Method and device for determining fault processing flow and electronic equipment

Abstract

The invention discloses a fault processing flow determination method and device and electronic equipment. Relates to automation field. The method comprises the steps that a target work order sent by a user side is received, M pieces of alarm information carried in the target work order are acquired, the target work order carries alarm information sent by target equipment, and M is a positive integer; identifying the keyword of each piece of alarm information to obtain M groups of keywords; respectively inputting each group of keywords into a target classification model to obtain a fault reason of each piece of alarm information; and determining a target fault reason of the target equipment according to the M fault reasons, and sending a processing flow corresponding to the target fault reason to the user side. According to the method and the device, the problem of low efficiency and accuracy of manually analyzing the fault processing flow of the fault power supply equipment in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of automation, and in particular to a method, device and electronic device for determining a fault handling process. Background Art

[0002] The stability of power supply in the computer room has always been an important guarantee for business security. In the event of a failure in the power supply equipment, the normal power supply to the computer room may be affected. Therefore, in the event of a failure in the equipment in the computer room, it is necessary to determine the fault handling process as soon as possible to ensure normal power supply to the computer room and normal operation of the business.

[0003] Currently, when determining the fault handling process, the main method used is a manual post-analysis process, that is, the possible causes are screened out manually based on the known fault site and manual experience, and they are checked and eliminated one by one. Finally, the root cause of the fault is obtained, and the fault handling process is obtained based on historical experience based on the cause of the fault. However, the above method of determining the fault handling process relies heavily on experience, resulting in low efficiency and accuracy in determining the fault handling process, and lack of timeliness in some scenarios.

[0004] With regard to the problem of low efficiency and accuracy of the fault handling process of the faulty power supply equipment through manual analysis in the related art, no effective solution has been proposed yet. Summary of the invention

[0005] The present application provides a method, device and electronic device for determining a fault handling process to solve the problem of low efficiency and accuracy of the fault handling process of a faulty power supply device through manual analysis in the related art.

[0006] According to one aspect of the present application, a method for determining a fault processing flow is provided. The method includes: receiving a target work order sent by a user terminal, and obtaining M alarm information carried in the target work order, wherein the target work order carries the alarm information sent by the target device, and M is a positive integer; identifying the keywords of each alarm information respectively, and obtaining M groups of keywords; inputting each group of keywords into a target classification model respectively, and obtaining the fault cause of each alarm information; determining the target fault cause of the target device according to the M fault causes, and sending the processing flow corresponding to the target fault cause to the user terminal.

[0007] Optionally, the target classification model is obtained in the following manner: obtaining the fault causes of historical faults that occurred in the target device at multiple historical moments to obtain multiple historical fault causes; obtaining historical fault information of each historical fault, and determining keywords of each historical fault based on the historical fault information; combining the keywords and historical fault causes of the same historical fault into a set of sample data to obtain multiple sets of sample data; using multiple sets of sample data to train the initial classification model to obtain the target classification model.

[0008] Optionally, determining keywords for each historical fault based on historical fault information includes: segmenting the historical fault information to obtain multiple sample words; determining the correlation between each sample word and the target device to obtain multiple correlations; determining sample words having a correlation greater than a target correlation as target words to obtain multiple target words; determining the occurrence frequency of each target word, and determining the target words having an occurrence frequency greater than a preset frequency as keywords for the historical fault.

[0009] Optionally, determining the target fault cause of the target device based on M fault causes includes: grouping the M fault causes to obtain multiple groups of fault causes, wherein at least one fault cause in each group of fault causes is the same; determining the number of fault causes in each group of fault causes, and obtaining a group of fault causes with the largest number of fault causes; and determining the fault cause contained in the group of fault causes with the largest number of fault causes as the target fault cause.

[0010] Optionally, after sending the processing flow corresponding to the target fault cause to the user end, the method also includes: obtaining device information of the target device, and determining a device associated with the target device based on the device information, to obtain H associated devices, where H is a positive integer; obtaining second operating information of each associated device, and determining an operating risk of abnormal operation of each associated device based on the second operating information, to obtain H operating risks; obtaining device information of associated devices whose operating risk is greater than a preset risk value, to obtain at least one group of device information, and generating prompt information based on at least one group of device information, and sending the prompt information to the user end.

[0011] Optionally, keywords of each alarm message are identified separately to obtain M groups of keywords, including: for any alarm message, text data in the alarm message is identified, and the text data is segmented to obtain N initial words, where N is a positive integer; the N initial words are input into a target recognition model to obtain N recognition results, where the target recognition model is used to identify the word type to which each initial word belongs; the initial words whose word type is the target type are determined as candidate words to obtain P candidate words, where P is a positive integer; and keywords of the alarm message are determined based on the P candidate words.

[0012] Optionally, determining the keywords of the alarm information based on P candidate words includes: performing an expansion operation on each candidate word to obtain P groups of candidate words, wherein the expansion operation includes: generating synonyms of the candidate words; using a preset dictionary to filter each group of candidate words in turn to obtain P groups of filtered candidate words, and determining the P groups of filtered candidate words as keywords of the alarm information, wherein the preset dictionary includes multiple preset keywords.

[0013] According to another aspect of the present application, a device for determining a fault processing flow is provided. The device includes: a receiving unit, which is used to receive a target work order sent by a user terminal, and obtain M alarm information carried in the target work order, wherein the target work order carries the alarm information sent by the target device, and M is a positive integer; an identification unit, which is used to identify the keywords of each alarm information respectively, and obtain M groups of keywords; an input unit, which is used to input each group of keywords into a target classification model respectively, and obtain the fault cause of each alarm information; a first determination unit, which is used to determine the target fault cause of the target device according to the M fault causes, and send the processing flow corresponding to the target fault cause to the user terminal.

[0014] According to another aspect of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the method for determining a fault handling process provided in the aforementioned embodiment of the present application is implemented.

[0015] According to another aspect of the present invention, an electronic device is also provided, comprising one or more processors and a memory; the memory stores computer-readable instructions, and the processor is used to execute the computer-readable instructions, wherein when the computer-readable instructions are executed, a method for determining a fault handling process provided in the aforementioned embodiment is executed.

[0016] Through this application, the following steps are adopted: receiving a target work order sent by the user end, and obtaining M alarm information carried in the target work order, wherein the target work order carries the alarm information sent by the target device, and M is a positive integer; identifying the keywords of each alarm information respectively, and obtaining M groups of keywords; inputting each group of keywords into the target classification model respectively, and obtaining the fault cause of each alarm information; determining the target fault cause of the target device according to the M fault causes, and sending the processing flow corresponding to the target fault cause to the user end. The problem of low efficiency and accuracy of the fault processing flow of the faulty power supply equipment through manual analysis in the related technology is solved. The alarm information carried in the target work order is analyzed through the target classification model to obtain the fault cause of each alarm information, and the target fault cause of the target device is comprehensively determined based on multiple fault causes, and then the processing flow is determined according to the target fault cause, thereby achieving the technical effect of improving the accuracy and efficiency of determining the fault processing flow. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 is a flowchart of a method for determining a fault handling process provided in an embodiment of the present application;

[0019] Figure 2 is a flowchart of an optional model training process provided according to an embodiment of the present application;

[0020] Figure 3 is a schematic diagram of a device for determining a fault handling process according to an embodiment of the present application;

[0021] Figure 4 It is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] It should be noted that the method, device and electronic device for determining the fault handling process determined in the present disclosure can be used in the field of automation, and can also be used in any field other than the field of automation. The application field of the method, device and electronic device for determining the fault handling process determined in the present disclosure is not limited.

[0026] It should be noted that the collected information, user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) used in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with the relevant laws, regulations and standards of the relevant regions, necessary confidentiality measures are taken, and public order and good customs are not violated. Corresponding operation portals are provided for users to choose to authorize or refuse to use. For example, an interface is set up between this system and relevant users or organizations. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0027] The embodiments or examples of the present disclosure are not exhaustive, but are only illustrative of some embodiments or examples, and are not intended to be specific limitations on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment or example can be implemented as an independent example, and the steps can be combined arbitrarily. For example, the scheme after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be combined arbitrarily; in addition, the various embodiments or examples can be combined arbitrarily, for example, some or all steps of different embodiments or examples can be combined arbitrarily, and a certain embodiment or example can be combined arbitrarily with the optional methods or optional examples of other embodiments or examples.

[0028] According to an embodiment of the present application, a method for determining a fault handling process is provided.

[0029] Figure 1 1 is a flowchart of a method for determining a fault handling process according to an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0030] Step S101, receiving a target work order sent by a user terminal, and obtaining M alarm information carried in the target work order, wherein the target work order carries the alarm information sent by the target device, and M is a positive integer.

[0031] Specifically, the user end can send a target work order for a certain computer room to the fault handling system. The target work order can include the alarm information of the computer room where the abnormality occurs. The abnormal phenomenon occurring in the computer room at the current moment can be determined through the alarm information. When a fault occurs in the computer room, the fault may cause multiple abnormal phenomena to occur in the computer room at the same time. For example, some equipment in computer room A loses power, and at the same time, the air conditioner in computer room A cannot work normally. At this time, the target work order will contain two alarm messages. The first alarm message is: a device at a certain location in computer room A loses power, and the second alarm message is: the air conditioner in computer room A cannot work normally. Therefore, corresponding alarm messages are generated for all abnormal phenomena contained in the computer room, thereby ensuring the integrity of the alarm information in the target work order.

[0032] It should be noted that the target device can be a single device that has failed, or multiple devices. There is no limit on the number of devices. The target device can be a device in the computer room, or a device associated with the computer room. There is no limitation here. The power supply status of the power supply equipment to the computer room can be determined through the alarm information sent by the target device.

[0033] Step S102: Identify the keywords of each warning message respectively to obtain M groups of keywords.

[0034] Specifically, after obtaining the target work order, it is necessary to perform keyword recognition on the content of each alarm information once, so as to obtain the keywords of each alarm information, that is, M groups of keywords, wherein each group of keywords includes multiple keywords.

[0035] For example, the alarm message: "The temperature in the computer room is abnormal. The current temperature has reached 45°C, far exceeding the safety threshold of 35°C."

[0036] The corresponding keywords may be: computer room, abnormal temperature.

[0037] Alarm message: "The air conditioner in the computer room has a power outage."

[0038] The corresponding keywords may be: computer room air conditioning, power failure.

[0039] Step S103: input each group of keywords into the target classification model to obtain the fault cause of each alarm information.

[0040] Specifically, after obtaining multiple groups of keywords, the multiple groups of keywords can be input into the target classification model, and each group of keywords can be identified by the target classification model to determine the fault cause corresponding to each group of keywords, thereby improving the efficiency of determining the fault cause.

[0041] It should be noted that after the target classification model receives a group of keywords, it will compare the group of keywords with the sample keywords in the model to determine the cluster center to which the group of keywords belongs, and determine the fault cause corresponding to the cluster center as the fault cause of the alarm information to which the group of keywords belongs.

[0042] Step S104: determine the target fault cause of the target device according to the M fault causes, and send the processing flow corresponding to the target fault cause to the user end.

[0043] Specifically, after obtaining the fault causes of each alarm information, since when multiple alarms occur in the computer room at the same time, the causes of multiple alarms are likely to be caused by the same fault cause. Therefore, after obtaining M fault causes, the most frequently occurring fault cause can be selected from the M fault causes as the target fault cause, thereby avoiding the phenomenon that the fault cause determined based on a certain alarm information is incorrect.

[0044] Furthermore, after obtaining the target fault cause, since the target fault cause has a corresponding processing flow, the fault processing flow of the target fault cause can be directly determined in the database, and the fault processing flow can be sent to the user end, so that the user end can directly handle the fault occurring in the computer room according to the fault processing flow, thereby achieving the technical effect of improving the accuracy and efficiency of determining the fault processing flow.

[0045] The method for determining the fault handling process provided in the embodiment of the present application receives a target work order sent by a user end, and obtains M alarm information carried in the target work order, wherein the target work order carries the alarm information sent by the target device, and M is a positive integer; the keywords of each alarm information are identified respectively to obtain M groups of keywords; each group of keywords is input into the target classification model respectively to obtain the fault cause of each alarm information; the target fault cause of the target device is determined according to the M fault causes, and the processing flow corresponding to the target fault cause is sent to the user end. The problem of low efficiency and accuracy of the fault handling process of the faulty power supply equipment through manual analysis in the related technology is solved. The alarm information carried in the target work order is analyzed by the target classification model to obtain the fault cause of each alarm information, and the target fault cause of the target device is comprehensively determined according to multiple fault causes, and then the processing flow is determined according to the target fault cause, thereby achieving the technical effect of improving the accuracy and efficiency of determining the fault handling process.

[0046] In order to ensure the accuracy of the target classification model in identifying the cause of the fault, optionally, in the method for determining the fault handling process provided in the embodiment of the present application, Figure 2 is a flowchart of an optional model training process provided according to an embodiment of the present application, such as Figure 2As shown in Figure 2, the target classification model is obtained as follows:

[0047] Step S201, obtaining the fault causes of historical faults of the target device at multiple historical moments, and obtaining multiple historical fault causes.

[0048] Step S202: acquiring historical fault information of each historical fault, and determining a keyword of each historical fault according to the historical fault information.

[0049] Step S203: combining keywords and historical fault causes of the same historical fault into a group of sample data to obtain multiple groups of sample data.

[0050] Step S204, using multiple groups of sample data to train the initial classification model to obtain a target classification model.

[0051] Specifically, in the first step of building the target classification model, we first need to determine the historical failures that occurred on the target device at multiple historical moments in the past. We can collect detailed descriptions of each failure of the target device and its corresponding causes by consulting equipment maintenance records, fault reports, etc. The causes of the failure may involve hardware damage, software errors, improper operation or environmental factors, etc., which constitute the basic data set for subsequent analysis.

[0052] Furthermore, it is necessary to analyze each piece of historical fault information, which may include the specific time when the fault occurred, the fault phenomenon, etc. After obtaining the historical fault information, the historical fault information can be identified and simplified, and the most representative keywords can be extracted from it. These keywords can highly summarize the main characteristics of the fault, thereby simplifying the complex historical fault information into labels that are easy to understand and process.

[0053] Furthermore, after obtaining the keywords and fault causes, we can pair the keywords of the same historical fault with its fault cause to obtain a set of sample data. Then, as the sample data continues to accumulate, we eventually build a data set containing multiple sets of sample data, so that the model can be trained with the above data set, so that the model can determine the corresponding fault cause based on the keywords, and then obtain the target classification model.

[0054] For example, we can first obtain the historical fault information and fault causes of the target computer room at historical moments, and determine the type with the highest correlation with the fault cause from the preset 18 types (high-voltage power distribution, low-voltage power distribution, generator, UPS, 240V DC, 48V DC, central air conditioning, computer room air conditioning, dynamic environment monitoring, lightning protection grounding, computer room power distribution, environment, micromodule, etc.) according to the standard type of computer room power supply equipment, and obtain the "fault type" attribute. And obtain the description content related to the fault phenomenon in the historical fault information, and perform semantic word segmentation on it, take the three words with higher frequency as the "fault phenomenon" attribute, and use the "fault type" attribute and "fault phenomenon" attribute as keywords to obtain the keywords of the historical fault information.

[0055] In order to accurately determine the keywords of historical faults, optionally, in the method for determining the fault handling process provided in the embodiment of the present application, determining the keywords of each historical fault based on the historical fault information includes: segmenting the historical fault information to obtain multiple sample words; determining the correlation between each sample word and the target device to obtain multiple correlations; determining the sample words having a correlation greater than the target correlation as target words to obtain multiple target words; determining the occurrence frequency of each target word, and determining the target words having an occurrence frequency greater than a preset frequency as keywords of the historical fault.

[0056] Specifically, when determining keywords, it is necessary to first segment the historical fault information, so as to extract meaningful word units from the complex text of the historical fault information as the basis for subsequent analysis. Specifically, the historical fault description text can be segmented into several independent words or phrases through natural language processing technology, each word or phrase represents a sample word, so that keywords that can accurately summarize the fault information can be selected from multiple sample words.

[0057] Furthermore, in order to accurately identify which sample words can best represent or describe the specific fault conditions of the target device, it is necessary to evaluate the degree of association between each sample word and the target device. At this time, the correlation score between each sample word and the target device, that is, the correlation degree, can be calculated through a preset statistical method or machine learning algorithm, so as to determine the words with a greater correlation with the target device based on the correlation degree, where the degree of correlation directly reflects the importance of the word in describing a specific fault. After obtaining the correlation degree of all sample words, we need to set a target correlation threshold to filter out words that are highly related to the target device fault. Sample words with a correlation degree greater than the threshold can be regarded as target words, thereby reducing the interference of noise words and improving the accuracy of keyword recognition.

[0058] For example, after word segmentation, the sample words obtained are: "8 o'clock", "computer room air conditioning", "no wind", and "A position". Among them, the three words "computer room air conditioning", "no wind", and "A position" have a high correlation with the target device. At this time, the above three words can be determined as target words.

[0059] Furthermore, after obtaining the target words, we need to further analyze the frequency of occurrence of these target words. By counting the number of times each target word appears in the historical fault description and comparing it with the preset frequency threshold, we can determine which words are truly representative historical fault keywords. These keywords are not only highly relevant to the target equipment, but also have a high frequency of occurrence in the historical fault information. In this way, the target words with an occurrence frequency greater than the preset frequency are determined as keywords for historical faults.

[0060] Optionally, in the method for determining the fault handling process provided in the embodiment of the present application, determining the target fault cause of the target device based on M fault causes includes: grouping the M fault causes to obtain multiple groups of fault causes, wherein at least one fault cause in each group of fault causes is the same; determining the number of fault causes in each group of fault causes, and obtaining a group of fault causes with the largest number of fault causes; and determining the fault cause contained in the group of fault causes with the largest number of fault causes as the target fault cause.

[0061] Specifically, when determining the cause of the failure of the target device, since the causes of the failure obtained based on different alarm information may be different, it is necessary to obtain the causes of the failure obtained from each alarm information, and group the failure causes, group the same failure causes into one group, thereby obtaining multiple groups of failure causes, and obtaining the group of failure causes with the largest number of failure causes, thereby determining the failure cause as the target failure cause.

[0062] That is, in the present application, when determining the target fault cause, it is necessary to select the fault cause with the highest probability from the M fault causes as the target fault cause, thereby achieving the technical effect of improving the accuracy of fault cause selection.

[0063] Optionally, in the method for determining the fault handling process provided in an embodiment of the present application, after sending the processing process corresponding to the target fault cause to the user end, the method also includes: obtaining device information of the target device, and determining a device having an associated relationship with the target device based on the device information, to obtain H associated devices, where H is a positive integer; obtaining second operating information of each associated device, and determining an operating risk of abnormal operation of each associated device based on the second operating information, to obtain H operating risks; obtaining device information of associated devices whose operating risk is greater than a preset risk value, to obtain at least one group of device information, and generating prompt information based on at least one group of device information, and sending the prompt information to the user end.

[0064] Specifically, after determining the cause of the failure of the target device, the device information of the target device can also be obtained, such as the location and business scope of a certain computer room. Based on the above device information, the device information associated with the target device can be determined, such as the server and client that need to be controlled by the device in the computer room, thereby obtaining H associated devices.

[0065] Furthermore, after the associated devices are determined, it is necessary to obtain second operating information of each associated device, wherein the second operating information may include information of multiple dimensions such as the operating status, performance indicators, error logs, etc. of the device, thereby reflecting the actual operating conditions of the device, and determining the operating risk of abnormal operation of each associated device based on the second operating information, thereby determining whether each associated device will be affected when a fault occurs in the target device, and the risk of being affected.

[0066] Furthermore, after obtaining the operating risks of all associated devices, these risk values ​​can be compared with the preset risk values. The preset risk value is a threshold value set based on industry experience, equipment specifications or user requirements, and is used to judge the level of equipment operating risk. For associated devices with operating risks greater than the preset risk value, they can be regarded as high-risk devices, and their equipment information is extracted. Detailed prompt information is generated based on this equipment information. This information may include the name of the associated device, risk level, specific risk points and recommended measures, etc., and then these prompt information will be sent to the user end in a timely manner so that the user can quickly understand and take corresponding measures to reduce the potential losses caused by abnormal equipment operation.

[0067] This embodiment determines the risks of the associated devices of the target device, thereby ensuring timely discovery of risky associated devices, and sending prompt information in time to maintain the devices, thereby ensuring the normal operation of the associated devices.

[0068] Optionally, in the method for determining the fault handling process provided in the embodiment of the present application, the keywords of each alarm information are identified respectively to obtain M groups of keywords, including: for any alarm information, the text data in the alarm information is identified, and the text data is segmented to obtain N initial words, where N is a positive integer; the N initial words are input into a target recognition model to obtain N recognition results, where the target recognition model is used to identify the word type to which each initial word belongs; the initial words whose word type is the target type are determined as candidate words to obtain P candidate words, where P is a positive integer; and the keywords of the alarm information are determined based on the P candidate words.

[0069] Specifically, when processing any alarm information, it is necessary to first identify and extract the text data therein, which usually contains key information such as the specific content, time, and location of the triggering alarm. Subsequently, in order to analyze this information more carefully, the text data is processed using word segmentation technology. Word segmentation is the process of dividing continuous text into independent words or phrases. Through word segmentation, N initial words can be obtained, and keywords can be determined from the N initial words.

[0070] Furthermore, after obtaining N initial words, the N initial words can be input into the target recognition model, so that the target recognition model can identify the word type to which each initial word belongs, wherein the word type may include various classifications such as names of people, places, time, events, etc. Through the processing of the target recognition model, N recognition results can be obtained, each result corresponding to the word type of an initial word. Afterwards, according to the word type of the initial word, the words of the target type can be screened, thereby eliminating words with low importance and words that will affect the model's determination of the cause of the fault, thereby obtaining candidate words, and then further screening the candidate words to obtain keywords.

[0071] In order to improve the accuracy of keywords, optionally, in the method for determining the fault handling process provided in the embodiment of the present application, determining the keywords of the alarm information based on P candidate words includes: performing an expansion operation on each candidate word to obtain P groups of candidate words, wherein the expansion operation includes: generating synonyms of the candidate words; using a preset dictionary to filter each group of candidate words in turn to obtain P groups of filtered candidate words, and determining the P groups of filtered candidate words as keywords of the alarm information, wherein the preset dictionary includes multiple preset keywords.

[0072] Specifically, since the candidate words obtained may be different from the keywords used when training the model, after obtaining the candidate words, the candidate words can be expanded to obtain synonyms of the candidate words, and the synonyms and candidate words are collectively determined as a group of candidate words, and each candidate word group is screened using a preset dictionary to select keywords in each candidate word group that are in the preset dictionary, so that the filtered keywords are both associated with the alarm information and ensure that the model can determine the cause of the failure of the target device based on the keyword, thereby ensuring the accuracy of determining the cause of the failure through keywords.

[0073] The following describes an embodiment of a method for determining an optional fault handling process implemented based on the present technical solution:

[0074] When implementing this solution, it is necessary to establish a fault case library analysis association model, use the self-configured atomic capabilities for data processing and calling, and finally realize real-time root cause analysis of work orders and intelligent workbench warning presentation. The specific process is as follows:

[0075] First, you need to establish a fault case library analysis association model. When establishing a fault case library analysis association model, you can use the following steps to establish it:

[0076] 1. According to the standard types of power supply equipment in the computer room, 18 types (high-voltage power transformation and distribution, low-voltage power distribution, generator, UPS, 240V DC, 48V DC, central air conditioning, computer room air conditioning, dynamic environment monitoring, lightning protection and grounding, computer room power distribution, environment, micromodule, etc.) are sorted out as keywords to traverse the "summary part" of the case, and obtain their occurrence probability. If there is only one, take it directly. If there are multiple types, take the type with the highest probability as an alternative. After comparing it with the "keyword" attribute, verify its accuracy and mark it as the "fault type" field.

[0077] For example: judging from the content of one of the historical fault cases that the fault type is a generator fault.

[0078] 2. Perform semantic word segmentation on the fault information in historical fault cases and take the three words with higher frequency as keywords. The main function is to further refine the subsequent same fault type.

[0079] For example: Two mains power outages. During the emergency repair process, at 12:49, some racks in rows 1 to 4 of the A3 building's 4th floor computer room lost power. Afterwards, the power-off equipment gradually returned to normal. By 13:04, all equipment was restored. The services of other computer rooms on this floor were not affected. Extracted keywords: power outage, mains power outage, rack power outage.

[0080] 3. Obtain the cause analysis attributes in historical fault cases, sort out the steps of each sequence of segmented troubleshooting, and form the "troubleshooting steps" attribute. Its main function is to automatically guide on-site or automated means to obtain key equipment performance and alarm conditions for future faults of the same type to determine the cause of the fault with the highest probability.

[0081] For example: The original case obtained is 1. The reason for the interruption of dual-line city power. The tripping of transformer No. 1 is the direct cause of the interruption of dual-line city power in the park. After investigation, it was found that the problem of the temperature sensor caused the non-electrical protection of the transformer to operate and trip. At 12:09, when the dual-line city power was cut off, the 380V transformer on the A line side of the 4th floor was in maintenance (the main circuit breaker was in the disconnected state), causing the backup power output by the oil engine to fail to be delivered to the important machine room. In this fault, after the gas turbine was started, the unit fan did not receive the spontaneous power supply normally, the fan could not start, and could not cool down in time. After the unit ran for a period of time, it reported a "high oil temperature alarm" and caused it to shut down.

[0082] The process for determining the cause of a fault is:

[0083] 1) Real-time query of the operating status of key equipment: query the operating status of the transformer connected to the AC input, query the operating status of the high-voltage distribution cabinet, query the operating status of the power supply equipment, query the operating status of the oil engine, query the operating status of the battery, etc.

[0084] 2) Delimit the fault according to the operating status. In this example, the trip alarm occurs due to the abnormal operating status of the upstream transformer, and the oil engine status is not started. It can be preliminarily determined that the fault point is in the oil engine part, and then the "high oil temperature alarm" of the oil engine is obtained.

[0085] 3) Remind the site to immediately check if the oil engine fails to start.

[0086] 4. After obtaining the cause of the fault, a processing flow can be generated based on the cause of the fault.

[0087] For example: At 12:09, the maintenance personnel of the 110KV substation found that the No. 3 transformer tripped abnormally. At this time, the dual-line power supply of the park was interrupted and the oil generator was started. The on-site maintenance personnel immediately notified the maintenance supervisor. After the maintenance supervisor rushed to the 110kv substation, he determined that the No. 3 transformer tripped due to a high temperature alarm. After analysis and judgment, he decided to switch to the No. 4 transformer for power supply.

[0088] At the same time, the on-site maintenance personnel separately confirmed the operating status and power supply of the oil engines at various locations. During this period, the maintenance personnel found that the three gas turbines stopped after running for a period of time (afterwards, it was found that the three oil engines stopped after running for 17, 18, and 22 minutes respectively). The on-site personnel manually restarted the oil engine, and the oil engine stopped again after working for a period of time. Since the city power had not been restored at this time, the on-site personnel restarted it to ensure the power supply of the oil engine (in fact, it was not normally powered on).

[0089] The solution obtained at this time is: if there is an oil engine failure, please ask the on-site personnel to rush to the site to manually restart the oil engine and restore the fault as soon as possible.

[0090] Furthermore, after analyzing historical faults, keywords and fault causes can be associated to obtain sample data, and the fault case library analysis association model can be trained using the sample data, so that the cause of the equipment failure can be determined based on the keywords later.

[0091] Furthermore, after obtaining the fault case library analysis association model, after receiving the newly added alarm work order, the fault cause of the target equipment (such as the equipment in the computer room) can be analyzed according to the alarm information in the alarm work order, and the processing flow corresponding to the fault cause can be sent to the user end.

[0092] The process of handling alarm work orders is as follows:

[0093] 1. Receive alarm work orders.

[0094] 2. Analyze the alarm information in the alarm work order to obtain keywords, and input the keywords into the fault case library analysis association model to obtain the cause of the fault.

[0095] 3. Select the fault cause with the highest probability from multiple fault causes, obtain the target fault cause, and generate a processing flow for the target fault cause.

[0096] 4. Further, additional alarm operations are performed according to the target fault cause, that is, the devices that may be affected when the target device has a target fault are determined.

[0097] For example, in this example, the first alarms added are transformer alarm, oil engine high temperature alarm, power supply equipment no input alarm, etc. After that, the real-time parameters of the relevant alarm equipment are automatically collected, and the fact that the oil engine did not start normally after the power outage is found. The guidance statement is automatically printed: an oil engine failure has occurred. Please ask on-site personnel to rush to the site to manually restart the oil engine and restore the fault as soon as possible.

[0098] 5. On-site operation guidance: After obtaining the processing flow of the target fault cause, print the processing flow in the work order to guide the on-site maintenance personnel to check step by step, and further print the processing plan with the highest probability, so that the on-site maintenance personnel can shorten the fault handling time and find the problem and deal with it as soon as possible.

[0099] 6. Establish a user work order analysis interface, and use the intelligent operation workbench to configure the presentation page. The initial options on the page include the following attributes: the fault work order number to be analyzed, the alarm type, the station name, the equipment name, the scope of impact, the maintenance personnel email address to be reminded, and the reminder cycle. Customize the analysis reminder content in the user interface, and send the content that needs to be reminded to the designated maintenance personnel email address on a regular basis to reduce the maintenance personnel's manual statistical workload.

[0100] 7. Use the smart workbench's mid-screen presentation function to automatically configure the above reminders to be presented on the large screen, so that maintenance personnel can view and understand the current fault status at any time with one click after logging in, so as to achieve one-point control of faults, one-point knowledge of the impact scope, and special attention to hidden dangers that are likely to cause faults.

[0101] Through the above process, the cause of the failure of the target device can be accurately determined, and the processing flow of the failure cause can be accurately determined, and the processing flow and related alarms can be sent to the maintenance personnel in a timely manner, thereby ensuring accurate and timely processing of the failure and reducing the business impact scope and degree of the failure.

[0102] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0103] The embodiment of the present application also provides a device for determining a fault handling process. It should be noted that the device for determining a fault handling process in the embodiment of the present application can be used to execute the method for determining a fault handling process provided in the embodiment of the present application. The device for determining a fault handling process provided in the embodiment of the present application is introduced below.

[0104] Figure 3 Schematic diagram of a device for determining a fault handling process according to an embodiment of the present application. Figure 3 As shown, the device includes: a receiving unit 31, a recognition unit 32, an input unit 33, and a first determination unit 34.

[0105] The receiving unit 31 is used to receive a target work order sent by a user terminal, and obtain M alarm information carried in the target work order, wherein the target work order carries the alarm information sent by the target device, and M is a positive integer.

[0106] The identification unit 32 is used to identify the keywords of each warning information respectively to obtain M groups of keywords.

[0107] The input unit 33 is used to input each group of keywords into the target classification model to obtain the fault cause of each alarm information.

[0108] The first determining unit 34 is configured to determine a target fault cause of the target device according to the M fault causes, and send a processing flow corresponding to the target fault cause to the user end.

[0109] The device for determining the fault handling process provided in the embodiment of the present application receives the target work order sent by the user end through the receiving unit 31, and obtains M alarm information carried in the target work order, wherein the target work order carries the alarm information sent by the target device, and M is a positive integer; the identification unit 32 identifies the keywords of each alarm information respectively to obtain M groups of keywords; the input unit 33 inputs each group of keywords into the target classification model respectively to obtain the fault cause of each alarm information; the first determination unit 34 determines the target fault cause of the target device according to the M fault causes, and sends the processing flow corresponding to the target fault cause to the user end. The problem of low efficiency and accuracy of the fault handling process of the faulty power supply equipment through manual analysis in the related technology is solved, the alarm information carried in the target work order is analyzed through the target classification model, the fault cause of each alarm information is obtained, and the target fault cause of the target device is comprehensively determined according to multiple fault causes, and then the processing flow is determined according to the target fault cause, thereby achieving the technical effect of improving the accuracy and efficiency of determining the fault handling process.

[0110] Optionally, in the fault handling process determination device provided in the embodiment of the present application, the target classification model is obtained in the following manner: a first acquisition unit is used to obtain the fault causes of historical faults that occurred in the target device at multiple historical moments, and obtain multiple historical fault causes; a second acquisition unit is used to obtain historical fault information of each historical fault, and determine the keywords of each historical fault based on the historical fault information; a combination unit is used to combine the keywords and historical fault causes of the same historical fault into a group of sample data, and obtain multiple groups of sample data; a training unit is used to train the initial classification model using multiple groups of sample data to obtain a target classification model.

[0111] Optionally, in the fault handling process determination device provided in the embodiment of the present application, the second acquisition unit includes: a first word segmentation module, used to segment historical fault information to obtain multiple sample words; a first determination module, used to determine the correlation between each sample word and the target device, and obtain multiple correlations; a second determination module, used to determine the sample words with a correlation greater than the target correlation as target words, and obtain multiple target words; a third determination module, used to determine the occurrence frequency of each target word, and determine the target words with an occurrence frequency greater than a preset frequency as keywords of historical faults.

[0112] Optionally, in the determination device of the fault handling process provided in the embodiment of the present application, the first determination unit 34 includes: a grouping module, used to group M fault causes to obtain multiple groups of fault causes, wherein at least one fault cause in each group of fault causes is the same; a fourth determination module, used to determine the number of fault causes in each group of fault causes, and obtain a group of fault causes with the largest number of fault causes; a fifth determination module, used to determine the fault cause contained in the group of fault causes with the largest number of fault causes as the target fault cause.

[0113] Optionally, in the fault handling process determination device provided in the embodiment of the present application, after the processing process corresponding to the target fault cause is sent to the user end, the device also includes: a third acquisition unit, used to acquire device information of the target device, and determine the device having an associated relationship with the target device based on the device information, to obtain H associated devices, where H is a positive integer; a second determination unit, used to acquire second operating information of each associated device, and determine the operating risk of abnormal operation of each associated device based on the second operating information, to obtain H operating risks; a fourth acquisition unit, used to acquire device information of associated devices whose operating risk is greater than a preset risk value, to obtain at least one group of device information, and generate prompt information based on at least one group of device information, and send the prompt information to the user end.

[0114] Optionally, in the fault handling process determination device provided in the embodiment of the present application, the identification unit 32 includes: a second word segmentation module, which is used to identify the text data in the alarm information for any alarm information, and to segment the text data to obtain N initial words, where N is a positive integer; an input module, which is used to input the N initial words into a target recognition model to obtain N recognition results, where the target recognition model is used to identify the word type to which each initial word belongs; a sixth determination module, which is used to determine the initial words whose word type is the target type as candidate words, and to obtain P candidate words, where P is a positive integer; a seventh determination module, which is used to determine the keywords of the alarm information based on the P candidate words.

[0115] Optionally, in the fault handling process determination device provided in the embodiment of the present application, the seventh determination module includes: an expansion submodule, which is used to perform expansion operations on each candidate word to obtain P groups of candidate words, wherein the expansion operation includes: generating synonyms for the candidate words; a screening submodule, which is used to use a preset dictionary to screen each group of candidate words in turn to obtain P groups of screened candidate words, and determine the P groups of screened candidate words as keywords for the alarm information, wherein the preset dictionary includes multiple preset keywords.

[0116] The above-mentioned fault handling process determination device includes a processor and a memory. The above-mentioned receiving unit 31, identification unit 32, input unit 33, first determination unit 34, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0117] The processor includes a kernel, and the kernel retrieves the corresponding program unit from the memory. One or more kernels can be set, and the problem of low efficiency and accuracy of the fault handling process of the faulty power supply equipment through manual analysis in the related art is solved by adjusting the kernel parameters.

[0118] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0119] An embodiment of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, the method for determining the fault handling process is implemented.

[0120] An embodiment of the present invention provides a processor, which is used to run a program, wherein the method for determining the fault handling process is executed when the program is running.

[0121] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application, such as Figure 4 As shown, an embodiment of the present invention provides an electronic device, the electronic device 40 includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the steps of the method for determining the above fault handling process when executing the program. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0122] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the steps of the determination method of the above-mentioned fault handling process.

[0123] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0124] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0125] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0126] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0127] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0128] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0129] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0130] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0131] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for determining a fault handling process, characterized in that: include: Receive a target work order sent by a user terminal, and obtain M alarm information carried in the target work order, wherein the target work order carries the alarm information sent by the target device, and M is a positive integer; Recognize the keywords of each alarm information respectively to obtain M groups of keywords; Input each group of keywords into the target classification model to obtain the fault cause of each alarm information; A target fault cause of the target device is determined according to the M fault causes, and a processing flow corresponding to the target fault cause is sent to the user end.

2. The method according to claim 1, characterized in that The target classification model is obtained in the following way: Obtaining the fault causes of historical faults of the target device at multiple historical moments to obtain multiple historical fault causes; Acquire historical fault information of each historical fault, and determine a keyword of each historical fault according to the historical fault information; Combining keywords and historical fault causes of the same historical fault into a set of sample data to obtain multiple sets of sample data; The initial classification model is trained using the multiple groups of sample data to obtain the target classification model.

3. The method according to claim 2, characterized in that The keywords for determining each historical fault according to the historical fault information include: Segmenting the historical fault information to obtain a plurality of sample words; Determining the relevance between each sample word and the target device to obtain a plurality of relevances; Determine the sample words whose relevance is greater than the target relevance as target words, and obtain a plurality of target words; The occurrence frequency of each target word is determined, and the target word whose occurrence frequency is greater than a preset frequency is determined as a keyword of the historical fault.

4. The method according to claim 1, characterized in that: Determining the target fault cause of the target device according to the M fault causes includes: Grouping the M fault causes to obtain multiple groups of fault causes, wherein at least one fault cause in each group of fault causes is the same; Determine the number of fault causes in each group of fault causes, and obtain a group of fault causes with the largest number of fault causes; A fault cause included in a group of fault causes with the largest number of the fault causes is determined as the target fault cause.

5. The method according to claim 1, characterized in that After sending the processing flow corresponding to the target fault cause to the user terminal, the method further includes: Acquire device information of the target device, and determine devices associated with the target device according to the device information to obtain H associated devices, where H is a positive integer; Acquire second operation information of each associated device, and determine the operation risk of abnormal operation of each associated device according to the second operation information to obtain H operation risks; The device information of the associated device whose operation risk is greater than a preset risk value is obtained to obtain at least one set of device information, and prompt information is generated according to the at least one set of device information, and the prompt information is sent to the user end.

6. The method according to claim 1, characterized in that The keywords of each alarm information are identified respectively, and M groups of keywords are obtained, including: For any warning information, identify text data in the warning information, and segment the text data to obtain N initial words, where N is a positive integer; Inputting the N initial words into a target recognition model to obtain N recognition results, wherein the target recognition model is used to identify the word type to which each initial word belongs; Determine the initial words whose word type is the target type as candidate words, and obtain P candidate words, where P is a positive integer; Determine keywords for the warning information based on the P candidate words.

7. The method according to claim 6, characterized in that Determining the keywords of the warning information according to the P candidate words includes: Performing an expansion operation on each candidate word to obtain P groups of candidate words, wherein the expansion operation includes: generating synonyms of the candidate words; Each group of candidate words is screened in turn using a preset dictionary to obtain P groups of screened candidate words, and the P groups of screened candidate words are determined as keywords of the alarm information, wherein the preset dictionary includes multiple preset keywords.

8. A device for determining a fault handling process, characterized in that: include: A receiving unit, configured to receive a target work order sent by a user terminal, and obtain M alarm information carried in the target work order, wherein the target work order carries the alarm information sent by the target device, and M is a positive integer; An identification unit, used to identify keywords of each alarm information respectively, to obtain M groups of keywords; An input unit, used to input each group of keywords into the target classification model to obtain the fault cause of each alarm information; The first determining unit is used to determine a target fault cause of the target device according to the M fault causes, and send a processing flow corresponding to the target fault cause to the user terminal.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for determining the fault handling process described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the fault handling process described in any one of claims 1 to 7.

Images