity; automatically parsing key parameters in the sensor signal (such as bit error rate and channel connection status), and further converting natural language descriptions and sensor signals into structured data formats.

[0038] S102: According to the structured data, matching is performed in a preset case library to obtain a target case, and a processing effect evaluation value corresponding to the target case is determined.

[0039] The preset case library may be a CBR (Case-Based Reasoning) case library. The target case refers to a case in the preset case library whose similarity with the abnormal alarm case corresponding to the structured data is greater than a preset similarity threshold. The processing effect evaluation value refers to an indicator value obtained by evaluating the processing effect of the target device in the case.

[0040] Optionally, according to the abnormal alarm information in the structured data, matching can be performed in the preset case library respectively to determine the similarity between each candidate case in the preset case library and the structured data, and the candidate case with a similarity greater than a preset similarity threshold is determined as the target case.

[0041] Optionally, the preset case library may also store weight information of each candidate case. Accordingly, after determining the candidate cases whose similarity is greater than a preset similarity threshold, the weight information of the candidate cases may be compared, and a preset number of candidate cases with higher weight information may be determined as target cases.

[0042] Optionally, determining the processing effect evaluation value corresponding to the target case includes: determining the processing success rate, processing time evaluation value and effect stability evaluation value corresponding to the target case based on the processing status information of the target device in the target case; determining the processing effect evaluation value corresponding to the target case based on the processing success rate, processing time evaluation value and effect stability evaluation value, combined with preset evaluation weights.

[0043] The processing information may include at least one of the following: the number of successful device recovery and the total number of processing cases, the actual processing time, the scheduled processing time, the device operation stability and the continuous operation time. The preset evaluation weights may include the weights corresponding to the processing success rate, the processing time evaluation value and the effect stability evaluation value, expressed as α, β and γ, and the sum of the three is 1.

[0044] For example, according to the treatment success rate, treatment time evaluation value and effect stability evaluation value, combined with the preset evaluation weights, the treatment effect evaluation value E corresponding to the target case can be determined based on the following formula: k :

[0045] E k =αP k +βT k ×γS k

[0046] Among them, α, β and γ are the weights corresponding to the treatment success rate, treatment time evaluation value and effect stability evaluation value, respectively. k , T k and S k They respectively represent the treatment success rate, treatment effectiveness evaluation value and effect stability evaluation value.

[0047] Optionally, based on the processing information of the target device in the target case, determine the processing success rate, processing time evaluation value and effect stability evaluation value corresponding to the target case, including: determining the number of successful device recovery times and the total number of processing cases based on the processing information of the target device in the target case, so as to obtain the processing success rate corresponding to the target case; determining the actual processing time and the scheduled processing time based on the processing information of the target device in the target case, so as to obtain the processing time evaluation value corresponding to the target case; determining the equipment operation stability and continuous operation time based on the processing information of the target device in the target case, so as to obtain the effect stability evaluation value corresponding to the target case.

[0048] For example, according to the number of successful device recovery times and the total number of processed cases, the processing success rate corresponding to the target case can be obtained based on the following formula:

[0049]

[0050] For example, according to the actual processing time and the scheduled processing time, the processing time evaluation value corresponding to the target case can be obtained based on the following formula:

[0051]

[0052] For example, according to the equipment operation stability and continuous operation time, the effect stability evaluation value corresponding to the target case can be obtained based on the following formula:

[0053] S k = Equipment operation stability × continuous operation time

[0054] S103: Determine an exception handling decision and decision priority for the target device according to the structured data, the target case, the processing effect evaluation value of the target case, and the current operation data, so as to perform exception handling on the target device.

[0055] The abnormality handling decision may include at least one of the following: inspection steps, fault isolation, and recovery operations. The current operation data may be related switch quantities, device status, environmental parameters, etc.

[0056] Optionally, the final case that is most suitable for the current structured data situation can be screened out from the target cases based on the structured data, the target cases, and the processing effect evaluation values ​​of the target cases, and the processing decision of the final case can be determined as the exception processing decision for the target device. The decision priority of each exception processing decision can be further analyzed in combination with the current operating data situation, so as to perform exception processing on the target device in order of priority.

[0057] For example, the structured data may include the following information: number (such as C001); name (such as "channel 1 communication abnormality"); type (such as "line protection device abnormality alarm"); severity (such as "serious"); characteristic attributes: real-time device status (such as fiber channel connection status: disconnected; bit error rate 10 -3 wait).

[0058] Optionally, the structured data, target cases, treatment effect evaluation values ​​of the target cases, and current running data may be input into a pre-trained large model, and a multi-step treatment recommendation may be generated through the large model, with a priority assigned to each step.

[0059] Exemplarily, the abnormal handling decision may include the following process: 1. Fault analysis: analyze the severity of the alarm (such as "serious" or "abnormal"); extract real-time data features (such as high bit error rate, disconnected fiber connection, etc.); 2. Generate preliminary suggestions: check steps, check the channel fiber connection status and bit error rate; fault isolation, if the fiber is damaged, switch to the backup channel; restore operation, recalibrate the time synchronization module, and restore communication quality. 3. Optimization suggestions: dynamically adjust suggestions based on real-time signals. For example: if the bit error rate is high but the fiber connection is normal, prioritize checking the data transmission quality; if the fiber is disconnected, directly perform isolation operations.

[0060] Exemplarily, the decision priority can be determined based on the following formula:

[0061] P k =f(S,T,E)

[0062] Among them, P k It represents the decision priority, S represents the severity of the alarm (such as "serious" or "abnormal"), T represents the real-time signal status (such as bit error rate, fiber connection status); E represents the processing effect evaluation value of the target case (such as success rate and timeliness).

[0063] Optionally, after determining the exception handling decision and decision priority for the target device to perform exception handling on the target device, it also includes: generating an exception alarm case based on the alarm text and the exception handling decision, and matching the exception alarm case in a preset case library to determine whether the exception alarm case is a new case; if not, determining a processing effect evaluation value of the exception alarm case based on the feedback result after the exception handling of the target device, and evaluating whether to update the weight of the exception alarm case in the preset case library based on the processing effect evaluation value.

[0064] For example, every time an abnormal alarm is processed, the large model will automatically update the case library according to the decision-making processing effect; for example, when a new abnormal alarm is processed, the system will automatically store it as a new case in the case library to provide a reference for subsequent similar abnormal alarm scenarios. In addition, the system can optimize the weights and processing strategies of existing cases. Based on the feedback mechanism of the decision-making processing effect, the system dynamically adjusts the priority and weight of the case to make it more in line with the current actual fault handling needs. Specifically, cases with better processing effects will receive higher weights and become the priority reference for future decision-making, ensuring that the case library improves the accuracy and adaptability of decisions in continuous updates.

[0065] Exemplarily, the case weights in the case library may be updated based on the following formula:

[0066] W Updated =W Old +γ·ΔE k

[0067] Where W Updated is the updated case weight, W Old is the original weight of the case, γ is the learning rate, which is used to control the amplitude of weight update, ΔE k The change in processing results reflects the degree of improvement of the “decision-making processing effect” of the case.

[0068] Exemplarily, the workflow of the preset large model may include input: complete abnormal alarm cases that have been processed and feedback results of decision-making processing effects. Feedback learning: Evaluate the decision-making effect of the case based on the processing feedback and calculate the "decision-making processing effect" indicator; then dynamically adjust the weight of the case based on the weight update formula, and automatically optimize the case processing strategy (such as adjusting the priority of the processing steps). Output: The optimized case library. If it is a new abnormal alarm, it will be stored in the case library as a new case. If it is a known abnormal alarm, the system will optimize the original weight of the corresponding case.

[0069] The technical solution of the embodiment of the present invention, in response to the abnormal processing request for the target device, determines the alarm text sent by the secondary master station system, and extracts the abnormal alarm information in the alarm text to generate corresponding structured data; according to the structured data, matches in the preset case library to obtain the target case, and determines the processing effect evaluation value corresponding to the target case; according to the structured data, the target case, the processing effect evaluation value of the target case and the current operation data, determines the abnormal processing decision and decision priority for the target device, so as to perform abnormal processing on the target device. In this way, intelligent and automated decision support for the secondary equipment of the converter station can be realized, helping relevant personnel to make decisions quickly and accurately, thereby improving the reliability of the equipment, operation and maintenance efficiency and stability of the power grid.

[0070] Embodiment 2

[0071] Figure 2A This is a schematic diagram of the process of generating an exception handling decision provided by the second embodiment of the present invention; Figure 2B is a flow chart of updating the case library provided in the second embodiment of the present invention; based on the above embodiment, this embodiment provides a preferred example of generating an exception handling decision corresponding to an abnormal situation of a device based on a case library to perform exception handling, specifically, Figure 2A As shown, the method includes the following process:

[0072] According to the alarm text, the multimodal real-time data is determined, and the converter station intelligent decision-making model is used to extract features and preprocess to achieve case-based structural processing. Further, case matching is performed based on the nearest neighbor method according to the case library to determine whether the abnormal alarm case is composed of new cases. If not, the decision processing effect feedback is performed to optimize the weight of the original case, so as to use the converter station intelligent decision-making model combined with real-time data to optimize the case. If so, the converter station intelligent decision-making model is directly used to analyze the characteristics of the new case, generate new case processing suggestions, obtain CBR structured new cases, and import the new cases into the case library, where the case library stores cases in the form of problems + solutions. Finally, after obtaining the optimized case or new case, the case can be called to generate decision suggestions and obtain abnormal processing decisions.

[0073] For example, see Figure 2B , the preset large model can be used to update the weights of historical cases in the preset case library. Specifically, the input data of the preset large model can be the processed abnormal alarm cases and the feedback results of the decision processing effect. The abnormal alarm case can be determined whether it is a new case based on the output result. If so, it is stored in the case library as a new case. If not, the "decision processing effect" indicator Ek is calculated to further determine whether the decision processing effect is improved. If so, the original weight of the historical case is updated, otherwise, the original weight of the historical case is maintained.

[0074] Optionally, the present invention can realize intelligent analysis and decision-making of secondary equipment in converter stations by calling API (Application Programming Interface) interface, combined with fine-tuning and prompt word technology of large model. API interface realizes the standardized processing logic framework of the model, dynamic adaptation of real-time data input and feedback mechanism, ensures that the model can generate personalized, multi-step processing suggestions based on real-time alarms and historical case libraries, and automatically updates CBR case libraries to optimize decision-making effects.

[0075] Exemplarily, the preparation of the converter station intelligent analysis and decision-making large model may include the following steps: 1. Fine-tuning. Fine-tuning is a key step for the large model to learn the converter station operation and maintenance rules, training materials and historical case libraries, and provide a standardized processing logic framework for the subsequent prompt word project. The fine-tuning data includes operation and maintenance specifications, training materials, CBR case libraries and other materials related to the operation and maintenance of the converter station. By internalizing these materials, the large model can learn the processing logic of common alarm types (such as communication failures and abnormal protection actions) and standardize them. 2. On the fine-tuned large model, the prompt words are used to guide the model to dynamically adapt to new fault scenarios, and combined with real-time signals, reasonable suggestions are generated for alarms that have not appeared. This process can optimize the priority and execution order of the suggestions. At the same time, the CBR case library is automatically updated to adapt to the ever-changing operating environment. In this step, the following two functions are mainly implemented: (1) For alarm scenarios that have never been seen before, refer to historical cases in the CBR case library and generate personalized suggestions in combination with real-time data; (2) Based on real-time input information (such as numerical data and Boolean data) and historical decision suggestion feedback, dynamically adjust the execution order and priority of processing suggestions to ensure that each decision step can quickly respond to the current alarm scenario, and optimize the construction and application of subsequent case libraries through feedback.

[0076] Exemplarily, the present invention proposes a large model guidance method based on prompt words for intelligent analysis and decision-making of secondary equipment in converter stations. Through prompt word design, combined with a large model that internalizes operation and maintenance specifications, training materials, and CBR case libraries after fine-tuning, standardized and dynamically adaptive processing suggestions are generated. Prompt word design not only solves the problem of rigid traditional CBR rules, but also significantly improves the flexibility and accuracy of fault handling. Specifically, the specific design of prompt words includes:

[0077] Task role setting: Define the large model as an "intelligent analysis expert for the power system", focusing on alarm analysis and processing suggestion generation for secondary equipment, ensuring the model's task focus in specific scenarios.

[0078] Input data normalization: Convert multimodal input data (such as alarm description, real-time signal status) into structured CBR input format, covering alarm number, type, severity, etc., to ensure efficient model processing.

[0079] Dynamic adaptation mechanism: Combines real-time input data (such as environmental parameters and equipment status) with decision-making effect feedback to dynamically adjust processing logic and priority, adapt to changing fault scenarios, and improve decision-making flexibility.

[0080] Output content optimization: Generate standardized processing suggestions including inspection, fault isolation, recovery operations, etc., and mark the priority of each step to optimize the execution process of fault handling.

[0081] Exemplarily, the design of prompt words mainly includes the following steps: Role and task definition: clarify the task scope of the large model, and set the model roles and responsibilities through prompt word descriptions, such as abnormal alarm signal analysis and processing suggestion generation. Input data processing: guided by prompt words, unstructured natural language data (such as alarm descriptions) and multimodal information are converted into a standardized CBR input format for subsequent processing. Output suggestion generation: combined with the CBR case library, real-time data and decision-making effect feedback, the model is guided by prompt words to generate personalized multi-step processing suggestions that meet the actual scenario, and dynamically optimize according to priority.

[0082] This paper proposes an intelligent analysis and decision-making scheme for abnormal alarms of secondary equipment in converter stations based on large model enhanced CBR, aiming to improve the abnormal alarm analysis and decision support of secondary equipment in converter stations. The system combines the semantic understanding and generation capabilities of large models with traditional CBR methods, and can dynamically generate personalized fault handling decision suggestions based on real-time data and case libraries when facing complex fault scenarios, thereby improving the accuracy, efficiency and flexibility of fault handling and reducing the impact of human intervention on equipment safety and grid stability.

[0083] Embodiment 3

[0084] Figure 3 1 is a structural block diagram of a device exception handling device provided in Embodiment 3 of the present invention; this embodiment can be applied to the case where the exception handling system parses the alarm file and detects the exception to perform exception handling on the target device, and the device exception handling device provided in the embodiment of the present invention can execute the device exception handling method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method; the device exception handling device can be implemented in the form of hardware and / or software, and configured in an electronic device with a device exception handling function, such as in an exception handling system, such as Figure 3 As shown, the device exception handling device specifically includes:

[0085] A generating module 301 is used to determine the alarm text sent by the secondary master station system in response to the abnormality processing request for the target device, and extract the abnormality alarm information in the alarm text to generate corresponding structured data;

[0086] The determination module 302 is used to match the structured data in a preset case library to obtain a target case and determine a treatment effect evaluation value corresponding to the target case;

[0087] The processing module 303 is used to determine the exception handling decision and decision priority for the target device according to the structured data, the target case, the processing effect evaluation value of the target case and the current operation data, so as to perform exception handling on the target device.

[0088] The technical solution of the embodiment of the present invention, in response to the abnormal processing request for the target device, determines the alarm text sent by the secondary master station system, and extracts the abnormal alarm information in the alarm text to generate corresponding structured data; according to the structured data, matches in the preset case library to obtain the target case, and determines the processing effect evaluation value corresponding to the target case; according to the structured data, the target case, the processing effect evaluation value of the target case and the current operation data, determines the abnormal processing decision and decision priority for the target device, so as to perform abnormal processing on the target device. In this way, intelligent and automated decision support for the secondary equipment of the converter station can be realized, helping relevant personnel to make decisions quickly and accurately, thereby improving the reliability of the equipment, operation and maintenance efficiency and stability of the power grid.

[0089] Furthermore, the generating module 301 may include:

[0090] The obtaining unit is used to perform semantic analysis and keyword extraction on the warning text by using a preset large language model to obtain abnormal warning information;

[0091] The generating unit is used to perform splicing processing on the abnormal alarm information based on the preset format requirements to generate corresponding structured data.

[0092] Furthermore, the unit is specifically used for:

[0093] Based on the preset target keywords, keyword extraction is performed on the alarm text to obtain the abnormal number, abnormal name, abnormal type and abnormal severity recorded in the alarm text;

[0094] A preset large language model is used to perform semantic analysis on the alarm text to obtain the abnormal features corresponding to the alarm text, and the abnormal alarm information is determined based on the abnormal number, abnormal name, abnormal type, abnormal severity and abnormal features.

[0095] Further, the determination module 302 may include:

[0096] A first determination unit is used to determine the processing success rate, processing time evaluation value and effect stability evaluation value corresponding to the target case according to the processing status information of the target device in the target case;

[0097] The second determination unit is used to determine the processing effect evaluation value corresponding to the target case according to the processing success rate, the processing time evaluation value and the effect stability evaluation value, combined with the preset evaluation weight.

[0098] Further, the first determining unit is specifically used for:

[0099] According to the processing information of the target device in the target case, the number of successful device recovery times and the total number of processing cases are determined to obtain the processing success rate corresponding to the target case;

[0100] According to the processing information of the target device in the target case, the actual processing time and the scheduled processing time are determined to obtain the processing time evaluation value corresponding to the target case;

[0101] According to the processing information of the target device in the target case, the equipment operation stability and continuous operation time are determined to obtain the effect stability evaluation value corresponding to the target case.

[0102] Furthermore, the above device is also used for:

[0103] Generate an abnormal alarm case based on the alarm text and the abnormal handling decision, and match the abnormal alarm case in the preset case library to determine whether the abnormal alarm case is a new case;

[0104] If not, the processing effect evaluation value of the abnormal alarm case is determined according to the feedback result after the target device abnormality is processed, so as to evaluate whether to update the weight of the abnormal alarm case in the preset case library according to the processing effect evaluation value.

[0105] Embodiment 4

[0106] Figure 4 It is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment 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 processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0107] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0108] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0109] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a device exception handling method.

[0110] In some embodiments, the device exception handling method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the device exception handling method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the device exception handling method in any other appropriate manner (e.g., by means of firmware).

[0111] Various implementations 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-chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0112] Computer programs for implementing 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, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0113] In the context of the present invention, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. A more specific example of a machine readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0114] To provide interaction with a user, the systems and techniques described herein may 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 a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0115] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0116] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0117] In one embodiment, the embodiment of the present invention further includes a computer program product, the computer program product includes a computer program, and the computer program implements the device exception handling method of any embodiment of the present invention when executed by a processor.

[0118] The computer program product may be implemented in one or more programming languages ​​or combinations thereof to write computer program code for performing the operations of the present invention, including object-oriented programming languages ​​and conventional procedural programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0119] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0120] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for handling device abnormalities, characterized in that: include: In response to an exception handling request for a target device, determine an alarm text sent by the secondary master station system, and extract abnormal alarm information in the alarm text to generate corresponding structured data; According to the structured data, match the preset case library to obtain the target case, and determine the treatment effect evaluation value corresponding to the target case; Based on the structured data, the target case, the processing effect evaluation value of the target case and the current operation data, the exception handling decision and decision priority for the target device are determined to perform exception handling on the target device.

2. The method according to claim 1, characterized in that Extract abnormal alarm information from the alarm text to generate corresponding structured data, including: Use the preset large language model to perform semantic analysis and keyword extraction on the alarm text to obtain abnormal alarm information; Based on the preset format requirements, the abnormal alarm information is spliced ​​and processed to generate corresponding structured data.

3. The method according to claim 2, characterized in that Use the preset large language model to perform semantic analysis and keyword extraction on the alarm text to obtain abnormal alarm information, including: Based on the preset target keywords, keyword extraction is performed on the alarm text to obtain the abnormal number, abnormal name, abnormal type and abnormal severity recorded in the alarm text; A preset large language model is used to perform semantic analysis on the alarm text to obtain the abnormal features corresponding to the alarm text, and the abnormal alarm information is determined based on the abnormal number, abnormal name, abnormal type, abnormal severity and abnormal features.

4. The method according to claim 1, characterized in that Determine the treatment effect evaluation value corresponding to the target case, including: According to the processing information of the target device in the target case, determine the processing success rate, processing time evaluation value and effect stability evaluation value corresponding to the target case; Based on the processing success rate, processing time evaluation value and effect stability evaluation value, combined with the preset evaluation weights, the processing effect evaluation value corresponding to the target case is determined.

5. The method according to claim 4, characterized in that According to the processing information of the target device in the target case, determine the processing success rate, processing time evaluation value and effect stability evaluation value corresponding to the target case, including: According to the processing information of the target device in the target case, the number of successful device recovery times and the total number of processing cases are determined to obtain the processing success rate corresponding to the target case; According to the processing information of the target device in the target case, the actual processing time and the scheduled processing time are determined to obtain the processing time evaluation value corresponding to the target case; According to the processing information of the target device in the target case, the equipment operation stability and continuous operation time are determined to obtain the effect stability evaluation value corresponding to the target case.

6. The method according to claim 1, characterized in that After determining the exception handling decision and decision priority for the target device to perform exception handling on the target device, it also includes: Generate an abnormal alarm case based on the alarm text and the abnormal handling decision, and match the abnormal alarm case in the preset case library to determine whether the abnormal alarm case is a new case; If not, the processing effect evaluation value of the abnormal alarm case is determined according to the feedback result after the target device abnormality is processed, so as to evaluate whether to update the weight of the abnormal alarm case in the preset case library according to the processing effect evaluation value.

7. A device for handling equipment abnormalities, characterized in that: include: A generating module, for determining the alarm text sent by the secondary master station system in response to an exception handling request for the target device, and extracting the abnormal alarm information in the alarm text to generate corresponding structured data; A determination module is used to match the structured data in a preset case library to obtain a target case and determine a treatment effect evaluation value corresponding to the target case; The processing module is used to determine the exception handling decision and decision priority for the target device according to the structured data, the target case, the processing effect evaluation value of the target case and the current operation data, so as to perform exception handling on the target device.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the device exception handling method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the device exception handling method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program implements the device exception handling method according to any one of claims 1 to 6.

Images