Alarm information processing method, device, electronic device and storage medium

Abstract

The present invention discloses an alarm information processing method, device, electronic device and storage medium. The method comprises: in response to an equipment alarm instruction, obtaining the alarm information corresponding to the equipment alarm instruction; determining an alarm information processing model, obtaining the information classification result corresponding to the alarm information based on the alarm information and the alarm information processing model, the alarm information processing model is used to describe the correspondence between different alarm information and different information classification results, the information classification result describes the classification result of the alarm information, and different information classification results correspond to different processing operation information; determining the processing operation information corresponding to the alarm information based on the information classification result. The present invention solves the problems of heavy workload of monitoring personnel, high probability of misjudgment or omission of events, low intelligent degree of monitoring, low intelligent degree of decision-making, etc., and can greatly reduce the workload and work intensity of operation and maintenance personnel, and improve the efficiency of handling abnormal events and the accuracy of abnormal event judgment.

Description

Technical Field

[0001] The present invention relates to the field of power systems, and in particular to an alarm information processing method, device, electronic equipment and storage medium. Background Art

[0002] At present, the power industry's supervision and operation and maintenance of equipment mainly rely on relevant monitoring systems, and generally implement manual operation and monitoring. When the monitoring system detects an abnormality and issues an alarm, the on-duty personnel analyze and judge the alarm event based on relevant operating procedures, equipment operation and maintenance manuals, and their own experience, and adjust the equipment operating parameters, and perform start-stop and other control operations based on the judgment results.

[0003] With the rapid growth of installed power capacity, the equipment monitoring center monitors a large number of power equipment, especially the new energy centralized control center. New energy power stations have many types of equipment and many manufacturers and models. The number of alarm events that need to be handled is large, and the availability of pushing alarm information is low. There is a lack of senior operation and maintenance personnel. The alarm information is analyzed one by one in the original way, which leads to problems such as heavy workload for monitoring personnel, high probability of misjudgment or omission of events, low degree of intelligence in monitoring, and low degree of intelligence in decision-making. Summary of the invention

[0004] The present invention provides an alarm information processing method, device, electronic device and storage medium to solve the problems of heavy workload of monitoring personnel, high probability of misjudgment or missed judgment of events, low intelligence level of monitoring, low intelligence level of decision-making, etc., greatly reduce the workload and work intensity of operation and maintenance personnel, and improve the efficiency of handling abnormal events and the accuracy of abnormal event judgment.

[0005] According to one aspect of the present invention, there is provided a method for processing alarm information, the method comprising:

[0006] In response to the device alarm instruction, obtaining alarm information corresponding to the device alarm instruction, the alarm information is used to describe the alarm type and alarm level of different types of equipment alarms, and the alarm information at least includes equipment operation data for a preset time period before a reference time, and the reference time is the moment when the device alarm instruction is triggered;

[0007] Determine an alarm information processing model, and obtain an information classification result corresponding to the alarm information based on the alarm information and the alarm information processing model, wherein the alarm information processing model is used to describe the corresponding relationship between different alarm information and different information classification results, and the information classification result describes the classification result of the alarm information, and different information classification results correspond to different processing operation information;

[0008] The processing operation information corresponding to the alarm information is determined based on the information classification result.

[0009] According to another aspect of the present invention, there is provided an alarm information processing device, the device comprising:

[0010] An information acquisition module, configured to respond to an equipment alarm instruction and acquire alarm information corresponding to the equipment alarm instruction, wherein the alarm information is used to describe the alarm type and alarm level of different types of equipment alarms, and the alarm information at least includes equipment operation data for a preset time period before a reference time, wherein the reference time is the time when the equipment alarm instruction is triggered;

[0011] a classification result determination module, used to determine an alarm information processing model, and obtain an information classification result corresponding to the alarm information based on the alarm information and the alarm information processing model, wherein the alarm information processing model is used to describe the corresponding relationship between different alarm information and different information classification results, and the information classification result describes the classification result of the alarm information, and different information classification results correspond to different processing operation information;

[0012] An information determination module is used to determine the processing operation information corresponding to the alarm information based on the information classification result.

[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 alarm information processing 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 alarm information processing method described in any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention, in response to the device alarm instruction, obtains the alarm information corresponding to the device alarm instruction, the alarm information is used to describe the alarm type and alarm level of different types of equipment alarms, the alarm information at least includes the equipment operation data of the preset time period before the reference time, that is, the information contained in the alarm information of the present invention is richer and more detailed, thereby ensuring the richness of the alarm information, further determining the alarm information processing model, and obtaining the information classification result corresponding to the alarm information based on the alarm information and the alarm information processing model, because the alarm information processing model is used to describe the correspondence between different alarm information and different information classification results, the information classification result describes the classification result of the alarm information, and the richness of the alarm information is sufficient, thereby ensuring that the information classification result can be quickly and accurately obtained based on the alarm information processing model and the alarm information, avoiding misjudgment or missed judgment of the event, and improving the handling efficiency of abnormal events and the accuracy of abnormal event judgment. In addition, different information classification results correspond to different processing operation information. Therefore, the processing operation information corresponding to the alarm information is determined based on the information classification result, which solves the problems of heavy workload of monitoring personnel, low intelligent degree of monitoring, and low intelligent degree of decision-making, and greatly reduces the workload and work intensity of operation and maintenance personnel.

[0019] 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

[0020] 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.

[0021] Figure 1 is a flowchart of an alarm information processing method provided according to an embodiment of the present invention;

[0022] Figure 2 is a flowchart of another alarm information processing method provided according to an embodiment of the present invention;

[0023] Figure 3 is a flowchart of another alarm information processing method provided according to an embodiment of the present invention;

[0024] Figure 4 is a structural diagram of an alarm information processing device provided according to an embodiment of the present invention;

[0025] Figure 5It is a structural diagram of an electronic device for implementing the alarm information processing method of the embodiment of the present invention according to the embodiment of the present invention. DETAILED DESCRIPTION

[0026] 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.

[0027] It should be noted that the terms "first", "second" and "third" 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 interchanged 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.

[0028] Embodiment 1

[0029] Figure 1 A flowchart of an alarm information processing method provided in an embodiment of the present invention. This embodiment can be applied to the situation of processing alarm information issued by an electric power monitoring system. The method can be executed by an alarm information processing device. The alarm information processing device can be implemented in the form of hardware and / or software. The alarm information processing device can be configured in any electronic device with network communication function.

[0030] like Figure 1 As shown, the alarm information processing method of the present invention includes the following process:

[0031] S110. In response to the device alarm instruction, obtain alarm information corresponding to the device alarm instruction.

[0032] Among them, the alarm information is used to describe the alarm type and alarm level of different types of equipment alarms. The alarm information at least includes the equipment operation data of the preset time period before the reference time. The reference time is the moment when the equipment alarm instruction is triggered. The equipment operation data in the period before the alarm time will affect the classification of the alarm information. Therefore, adding the equipment operation data is to make the alarm information more accurate and avoid missing factors that may affect the classification results.

[0033] The alarm information includes the device type, brand model, device ID, alarm occurrence time, alarm level, alarm category, alarm information description and alarm code corresponding to the device alarm instruction. The alarm information description is used to describe the device defects when the device alarms, such as high device temperature, excessive device current, etc. The alarm code is the code description information corresponding to different alarm information.

[0034] The alarm information of the present invention comes from the power monitoring system, such as Figure 2 After the power monitoring system shown detects the device alarm instruction, it sends the alarm information corresponding to the device alarm instruction to the module for processing the alarm information.

[0035] S120: Determine an alarm information processing model, and obtain an information classification result corresponding to the alarm information based on the alarm information and the alarm information processing model.

[0036] The alarm information processing model can be used to describe the corresponding relationship between different alarm information and different information classification results. The alarm information processing model is used to analyze the alarm information to classify the alarm information, thereby determining what information classification results different alarm information is.

[0037] The information classification result can describe the classification result of the alarm information. The information classification result can be understood as the classification of the alarm information and the standardized disposal labels. For example, the information classification result can include disposal labels such as push defect, attention, confirmation, false alarm, and shielding. Different information classification results correspond to different processing operation information.

[0038] Specifically, the alarm information processing model is obtained, and it is determined whether the usage time of the alarm information processing model has reached the preset usage time. If the usage time of the alarm information processing model has reached the preset usage time, the alarm information processing model is trained using historical alarm data between the preset time period from the current time to adjust the parameters of the alarm information processing model to obtain an updated alarm information processing model, and the updated alarm information processing model and the alarm information are further used to obtain the information classification result corresponding to the alarm information. If the usage time of the alarm information processing model has not reached the preset usage time, the current alarm information processing model and the alarm information are used to obtain the information classification result corresponding to the alarm information.

[0039] The historical alarm data includes at least historical alarm information and historical information classification results. The historical alarm information includes at least the alarm type, alarm level and equipment operation data including timestamp of different types of equipment. The timestamp is a time window of a preset time interval before and after the alarm moment. There is a corresponding relationship between the historical alarm information and the historical information classification results.

[0040] For example, Figure 2 As shown, the large model is the alarm information processing model of the present invention. The large model receives the alarm information sent by the power monitoring system, and uses the large model to perform reasoning to obtain the information classification result corresponding to the alarm information.

[0041] Optionally, the alarm information processing model includes an information knowledge base, which is placed inside or outside the alarm information processing model. The information knowledge base includes different processing operation information corresponding to different information classification results. Different information classification results correspond to different alarm information. Different alarm information is stored in the information knowledge base in the form of alarm codes.

[0042] Among them, the information knowledge base is placed outside the alarm information processing model, that is, the information knowledge base is externally attached to the alarm information processing model. The way of placing the information knowledge base outside the alarm information processing model can be applied through the retrieval enhancement generation technology (RAG).

[0043] Specifically, Figure 2 The operation and maintenance knowledge base shown may be the information knowledge base of the present application, and the information knowledge base may include, but is not limited to, equipment operation rules, equipment operation manuals, safety measures and regulations, expert experience, inspection and maintenance manuals, production management processes, and other information. The alarm code is stored in the information knowledge base in order to better match the processing operation information corresponding to the alarm information from the information knowledge base. For example, each piece of information in the inspection and maintenance manual may correspond to different or the same alarm code.

[0044] The construction of the information knowledge base of this embodiment can make it possible to quickly and accurately match appropriate processing operation information for the alarm information from the information knowledge base based on the information classification result after obtaining the information classification result corresponding to the alarm information. In addition, the information knowledge base can also be used as prior knowledge.

[0045] S130. Determine processing operation information corresponding to the alarm information based on the information classification result.

[0046] The processing operation information may be understood as information available for performing operations on the device.

[0047] Specifically, if the information classification result is associated with the processing operation information, the information classification result is obtained, and the processing operation information corresponding to the alarm information is obtained based on the information classification result and the associated relationship.

[0048] As an optional but non-limiting method, the alarm information includes an alarm code, and the processing operation information corresponding to the alarm information is determined based on the information classification result, including: matching the processing operation information corresponding to the alarm information from the information knowledge base according to the information classification result and the alarm code, and the information classification result includes pushing defects, attention, confirmation, false alarm and blocking.

[0049] Specifically, the processing operation information corresponding to the alarm information is matched from the information knowledge base according to the information classification result and the alarm code, including the following methods:

[0050] A. If the information classification result is a push defect, the first processing operation information is matched from the information knowledge base according to the alarm code and the push defect, and sent to the operation and maintenance personnel. The first processing operation information at least includes the equipment area information, equipment information, equipment defect information and equipment defect processing method. The equipment information includes the equipment type and equipment name. The equipment defect information includes the equipment defect type, equipment defect level, equipment defect parts and equipment defect details.

[0051] Specifically, when the information classification result is a push defect, the alarm code and the information corresponding to the push defect are searched from the information knowledge base, and the information is used as the first processing operation information. After the operation and maintenance personnel receive the first processing operation information and confirm that the information is correct, the corresponding equipment work order is automatically generated, so as to process the equipment defect according to the equipment work order. The equipment work order includes preparation work, safety inspection, required tools, processing steps and other contents.

[0052] B. If the information classification result is concern, intervention of operation and maintenance personnel is taken as the second processing operation information and sent to the operation and maintenance personnel.

[0053] Specifically, if the information classification result is a concern, indicating that operation and maintenance personnel need to intervene, the second processing operation information will be sent to the operation and maintenance personnel to remind them. The reminder can be in the form of an audible and visual alarm signal in the power monitoring system, and the operation and maintenance personnel will take over the subsequent handling process.

[0054] C. If the information classification result is confirmed, the third processing operation information is matched from the information knowledge base according to the alarm code and the pushed defect, and the equipment is operated and maintained based on the third processing operation information. The third processing operation information includes the equipment defect processing method, and the operation and maintenance operation includes defect detection and maintenance of the equipment.

[0055] Specifically, after the third processing operation information is generated, the power monitoring system may generate corresponding control instructions according to the third processing operation information, the device obtains the control instructions in the power monitoring system, and performs corresponding operation processing according to the control instructions.

[0056] D. If the information classification result is a false alarm, determine the target number of false alarms for the information classification result; if the target number is less than the preset number, the device operates normally; if the target number reaches the preset number, the information classification result is shielded, and the alarm information is shielded according to the preset shielding time.

[0057] The embodiment of the present invention matches the processing operation information corresponding to the alarm information from the information knowledge base according to the information classification result and the alarm code, thereby realizing accurate and rapid processing of the alarm information, improving the intelligent level of monitoring, greatly reducing the workload and work intensity of monitoring personnel, and improving the efficiency of handling abnormal events.

[0058] The technical solution of the embodiment of the present invention, in response to the device alarm instruction, obtains the alarm information corresponding to the device alarm instruction, the alarm information is used to describe the alarm type and alarm level of different types of equipment alarms, the alarm information at least includes the equipment operation data of the preset time period before the reference time, that is, the information contained in the alarm information of the present invention is richer and more detailed, thereby ensuring the richness of the alarm information, further determining the alarm information processing model, and obtaining the information classification result corresponding to the alarm information based on the alarm information and the alarm information processing model, because the alarm information processing model is used to describe the correspondence between different alarm information and different information classification results, the information classification result describes the classification result of the alarm information, and the richness of the alarm information is sufficient, thereby ensuring that the information classification result can be quickly and accurately obtained based on the alarm information processing model and the alarm information, avoiding misjudgment or missed judgment of the event, and improving the handling efficiency of abnormal events and the accuracy of abnormal event judgment. In addition, different information classification results correspond to different processing operation information. Therefore, the processing operation information corresponding to the alarm information is determined based on the information classification result, which solves the problems of heavy workload of monitoring personnel, low intelligent degree of monitoring, and low intelligent degree of decision-making, and greatly reduces the workload and work intensity of operation and maintenance personnel.

[0059] Embodiment 2

[0060] Figure 3 A flowchart of another alarm information processing method provided for an embodiment of the present invention. The technical solution of this embodiment further optimizes the process of determining the alarm information processing model in S120 in the aforementioned embodiment on the basis of the above embodiment. This embodiment can be combined with various optional solutions in one or more of the above embodiments.

[0061] like Figure 3 As shown, the alarm information processing method of the present invention includes:

[0062] S210, obtaining historical alarm data.

[0063] Among them, the historical alarm data at least includes historical alarm information and historical information classification results. The historical alarm information at least includes the alarm type, alarm level and equipment operation data including timestamp of different types of equipment. The timestamp is a time window with a preset time interval before and after the alarm moment. There is a corresponding relationship between the historical alarm information and the historical information classification results.

[0064] Specifically, the historical alarm data is preprocessed data. Preprocessing includes data cleaning; data cleaning may include removing duplicate and invalid data and processing missing data. Processing missing data may be done by interpolation, filling or discarding missing values.

[0065] Preprocessing may also include labeling the data, including indicating the final processing result and validity of each historical alarm information, and labeling the important parameters and operation steps in each historical alarm information.

[0066] S220: Integrate the historical alarm information into historical alarm information containing time series features.

[0067] The time series feature is determined according to the timestamp, and one time series feature corresponds to one historical alarm information.

[0068] Specifically, the process of determining the timing characteristics is as follows:

[0069] Timestamp alignment: Ensure that the timestamps of the equipment operating parameters before and after the alarm are aligned with the alarm time point. Select the time window from the preset time interval before the alarm to the preset time interval after the alarm, for example, the time window from 30 minutes before the alarm to 30 minutes after the alarm.

[0070] Time series data feature extraction: Extract statistical features within the time window, such as mean, standard deviation, maximum value, minimum value, rate of change, etc.; extract time series features, such as autoregressive features, moving average features, time series decomposition features, etc.

[0071] Numerical normalization: Normalize numerical data to the same scale (such as between 0 and 1). Common methods include minimum-maximum normalization and Z-score normalization.

[0072] Specifically, after the time series feature is obtained, the time series feature is integrated with the historical alarm information to obtain the historical alarm information containing the time series feature.

[0073] S230: Based on the historical alarm information containing time series features and the historical information classification results, the initial alarm information processing model is trained to obtain an alarm information processing model.

[0074] Among them, the initial alarm information processing model can be set according to its own needs, such as performance requirements and resource consumption levels to select models of different types and parameter sizes. The initial alarm information processing model can be understood as a pre-trained AI large model. The initial alarm information processing model can select one of the models such as BERT, LLaMA, Qwen or ChatGLM.

[0075] As an optional but non-limiting manner, based on the historical alarm information containing time series features and the historical information classification results, the initial alarm information processing model is trained to obtain the alarm information processing model, including steps A1-A3:

[0076] Step A1: Use the last layer of the initial alarm information processing model as the fully connected layer for outputting information classification results, and select the preset layers of the initial alarm information processing model as training layers, wherein the preset layers include the last layer of the initial alarm information processing model, and the preset layers of the initial alarm information processing model are continuously connected.

[0077] For example, some training layers in the initial alarm information processing model can be selectively frozen, and the last few layers can be selected for training to avoid overfitting and ensure the accuracy of the final model.

[0078] Step A2: Based on the historical alarm information containing time series features and the historical information classification results, the initial alarm information processing model is trained to obtain a loss function corresponding to the training.

[0079] Among them, the loss function can choose cross entropy loss.

[0080] Step A3: adjusting the parameters of the initial alarm information processing model based on the loss function to obtain the alarm information processing model.

[0081] Specifically, an optimizer (Adam may be selected) may be selected to adjust the parameters in the initial alarm information processing model to obtain the alarm information processing model.

[0082] The technical solution of this embodiment avoids overfitting in training by using the last layer of the initial alarm information processing model as the fully connected layer that outputs the information classification result, and selecting the preset layer of the initial alarm information processing model as the training layer. The initial alarm information processing model is further trained based on the historical alarm information and historical information classification results containing time series features to obtain the loss function corresponding to the training. Then, the parameters of the initial alarm information processing model are adjusted based on the loss function to obtain the alarm information processing model, thereby ensuring the accuracy of the alarm information processing model.

[0083] S240. In response to the device alarm instruction, obtain alarm information corresponding to the device alarm instruction, obtain an information classification result corresponding to the alarm information based on the alarm information and an alarm information processing model, and determine processing operation information corresponding to the alarm information based on the information classification result.

[0084] Optionally, the alarm information of the equipment and the corresponding information classification results, as well as the manual intervention data, can be collected, and the alarm information processing model can be regularly optimized, fine-tuned and iterated based on the above data to continuously improve the analysis accuracy and disposal effect of this method.

[0085] The technical solution of the embodiment of the present invention obtains historical alarm data. Since the historical alarm data at least includes historical alarm information and historical information classification results, the historical alarm information at least includes the alarm type, alarm level and equipment operation data of different types of equipment including timestamps, thereby ensuring the richness of the historical alarm information. The timestamp is a time window with a preset time interval before and after the alarm moment. The setting of the timestamp ensures that the information corresponding to the alarm time can be accurately included in the historical alarm data, thereby further enriching the historical alarm data. The historical alarm information is then integrated into historical alarm information including time series features. Since there is a corresponding relationship between the historical alarm information and the historical information classification results, the initial alarm information processing model is trained based on the historical alarm information including time series features and the historical information classification results to obtain the alarm information processing model, thereby ensuring the accuracy of the alarm information processing model. Then, in response to the device Alarm instruction, obtain the alarm information corresponding to the equipment alarm instruction, and further obtain the information classification result corresponding to the alarm information based on the alarm information and the alarm information processing model, because the alarm information processing model is used to describe the correspondence between different alarm information and different information classification results, the information classification result describes the classification result of the alarm information, and the alarm information is rich enough, thereby ensuring that the information classification result based on the alarm information processing model and the alarm information can be obtained quickly and accurately, avoiding misjudgment or omission of events, and improving the handling efficiency of abnormal events and the accuracy of abnormal event judgment. In addition, different information classification results correspond to different processing operation information. Therefore, the processing operation information corresponding to the alarm information is determined based on the information classification result, which solves the problems of heavy workload of monitoring personnel, low degree of monitoring intelligence, and low degree of decision-making intelligence, and greatly reduces the workload and work intensity of operation and maintenance personnel.

[0086] Embodiment 3

[0087] Figure 4 This is a schematic diagram of the structure of an alarm information processing device provided by an embodiment of the present invention. This embodiment can be applied to the case of processing alarm information issued by a power monitoring system. The alarm information processing device can be implemented in the form of hardware and / or software. The alarm information processing device can be configured in any electronic device with network communication function. Figure 4 As shown, the device comprises:

[0088] An information acquisition module 310 is used to obtain alarm information corresponding to the device alarm instruction in response to the device alarm instruction, wherein the alarm information is used to describe the alarm type and alarm level of different types of device alarms, and the alarm information at least includes device operation data for a preset time period before a reference time, wherein the reference time is the time when the device alarm instruction is triggered;

[0089] A classification result determination module 320 is used to determine an alarm information processing model, and obtain an information classification result corresponding to the alarm information based on the alarm information and the alarm information processing model, wherein the alarm information processing model is used to describe the corresponding relationship between different alarm information and different information classification results, and the information classification result describes the classification result of the alarm information, and different information classification results correspond to different processing operation information;

[0090] The information determination module 330 is used to determine the processing operation information corresponding to the alarm information based on the information classification result.

[0091] Optionally, the classification result determination module includes a model determination unit, including:

[0092] An information acquisition unit, used to acquire historical alarm data, wherein the historical alarm data at least includes historical alarm information and historical information classification results, wherein the historical alarm information at least includes alarm types, alarm levels and equipment operation data including timestamps for different types of equipment, wherein the timestamps are time windows with a preset time interval before and after the alarm moment; and there is a corresponding relationship between the historical alarm information and the historical information classification results;

[0093] An information processing unit, used for integrating the historical alarm information into historical alarm information containing time series features, wherein the time series features are determined according to a timestamp, and one time series feature corresponds to one historical alarm information;

[0094] The training unit is used to train the initial alarm information processing model based on the historical alarm information containing time series features and the historical information classification results to obtain the alarm information processing model.

[0095] Optionally, a training unit is used to: use the last layer of the initial alarm information processing model as a fully connected layer that outputs information classification results, and select preset layers of the initial alarm information processing model as training layers, the preset layers include the last layer of the initial alarm information processing model, and the preset layers of the initial alarm information processing model are continuously connected; based on the historical alarm information containing time series features and the historical information classification results, train the initial alarm information processing model to obtain a loss function corresponding to the training; adjust the parameters of the initial alarm information processing model based on the loss function to obtain an alarm information processing model.

[0096] Optionally, the alarm information processing model includes an information knowledge base, which is placed outside the alarm information processing model. The information knowledge base includes different processing operation information corresponding to different information classification results. The different information classification results correspond to different alarm information. Different alarm information is stored in the information knowledge base in the form of alarm codes.

[0097] Optionally, the alarm information includes an alarm code, and the information determination module is used to match the processing operation information corresponding to the alarm information from the information knowledge base according to the information classification result and the alarm code, and the information classification result includes pushing defects, attention, confirmation, false alarm and blocking.

[0098] Optionally, the information determination module includes a first information determination unit, which is used to: if the information classification result is a push defect, match the first processing operation information from the information knowledge base according to the alarm code and the push defect, and send it to the operation and maintenance personnel, the first processing operation information at least includes the equipment area information, equipment information, equipment defect information and equipment defect processing method, the equipment information includes the equipment type and equipment name, the equipment defect information includes the equipment defect type, equipment defect level, equipment defect components and equipment defect details; if the information classification result is concern, the operation and maintenance personnel intervention is taken as the second processing operation information, and sent to the operation and maintenance personnel; if the information classification result is confirmation, match the third processing operation information from the information knowledge base according to the alarm code and the push defect, and perform operation and maintenance operations on the equipment based on the third processing operation information, the third processing operation information includes the equipment defect processing method, and the operation and maintenance operation includes defect detection and maintenance of the equipment.

[0099] Optionally, the information determination module includes a second information determination unit, which is used to: if the information classification result is a false alarm, determine the target number of times the information classification result is a false alarm; if the target number is less than a preset number of times, the device operates normally; if the target number of times reaches a preset number of times, the information classification result is shielded, and the alarm information is shielded according to the preset shielding time.

[0100] The alarm information processing device provided in the embodiment of the present invention can execute the alarm information processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0101] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations and do not violate public order and good morals.

[0102] Embodiment 4

[0103] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0104] Figure 5 The structural schematic diagram of an electronic device that can be used to implement the alarm information processing method of 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, workbenches, 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.

[0105] like Figure 5 As 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. The input / output (I / O) interface 15 is also connected to the bus 14.

[0106] 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.

[0107] 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 special 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 the alarm information processing method.

[0108] In some embodiments, the alarm information processing 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 alarm information processing method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the alarm information processing method in any other appropriate manner (e.g., by means of firmware).

[0109] 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), systems 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.

[0110] 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.

[0111] 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, or 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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 processing alarm information, characterized in that: The method comprises: In response to an equipment alarm instruction, alarm information corresponding to the equipment alarm instruction is obtained, the alarm information is used to describe the alarm type and alarm level of different types of equipment alarms, the alarm information at least includes equipment operation data for a preset time period before a reference time, the reference time is the moment when the equipment alarm instruction is triggered; the alarm information is information sent by the power monitoring system, the alarm information includes the equipment type, brand model, equipment ID, alarm occurrence time, alarm level, alarm category, alarm information description and alarm code corresponding to the equipment alarm instruction, the alarm code is the code description information corresponding to different alarm information; Determine an alarm information processing model, and obtain an information classification result corresponding to the alarm information based on the alarm information and the alarm information processing model, wherein the alarm information processing model is used to describe the corresponding relationship between different alarm information and different information classification results, and the information classification result describes the classification result of the alarm information, and different information classification results correspond to different processing operation information; Determine the processing operation information corresponding to the alarm information based on the information classification result; Wherein, the alarm information processing model includes an information knowledge base, the information knowledge base is placed inside or outside the alarm information processing model, the information knowledge base includes different processing operation information corresponding to different information classification results, the different information classification results correspond to different alarm information, and different alarm information is stored in the information knowledge base in the form of alarm codes. The information knowledge base is placed outside the alarm information processing model and is applied by means of retrieval enhancement generation technology (RAG); Wherein, determining the processing operation information corresponding to the alarm information based on the information classification result includes: matching the processing operation information corresponding to the alarm information from the information knowledge base according to the information classification result and the alarm code, the information classification result including push defect, attention, confirmation, false alarm and shielding; Among them, determining the alarm information processing model includes: Acquire historical alarm data, the historical alarm data at least including historical alarm information and historical information classification results, the historical alarm information at least including alarm types, alarm levels and equipment operation data including timestamps for different types of equipment, the timestamp being a time window with a preset time interval before and after the alarm moment; there is a corresponding relationship between the historical alarm information and the historical information classification results; Integrate the historical alarm information into historical alarm information containing time series features, wherein the time series features are determined according to the timestamp, and one time series feature corresponds to one historical alarm information; Based on the historical alarm information containing time series features and the historical information classification results, an initial alarm information processing model is trained to obtain an alarm information processing model; Wherein, matching the processing operation information corresponding to the alarm information from the information knowledge base according to the information classification result and the alarm code includes: If the information classification result is a push defect, first processing operation information is matched from the information knowledge base according to the alarm code and the push defect, and sent to the operation and maintenance personnel, wherein the first processing operation information at least includes equipment area information, equipment information, equipment defect information and equipment defect processing method, the equipment information includes equipment type and equipment name, and the equipment defect information includes equipment defect type, equipment defect level, equipment defect component and equipment defect details; If the information classification result is concern, intervention of operation and maintenance personnel is taken as the second processing operation information and sent to the operation and maintenance personnel; If the information classification result is confirmed, third processing operation information is matched from the information knowledge base according to the alarm code and the pushed defect, and an operation and maintenance operation is performed on the equipment based on the third processing operation information, wherein the third processing operation information includes an equipment defect processing method, and the operation and maintenance operation includes defect detection and maintenance of the equipment; Wherein, based on the historical alarm information containing time series features and the historical information classification result, the initial alarm information processing model is trained to obtain the alarm information processing model, including: The last layer of the initial alarm information processing model is used as a fully connected layer for outputting information classification results, and preset layers of the initial alarm information processing model are selected as training layers, wherein the preset layers include the last layer of the initial alarm information processing model, and the preset layers of the initial alarm information processing model are continuously connected; Based on the historical alarm information containing time series features and the historical information classification results, the initial alarm information processing model is trained to obtain a loss function corresponding to the training; The parameters of the initial alarm information processing model are adjusted based on the loss function to obtain an alarm information processing model.

2. The method according to claim 1, characterized in that: Matching the processing operation information corresponding to the alarm information from the information knowledge base according to the information classification result and the alarm code includes: If the information classification result is a false alarm, determining a target number of false alarms for the information classification result; If the target number of times is less than the preset number of times, the device operates normally; If the target number of times reaches a preset number of times, the information classification result is shielding, and the alarm information is shielded according to a preset shielding time.

3. An alarm information processing device, characterized in that: The device comprises: An information acquisition module, for responding to an equipment alarm instruction, acquiring alarm information corresponding to the equipment alarm instruction, the alarm information being used to describe the alarm type and alarm level of different types of equipment alarms, the alarm information at least including equipment operation data for a preset time period before a reference time, the reference time being the moment when the equipment alarm instruction is triggered; the alarm information is information sent by a power monitoring system, the alarm information including the equipment type, brand model, equipment ID, alarm occurrence time, alarm level, alarm category, alarm information description and alarm code corresponding to the equipment alarm instruction, the alarm code being code description information corresponding to different alarm information; a classification result determination module, used to determine an alarm information processing model, and obtain an information classification result corresponding to the alarm information based on the alarm information and the alarm information processing model, wherein the alarm information processing model is used to describe the corresponding relationship between different alarm information and different information classification results, and the information classification result describes the classification result of the alarm information, and different information classification results correspond to different processing operation information; An information determination module, used to determine processing operation information corresponding to the alarm information based on the information classification result; Wherein, the alarm information processing model includes an information knowledge base, the information knowledge base is placed outside the alarm information processing model, the information knowledge base includes different processing operation information corresponding to different information classification results, the different information classification results correspond to different alarm information, and different alarm information is stored in the information knowledge base in the form of alarm codes. The information knowledge base is placed outside the alarm information processing model and is applied by means of retrieval enhancement generation technology (RAG); The information determination module is used to match the processing operation information corresponding to the alarm information from the information knowledge base according to the information classification result and the alarm code, and the information classification result includes push defect, attention, confirmation, false alarm and shielding; The classification result determination module includes a model determination unit, including: An information acquisition unit, used to acquire historical alarm data, wherein the historical alarm data at least includes historical alarm information and historical information classification results, wherein the historical alarm information at least includes alarm types, alarm levels and equipment operation data including timestamps for different types of equipment, wherein the timestamps are time windows with a preset time interval before and after the alarm moment; and there is a corresponding relationship between the historical alarm information and the historical information classification results; An information processing unit, used for integrating the historical alarm information into historical alarm information containing time series features, wherein the time series features are determined according to a timestamp, and one time series feature corresponds to one historical alarm information; A training unit, configured to train an initial alarm information processing model based on the historical alarm information containing time series features and the historical information classification result to obtain an alarm information processing model; The information determination module includes a first information determination unit, which is used to: if the information classification result is a push defect, match the first processing operation information from the information knowledge base according to the alarm code and the push defect, and send it to the operation and maintenance personnel, the first processing operation information at least includes the area information of the equipment, the equipment information, the equipment defect information and the equipment defect processing method, the equipment information includes the equipment type and the equipment name, and the equipment defect information includes the equipment defect type, the equipment defect level, the equipment defect component and the equipment defect details; if the information classification result is a concern, the operation and maintenance personnel intervention is used as the second processing operation information, and sent to the operation and maintenance personnel; if the information classification result is a confirmation, match the third processing operation information from the information knowledge base according to the alarm code and the push defect, and perform operation and maintenance operations on the equipment based on the third processing operation information, the third processing operation information includes the equipment defect processing method, and the operation and maintenance operation includes defect detection and maintenance of the equipment; Among them, the training unit is also used to: use the last layer of the initial alarm information processing model as the fully connected layer of the output information classification result, and select the preset layer of the initial alarm information processing model as the training layer, the preset layer includes the last layer of the initial alarm information processing model, and the preset layers of the initial alarm information processing model are continuously connected; based on the historical alarm information containing time series features and the historical information classification results, the initial alarm information processing model is trained to obtain the loss function corresponding to the training; based on the loss function, the parameters of the initial alarm information processing model are adjusted to obtain the alarm information processing model.

4. 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 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 alarm information processing method according to any one of claims 1 to 2.

5. 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 alarm information processing method according to any one of claims 1 to 2 when executed.

Images