Intelligent feedback method and device of alarm information, server and storage medium

Abstract

The invention relates to the technical field of IT operation and maintenance, in particular to an intelligent feedback method and device of alarm information, a server and a storage medium, which are used for solving the problem that the operation and maintenance efficiency and effect are seriously reduced in the related art. Whether an abnormal event corresponding to the alarm information is fed back or not is recognized, each piece of fed-back alarm information comprises corresponding alarm information and push feedback information, and the push feedback information comprises a processing instruction for subsequent alarm information of the abnormal event corresponding to the corresponding alarm information; if yes, processing the alarm information based on a processing instruction in push feedback information included in fed-back alarm information matched with the alarm information; if not, pushing the alarm information to a chat window of an associated user; therefore, by introducing a feedback mechanism of the alarm information, the operation and maintenance efficiency and accuracy of the alarm information are effectively improved.

Description

Technical Field

[0001] This application relates to the field of IT operation and maintenance technology, and particularly to an intelligent feedback method, device, server and storage medium for alarm information. Background Art

[0002] In order to timely know the running state of a software system, a monitoring platform is usually deployed for the software system. According to various set alarm rules, the monitoring platform monitors the running state of the software system in real time. Once a software system failure or abnormality is found, alarm information can be output in time to notify operation and maintenance users. After receiving the alarm information, the operation and maintenance users can make system maintenance, fault troubleshooting, etc. in time.

[0003] In today's era of information explosion, there is a vast amount of data and information in software systems, and the alarm information generated by the monitoring platform also emerges like a flood. However, many alarm information is invalid or repeated, resulting in the operation and maintenance team having to spend a lot of time and energy dealing with these meaningless alarm information, seriously reducing the processing efficiency and effect of alarm information operation and maintenance. Even when the true problem begins to show signs, it is ignored, ultimately leading to serious system failures and affecting normal business operations. Summary of the Invention

[0004] Embodiments of this application provide an intelligent feedback method, device, server and storage medium for alarm information, so as to improve the processing efficiency and intelligence level of alarm information, effectively improve operation and maintenance efficiency and alarm processing accuracy, realize efficient management and response to alarms, and at the same time reduce operation and maintenance costs.

[0005] The specific technical solutions provided by the embodiments of this application are as follows:

[0006] In a first aspect, an embodiment of this application provides an intelligent feedback method for alarm information, which is applied to an operation and maintenance server with an instant messaging function. The method includes:

[0007] Every time alarm information sent by the monitoring platform is received, it is determined whether the abnormal event corresponding to the alarm information has been fed back based on each already fed-back alarm information. Each already fed-back alarm information includes the corresponding alarm information and a push feedback message, and the push feedback message includes a processing instruction for subsequent alarm information corresponding to the abnormal event corresponding to the corresponding alarm information;

[0008] If it is determined that the abnormal event corresponding to the alarm information has been fed back, the alarm information is processed based on the processing instruction in the push feedback message included in the already fed-back alarm information that matches the alarm information;

[0009] If it is determined that the abnormal event corresponding to the alarm information has not been fed back, the alarm information is pushed to the chat window of the associated user.

[0010] In the above method of the present application, by introducing a feedback mechanism for alarm information, it is realized to identify whether the received alarm information has been feedback through each feedback alarm information, and based on the identification result, the alarm information is intelligently processed. At the same time, the alarm information is pushed through the chat window, which improves the real-time, mobility and intelligence of the alarm information push, achieves the purpose of an intelligent mechanism for automatically adjusting the push frequency and type of alarm information according to user feedback, improves the operation and maintenance efficiency and accuracy of alarm information, and enables the operation and maintenance personnel to manage and respond to alarms more efficiently.

[0011] In a possible implementation manner, pushing the alarm information to the chat window of the associated user includes:

[0012] Identifying the fault level information in the alarm information to obtain the fault level of the abnormal event;

[0013] Based on the corresponding relationship between the fault level and the associated user, determining the associated user corresponding to the fault level, wherein if the fault level is lower than or equal to the fault level threshold, there is one associated user, and if the fault level is higher than the fault level threshold, there are multiple associated users;

[0014] If there is one associated user, pushing the alarm information to the chat window of the associated user;

[0015] If there are multiple associated users, based on the user identifiers of the multiple associated users, a collaborative processing group is established, and the alarm information is pushed to the chat window of the collaborative processing group.

[0016] In the above method, one or more associated users are set according to the fault level of the alarm information. When it is determined that there are multiple associated users, a group is automatically created, and multiple associated users are automatically invited to the group, and the alarm information is pushed to the chat window of the group, so as to facilitate the operation and maintenance personnel to assist each other, thereby quickly resolving the abnormal event and achieving efficient operation and maintenance.

[0017] In a possible implementation manner, after pushing the alarm information to the chat window of the associated user or the collaborative processing group, it further includes:

[0018] If a claim information for the alarm information input by the associated user through the chat window is received, extracting a processing instruction for the abnormal event from the claim information;

[0019] Using the reception time of the claim information, the user identifier of the associated user and the processing instruction to generate a push feedback information for the alarm information;

[0020] If the alarm information is feedback for the first time, record the alarm information and the push feedback information of the alarm information as new feedback alarm information.

[0021] If the alarm information is not feedback for the first time, add the push feedback information of the alarm information to the feedback alarm information corresponding to the alarm information.

[0022] In the above method, a feedback mechanism is introduced to realize the feedback based on the alarm information received by the operation and maintenance personnel, and record the corresponding push feedback information, so as to filter out invalid or repeated alarm information subsequently, reduce unnecessary alarm notifications, and thus improve the operation and maintenance efficiency.

[0023] In a possible implementation manner, the processing instruction includes any one of the following instructions:

[0024] A confirmation instruction, which is used to indicate that after the receiving moment, delete the alarm information of the abnormal event until the completion instruction of the alarm information is received;

[0025] A rejection instruction, which is used to indicate that within the first duration after the receiving moment, delete the alarm information of the abnormal event;

[0026] An ignore instruction, which is used to indicate that within the second duration after the receiving moment, delete the alarm information of the abnormal event;

[0027] A completion instruction, which is used to indicate that after the receiving moment, re-push the alarm information of the abnormal event.

[0028] In the above method, by setting specific processing instructions, the operation and maintenance personnel can give feedback on the received alarm information to adjust the push frequency and type of the alarm information.

[0029] In a possible implementation manner, after pushing the alarm information to the chat window of the associated user or the collaborative processing group, it further includes:

[0030] The first duration is the first default duration or the duration carried in the claim information;

[0031] The second duration is the second default duration or the duration carried in the claim information.

[0032] In the above method, the first duration and the second duration can be set by the operation and maintenance personnel who claim the alarm information themselves, which improves the personalization and flexibility of the solution.

[0033] If the Q&A information for the abnormal event input by the associated user through the chat window is received, then based on the Q&A information, use a large language model to reply to the operation and maintenance suggestions for the abnormal event to obtain a reply message;

[0034] Push the reply message to the chat window.

[0035] In the above method, a large language model is introduced, and with the help of the Q&A ability of the large language model, intelligent operation and maintenance suggestions are provided, realizing a quick response to high-fault-level alarms, effectively improving the operation and maintenance efficiency of alarm information and the accuracy of alarm handling.

[0036] In a possible implementation manner, the method further includes:

[0037] If the feedback query information input by the associated user through the chat window is received, then extract the processing instruction to be queried from the feedback query information;

[0038] Based on the user identifier of the associated user and the processing instruction to be queried, filter out the target alarm information feedback by the associated user from the recorded feedback alarm information;

[0039] Push the target alarm information to the chat window of the associated user.

[0040] In the above method, by setting up a feedback query mechanism, the associated user can query the alarm information they have feedback at any time, so as to execute reference or management for the feedback alarm information.

[0041] In a possible implementation manner, the identifying whether the abnormal event corresponding to the alarm information has been feedback based on each feedback alarm information includes:

[0042] Compare the alarm information included in each feedback alarm information with the alarm information respectively;

[0043] If it is determined that the alarm information matches the alarm information included in any feedback alarm information, it is determined that the abnormal event corresponding to the alarm information has been feedback;

[0044] If it is determined that the alarm information does not match the alarm information included in each feedback alarm information, it is determined that the abnormal event corresponding to the alarm information has not been feedback.

[0045] In the above method, by comparing and identifying whether two alarm information are the same alarm information, so that subsequently after determining that the newly received alarm information has been feedback, the processing instruction in the push feedback information included in the feedback alarm information that matches the alarm information is used to process the alarm information, so as to effectively filter out invalid or duplicate alarm information, and then improve the operation and maintenance efficiency.

[0046] In a second aspect, an intelligent feedback device for alarm information provided by an embodiment of the present application is applied to an operation and maintenance server with an instant messaging function. The device includes:

[0047] An identification module, configured to, every time an alarm information sent by a monitoring platform is received, based on each already-fed-back alarm information, identify whether the abnormal event corresponding to the alarm information has been fed back. Each already-fed-back alarm information includes the corresponding alarm information and a push feedback message, and the push feedback message includes a processing instruction for subsequent alarm information of the abnormal event corresponding to the corresponding alarm information;

[0048] A processing module, configured to, if it is determined that the abnormal event corresponding to the alarm information has been fed back, process the alarm information based on the processing instruction in the push feedback message included in the already-fed-back alarm information that matches the alarm information;

[0049] A push module, configured to, if it is determined that the abnormal event corresponding to the alarm information has not been fed back, push the alarm information to the chat window of the associated user.

[0050] In a possible implementation manner, the push module is specifically configured to:

[0051] Identify the fault level information in the alarm information to obtain the fault level of the abnormal event;

[0052] Based on the correspondence between the fault level and the associated user, determine the associated user corresponding to the fault level. If the fault level is lower than or equal to the fault level threshold, there is one corresponding associated user. If the fault level is higher than the fault level threshold, there are multiple corresponding associated users;

[0053] If there is one associated user, push the alarm information to the chat window of the associated user;

[0054] If there are multiple associated users, establish a collaborative processing group based on the user identifiers of the multiple associated users, and push the alarm information to the chat window of the collaborative processing group.

[0055] In a possible implementation manner, after pushing the alarm information to the chat window of the associated user or the collaborative processing group, the push module is further configured to:

[0056] If a claim information for the alarm information input by the associated user through the chat window is received, extract a processing instruction for the abnormal event from the claim information;

[0057] Generate push feedback information for the alarm information using the reception time of the claimed information, the user identifier of the associated user, and the processing instruction;

[0058] If the alarm information is fed back for the first time, record the alarm information and the push feedback information of the alarm information as new feedback alarm information;

[0059] If the alarm information is not fed back for the first time, add the push feedback information of the alarm information to the feedback alarm information corresponding to the alarm information.

[0060] In a possible implementation manner, the processing instruction includes any one of the following instructions:

[0061] A confirmation instruction, which is used to indicate that after the reception time, delete the alarm information of the abnormal event until the completion instruction of the alarm information is received;

[0062] A rejection instruction, which is used to indicate that within a first duration after the reception time, delete the alarm information of the abnormal event;

[0063] An ignore instruction, which is used to indicate that within a second duration after the reception time, delete the alarm information of the abnormal event;

[0064] A completion instruction, which is used to indicate that after the reception time, re-push the alarm information of the abnormal event.

[0065] In a possible implementation manner, the first duration is the first default duration or the duration carried in the claimed information;

[0066] The second duration is the second default duration or the duration carried in the claimed information.

[0067] In a possible implementation manner, after pushing the alarm information to the chat window of the associated user or the collaborative processing group, the push module is further used for:

[0068] If the Q&A information for the abnormal event input by the associated user through the chat window is received, based on the Q&A information, use a large language model to reply to the operation and maintenance suggestions of the abnormal event to obtain a reply message;

[0069] Push the reply message to the chat window.

[0070] In a possible implementation manner, the push module is further used for:

[0071] If the feedback query information input by the associated user through the chat window is received, the processing instruction to be queried is extracted from the feedback query information;

[0072] Based on the user identifier of the associated user and the processing instruction to be queried, the target alarm information fed back by the associated user is filtered out from the recorded fed-back alarm information;

[0073] The target alarm information is pushed to the chat window of the associated user.

[0074] In a possible implementation manner, the recognition module is specifically configured to:

[0075] Compare the alarm information included in each fed-back alarm information with the alarm information respectively;

[0076] If it is determined that the alarm information matches the alarm information included in any fed-back alarm information, it is determined that the abnormal event corresponding to the alarm information has been fed back;

[0077] If it is determined that the alarm information does not match the alarm information included in each fed-back alarm information, it is determined that the abnormal event corresponding to the alarm information has not been fed back.

[0078] In a third aspect, an embodiment of the present application provides a server, including:

[0079] A memory for storing computer programs or instructions;

[0080] A processor for executing the computer programs or instructions in the memory, so that the method as described in any one of the first aspects above is executed.

[0081] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, when the instructions in the storage medium are executed by a processor, enabling the processor to execute the method as described in any one of the first aspects above.

[0082] In a fifth aspect, an embodiment of the present application provides a computer program product, the computer program product includes: computer program code, when the computer program code runs on a computer, enabling the computer to execute the method as described in any one of the first aspects above. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 It is a schematic diagram of an application scenario in some embodiments of the present application;

[0084] Figure 2 It is a schematic flowchart of an intelligent feedback method for alarm information in some embodiments of the present application;

[0085] Figure 3Schematic diagram of a process for identifying whether an alarm message has been fed back in some embodiments of the present application;

[0086] Figure 4 Schematic diagram of a process for pushing alarm messages in some embodiments of the present application;

[0087] Figure 5 Schematic diagram of a display effect of a chat window in some embodiments of the present application;

[0088] Figure 6 Schematic diagram of another display effect of a chat window in some embodiments of the present application;

[0089] Figure 7 Schematic diagram of a process for generating and recording push feedback information in some embodiments of the present application;

[0090] Figure 8 Schematic diagram of yet another display effect of a chat window in some embodiments of the present application;

[0091] Figure 9 Schematic diagram of the fourth display effect of a chat window in some embodiments of the present application;

[0092] Figure 10 Schematic diagram of the fifth display effect of a chat window in some embodiments of the present application;

[0093] Figure 11 Schematic diagram of a process for implementing operation and maintenance recommendation using a large language model in some embodiments of the present application;

[0094] Figure 12 Schematic diagram of a process for implementing a feedback query mechanism in some embodiments of the present application;

[0095] Figure 13 Schematic diagram of a closed-loop control of a two-way information interaction feedback mechanism in some embodiments of the present application;

[0096] Figure 14 Schematic diagram of a process for completing an operation using a feedback mechanism in some embodiments of the present application;

[0097] Figure 15 Schematic diagram of the logical architecture of an intelligent feedback device for alarm messages in some embodiments of the present application;

[0098] Figure 16 Schematic diagram of the entity architecture of a server in some embodiments of the present application. Detailed implementation manners

[0099] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0100] It should be noted that the terms "first", "second", "third", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0101] In addition, the term "and / or" in the embodiments of the present application describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0102] In the related art, among the alarm messages pushed by the monitoring platform, many alarm messages are one-way, invalid or repeated, resulting in the operation and maintenance team having to spend a lot of time and energy dealing with these meaningless alarm messages, seriously reducing the processing efficiency and effect of the alarm messages, and even being ignored when the real problem begins to show signs, ultimately leading to serious failures of the software system and affecting the normal business operation.

[0103] In view of this, in order to solve the problem that the related art seriously reduces the operation and maintenance efficiency and effect, some embodiments of the present application provide an intelligent feedback method for alarm messages, which is applied to an operation and maintenance server with an instant messaging function; the method may include: every time an alarm message sent by the monitoring platform is received, based on each already feedback alarm message, identify whether the abnormal event corresponding to the alarm message has been feedback, where each already feedback alarm message includes the corresponding alarm message and a push feedback message, and the push feedback message includes a processing instruction for subsequent alarm messages corresponding to the abnormal event corresponding to the corresponding alarm message; if it is determined that the abnormal event corresponding to the alarm message has been feedback, then based on the processing instruction in the push feedback message included in the already feedback alarm message that matches the alarm message, process the alarm message; if it is determined that the abnormal event corresponding to the alarm message has not been feedback, then push the alarm message to the chat window of the associated user.

[0104] In this application, a feedback mechanism for alarm information is introduced. By each feedback alarm information, it is identified whether the received alarm information has been feedback, so as to realize intelligent processing of the alarm information based on the identification result. At the same time, the alarm information is pushed through the chat window, which improves the real-time, mobility and intelligence of the alarm information push, and achieves an intelligent mechanism for automatically adjusting the push frequency and type of the alarm information according to the user feedback. Thus, the operation and maintenance efficiency and accuracy of the alarm information are improved, enabling the operation and maintenance personnel to manage and respond to alarms more efficiently.

[0105] With the development of technologies such as cloud computing, big data, and artificial intelligence, new concepts and practices such as DevOps (development and operations integration) and AIOps (intelligent operations) have promoted the automation and intelligent development of operations work. DevOps is a combination of Development and Operations, and is a general term for a set of processes, methods and systems, aiming to promote the communication, collaboration and integration among development, technical operations and quality assurance. Through automated processes, software construction, testing and release are made faster, more frequent and more reliable. AIOps aims to use the capabilities of artificial intelligence and machine learning to improve and automate operations. By collecting, analyzing and interpreting a large amount of operations data, it can help the operations team better understand the behavior patterns of the system, detect anomalies, predict potential problems, and provide intelligent decision-making support.

[0106] In the related technologies, during the process of processing alarm information, the operations and maintenance personnel (i.e., the associated users) usually need to view the reasons in multiple upstream and downstream systems and collaborate with multiple different roles to determine the repair plan. As the complexity of the system increases, the information required to be obtained and communicated also becomes more complex. Without an efficient information acquisition and communication mechanism, the formation of information islands will be caused. In this case, the efficiency of collaboration and communication will more affect the processing efficiency of alarm information. Therefore, adopting an efficient collaboration and communication method, integrating the information of different roles into one system, and providing real-time and accurate context information are the keys to improving the alarm processing efficiency.

[0107] ChatOps (operations through chat) is a practice method that integrates operations and development operations into the chat tools commonly used by the team. By using command lines or simple natural language instructions to execute various operations and tasks, the efficiency and transparency of the team are improved. The core idea of ChatOps is to enable team members to communicate, share information, execute tasks and operations in a shared real-time environment through the chat tool, so as to solve problems and complete tasks faster.

[0108] In some embodiments of the present application, ChatOps can be deployed in the operation and maintenance server, enabling operation and maintenance personnel to conveniently view historical records, relevant documents and resources, monitoring data, etc., and collaborate and communicate in real time, thereby solving problems more quickly.

[0109] The following further elaborates on some implementation manners of the present application in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. And without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0110] Refer to Figure 1 As shown, the application scenarios in some embodiments of the present application may include a monitoring platform (i.e., platform server) 10, an operation and maintenance server 20, and a user terminal 30. Among them, the monitoring platform 10, the operation and maintenance server 20, and the user terminal 30 can communicate wirelessly or by wire.

[0111] The monitoring platform 10 is used to monitor the running status of the software system of the system or network to be monitored in real time, and when a software system failure or abnormality (i.e., an abnormal event occurs) is detected, it outputs an alarm message to the operation and maintenance server 20 in a timely manner;

[0112] The operation and maintenance server 20 includes an operation and maintenance robot and has an instant messaging function;

[0113] The operation and maintenance server 20 is used to receive the alarm message sent by the monitoring platform, and is also used to push the alarm message to the chat window of the associated user of the user terminal 30 and the operation and maintenance robot through the operation and maintenance robot, and receive the claim information for the abnormal event corresponding to the alarm message sent by the user terminal 30. The claim information is the information input by the associated user through the chat window for this alarm message. Among them, this information includes the processing instruction for the subsequent alarm message of the abnormal event corresponding to this alarm message;

[0114] The user terminal 30 is used to display the alarm message in the chat window between the operation and maintenance robot and the associated user on the display interface, and is also used to generate a claim message in response to the input operation of the associated user for this chat window, and send the claim message to the operation and maintenance server 30.

[0115] In some embodiments of the present application, one or more user terminals 30 may be included in the above application scenario. Each user terminal 30 corresponds to at least one associated user, and each associated user is responsible for maintaining the normal operation and management of the system.

[0116] After introducing the application scenarios of some embodiments in the present application, the following further elaborates on the technical solutions in some embodiments of the present application in conjunction with the accompanying drawings.

[0117] Refer to Figure 2As shown in the figure, some embodiments of the present application provide an intelligent feedback method for alarm information. This method can be applied to an operation and maintenance server with instant messaging function. The specific process includes but is not limited to the following:

[0118] Step 200: Every time an alarm information sent by the monitoring platform is received, based on each already feedback alarm information, identify whether the abnormal event corresponding to the alarm information has been feedback. Among them, each already feedback alarm information includes the corresponding alarm information and a push feedback message, and the push feedback message includes a processing instruction for subsequent alarm information corresponding to the abnormal event corresponding to the foregoing corresponding alarm information.

[0119] In some embodiments of the present application, the monitoring platform sends the monitored alarm information to the operation and maintenance server. For the operation and maintenance server, when executing Step 200, every time the operation and maintenance server receives the alarm information sent by the monitoring platform, it can identify the abnormal event corresponding to the alarm information based on each already recorded already feedback alarm information, so as to determine whether the abnormal event is an invalid or repeated event. Among them, each already feedback alarm information includes the corresponding alarm information and the push feedback message of this alarm information, and the push feedback message includes a processing instruction for subsequent alarm information corresponding to the abnormal event corresponding to the corresponding alarm information.

[0120] In some embodiments of the present application, the above already feedback alarm information is the feedback made by the associated user for this alarm information through the chat window after pushing the alarm information included in the already feedback alarm information to the corresponding chat window. The feedback includes the foregoing processing instruction, and the processing instruction is input in the chat window; the user terminal of the associated user encapsulates the instruction as a claim information and sends it to the operation and maintenance server. After receiving the claim information, the operation and maintenance server extracts the processing instruction, generates the push feedback message of the alarm information and records it. Through the above process, the associated user can give feedback to the operation and maintenance server in time through the information input in the chat window, so that the operation and maintenance server can adjust the push frequency and type of alarm information according to the feedback of the associated user.

[0121] In some embodiments of the present application, the above processing instruction may include any one of the following instructions: confirmation instruction, completion instruction, rejection instruction, ignore instruction. Among them, the push strategy and code representation corresponding to each processing instruction can be as follows:

[0122] Confirmation instruction ( / accept): Characterize the confirmation of the abnormal event, stop pushing the same alarm information, and wait for the operation and maintenance personnel to repair and reply with the completion instruction ( / complete) before resuming the alarm;

[0123] Rejection instruction ( / refuse): Characterize the clear rejection of the abnormal event, indicating that the abnormal event does not affect the business, and can stop pushing the same alarm information within the first time period;

[0124] Ignore instruction ( / ignore): It indicates that there are certain potential hazards in the abnormal event, but it is not urgent or cannot be processed. The same alarm information can be stopped from being pushed within the second time period.

[0125] Completion instruction ( / complete): It is associated with the restoration after the user's repair, indicating the restoration of the alarm. It can also record the processing time and processing record (if any) of the abnormal event here. In this way, when similar alarm information appears next time, the relevant processing record can be pushed to the associated user as a knowledge reference.

[0126] After introducing the relevant content of the already reported alarm information, the following takes a received alarm information as an example to detail the specific processing flow of the intelligent feedback method for alarm information in some embodiments of the present application.

[0127] Involving step 200, refer to Figure 3 As shown, in some embodiments of the present application, when performing step 200, the corresponding function can be realized by executing the following process:

[0128] Step 2001: Compare the alarm information included in each already reported alarm information with this alarm information respectively.

[0129] Step 2002: If it is determined that this alarm information matches the alarm information included in any already reported alarm information, it is determined that the abnormal event corresponding to this alarm information has been reported.

[0130] Step 2003: If it is determined that this alarm information does not match the alarm information included in each already reported alarm information, it is determined that the abnormal event corresponding to this alarm information has not been reported.

[0131] In some embodiments of the present application, when performing step 2001, compare the alarm information included in each already reported alarm information with this alarm information character by character. If it is determined that the first preset number of characters in this alarm information are the same as those in the alarm information included in any already reported alarm information, it is determined that this alarm information matches the alarm information included in this already reported alarm information, and then step 2002 is executed; conversely, if it is determined that the first preset number of characters in this alarm information are all different from those in the alarm information included in all already reported alarm information, it is determined that this alarm information does not match the alarm information included in each already reported alarm information, and then step 2003 is executed.

[0132] It should be noted that the above only takes character comparison as an example to illustrate the process of determining whether two alarm information are for the same abnormal event. In actual applications, other comparison methods can also be used to determine whether two alarm information are for the same abnormal event, such as feature comparison, similarity comparison, etc. The present application does not limit the specific comparison method.

[0133] In some embodiments of the present application, after determining that the abnormal event corresponding to the alarm information has been reported, step 210 is executed to intelligently adjust the push frequency and type of the alarm information according to the user's feedback; in other embodiments of the present application, after determining that the abnormal event corresponding to the alarm information has not been reported, step 220 is executed to push the alarm information to the chat window of the associated user in a timely manner to alert the operation and maintenance personnel that an abnormal event has occurred in the monitored software system, so that the operation and maintenance personnel can perform fault inspection, location, and repair in a timely manner.

[0134] Step 210: If it is determined that the abnormal event corresponding to the alarm information has been reported, then based on the processing instruction in the push feedback information included in the reported alarm information that matches the alarm information, the alarm information is processed.

[0135] In some embodiments of the present application, if it is determined that the abnormal event corresponding to the alarm information has been reported, then step 210 is executed to intelligently process the alarm information based on the processing instruction in the push feedback information included in the reported alarm information that matches it.

[0136] Continuing from the foregoing, if the reported alarm information that matches the alarm information only includes push feedback information containing a confirmation instruction, then the alarm information is deleted; if the reported alarm information that matches the alarm information includes push feedback information containing a confirmation instruction and push feedback information containing a completion instruction, then the alarm information is re-pushed; if the reported alarm information that matches the alarm information only includes push feedback information containing a rejection instruction and within the first time period, then the alarm information is deleted; if the reported alarm information that matches the alarm information only includes push feedback information containing an ignore instruction and within the second time period, then the alarm information is deleted.

[0137] In some embodiments, if there are multiple push feedback information included in the reported alarm information that matches the alarm information, then the push feedback information with the latest reception time can be selected, and based on the processing instruction in the latest push feedback information, the alarm information is processed accordingly.

[0138] In a specific implementation manner, the operation and maintenance server can set a processing status mark, such as an identifier, for the alarm information in each reported alarm information. In this way, when it is determined that the newly received alarm information matches the alarm information included in any reported alarm information, the newly received alarm information can be processed accordingly through the processing status mark of the alarm information included in the reported alarm information that matches the alarm information.

[0139] Step 220: If it is determined that the abnormal event corresponding to the alarm information has not been reported, push the alarm information to the chat window of the associated user.

[0140] In some embodiments of the present application, if it is determined that the abnormal event corresponding to the alarm information has not been reported, it indicates that the abnormal event corresponding to the alarm information may be a new event. Then, perform Step 220 to push the alarm information to the chat window of the associated user to output the alarm to the operation and maintenance personnel in a timely manner.

[0141] In practical applications, alarm information usually carries fault level information. Some alarm information with a low fault level can usually be handled by one person, while some alarm information with a high fault level may be associated with multiple aspects. At this time, resolving the fault of the alarm information requires multiple people to cooperate to complete. Based on this, in some embodiments of the present application, when performing Step 220, refer to Figure 4 As shown, different push schemes can be adopted for different situations by specifically performing the following steps:

[0142] Step 2201: Identify the fault level information in the alarm information to obtain the fault level of the abnormal event.

[0143] Step 2202: Based on the correspondence between the fault level and the associated user, determine the associated user corresponding to the fault level. Among them, if the fault level is lower than or equal to the fault level threshold, there is one associated user; if the fault level is higher than the fault level threshold, there are multiple associated users.

[0144] Step 2203: If there is one associated user, push the alarm information to the chat window of the associated user.

[0145] Step 2204: If there are multiple associated users, establish a collaborative processing group based on the user identifiers of the multiple associated users, and push the alarm information to the chat window of the collaborative processing group.

[0146] In some embodiments of the present application, the fault level of the abnormal event can be obtained by performing Step 2201. Then, the associated users required to resolve the abnormal event can be obtained by performing Step 2202, and then the specific push scheme of the alarm information can be determined according to the number of associated users, and the alarm information can be pushed in a targeted manner based on the determined specific push scheme.

[0147] In some embodiments, when there is one associated user, the operation and maintenance server directly pushes the alarm information to the chat window between the associated user and the operation and maintenance robot through the operation and maintenance robot. The schematic diagram of the display effect in the chat window after the alarm is pushed is as Figure 5 shown.

[0148] In some other embodiments, when there are multiple associated users, the operation and maintenance server initiates an operation to create a system processing group through the operation and maintenance robot, automatically creates a collaborative processing group, automatically invites each determined associated user into the collaborative processing group, and pushes the alarm information to the chat window of the collaborative processing group through the operation and maintenance robot. The schematic diagram of the display effect of the chat window after the alarm is pushed is as shown in Figure 6 shown. The collaborative processing group shown in Figure 6 includes X users, where the operation and maintenance robot is regarded as one user, and there are X - 1 associated users in total. In this application, for the alarm information with a high fault level, a collaborative processing group is automatically created, and relevant core personnel are automatically invited into the collaborative processing group, facilitating the mutual assistance of relevant operation and maintenance personnel, so as to achieve the purpose of quickly resolving the abnormal event and further realizing efficient operation and maintenance.

[0149] In some embodiments of this application, after step 220, that is, pushing the alarm information to the chat window of the associated user or the collaborative processing group, referring to Figure 7 shown, the following steps can also be executed to obtain and record the push feedback information of the alarm information, so as to realize intelligent processing after receiving the alarm information that matches the alarm information:

[0150] Step 700: If a claim information for the alarm information input by the associated user through the chat window is received, extract the processing instruction for the abnormal event from the claim information.

[0151] In some embodiments of this application, as shown in Figure 8 if the associated user inputs feedback on the alarm information, that is, a processing instruction, through the chat window, the user terminal encapsulates the processing instruction as claim information and sends it to the operation and maintenance server. In this way, after receiving the claim information, the operation and maintenance server executes step 700 to extract the aforementioned processing instruction from the claim information.

[0152] Step 710: Generate push feedback information for the alarm information using the reception time of the claim information, the user identifier of the associated user, and the processing instruction.

[0153] In some embodiments of this application, the above processing instruction includes any one of the following instructions:

[0154] 1) Confirmation instruction, which is used to indicate that after the reception time, the alarm information of the abnormal event is deleted until a completion instruction for the alarm information is received;

[0155] 2) Rejection instruction, which is used to indicate that within a first duration after the reception time, the alarm information of the abnormal event is deleted;

[0156] 3) An ignore instruction, which is used to indicate that the alarm information of the abnormal event is to be deleted within a second time period after this reception moment;

[0157] 4) A completion instruction, which is used to indicate that after this reception moment, the alarm information of the abnormal event is to be re-pushed.

[0158] In some embodiments of the present application, a time can also be attached to the processing instruction to set the interval for stopping receiving alarm information; then, the above first time period can be a first default time period or the time period carried in the claim information; the above second time period is a second default time period or the time period carried in the claim information.

[0159] In some embodiments of the present application, the operation keyword in each processing instruction can be regarded as a feedback option. The user can input the feedback option through the chat window to obtain the instruction, such as " / feedback", to obtain each feedback option and the usage instructions for each of the above feedback options. As Figure 9 shown, when the associated user inputs " / feedback" through the chat window, after the operation and maintenance server receives this instruction, it can push the usage instructions of each feedback option to the chat window of the associated user and the operation and maintenance robot through the operation and maintenance robot, that is Figure 9 the reply of the operation and maintenance robot to " / feedback" shown in the chat window.

[0160] In the present application, by setting the above feedback options, the operation and maintenance personnel can give feedback on the received alarm information to adjust the push frequency and type of the alarm information, so that the operation and maintenance personnel can focus on processing the effective alarm information, avoid occupying a large amount of energy of the operation and maintenance personnel due to the flooding of invalid or repeated alarm information, and at the same time enable the operation and maintenance personnel to maintain a high level of vigilance, improving the operation and maintenance efficiency and accuracy.

[0161] Step 720: If the alarm information is feedback for the first time, record the alarm information and the push feedback information of the alarm information as new feedback alarm information.

[0162] Step 730: If the alarm information is not feedback for the first time, add the push feedback information of the alarm information to the feedback alarm information corresponding to the alarm information.

[0163] In some embodiments of the present application, the alarm information may be feedback for the first time or may not be feedback for the first time. Then, according to the actual situation of the alarm information, the recorded feedback alarm information is maintained in real time, that is, step 720 or step 730 is executed, to improve the intelligence level of alarm information push.

[0164] In some embodiments of the present application, a large language model can also be deployed in the operation and maintenance server to provide the ability to answer questions of the large language model (LLM), assisting operation and maintenance personnel in efficiently handling faults.

[0165] In some embodiments of the present application, after pushing the alarm information to the chat window of the associated user or the collaborative processing group, the associated user can input question-and-answer information for the alarm information through the chat window, such as Figure 10 The question-and-answer information shown can be "Is there a limit to the size of the artifact repository quota?", then, referring to Figure 11 As shown, the operation and maintenance server can also obtain operation and maintenance suggestions for the alarm information by performing the following steps with the help of the large language model question-and-answer ability:

[0166] Step 1100: If the question-and-answer information for the alarm information input by the associated user through the chat window is received, then based on the question-and-answer information, use the large language model to reply to the operation and maintenance suggestions for the alarm information to obtain a reply message;

[0167] Step 1110: Push the reply message to the above chat window.

[0168] Still as Figure 10 As shown, after receiving the question-and-answer information, perform Step 1100, call the large language model, use the question-and-answer information as the input of the large language model, and use the knowledge reserve of the large language model to obtain the reply message for the question-and-answer information. Perform Step 1110, and push the reply message to the above chat window through the operation and maintenance robot, such as Figure 10 The information given by the operation and maintenance robot shown in it, to provide operation and maintenance suggestions for the associated user, provide intelligent operation and maintenance suggestions, achieve rapid response to high-fault-level alarms, and effectively improve the operation and maintenance efficiency of alarm information and the accuracy of alarm handling.

[0169] Further, as Figure 10 As shown, after the associated user receives the reply message, if the reply message can solve the problem of the abnormal event corresponding to the alarm information and the operation and maintenance personnel have completed the repair, then the associated user can input a completion instruction by referring to the alarm information, such as Figure 10 " / complete artifact repository quota problem" in it, to resume alarm pushing. Correspondingly, the claim information corresponding to the instruction will also be fed back to the operation and maintenance server, and the operation and maintenance server will update the already feedback alarm information corresponding to the alarm information based on this. Among them, Figure 10 "Artifact repository quota problem" shown in it can be recorded as a processing record for the alarm information in the already feedback alarm information, so that when a similar alarm information appears next time, relevant processing records can be pushed to the associated user as knowledge reference.

[0170] It should be noted that Figure 10 The Q&A information shown is obtained in the form of text input. In actual applications, the above Q&A information can also be voice data. The user terminal can recognize the voice data to obtain the aforementioned Q&A information and send it to the operation and maintenance server. Of course, the user terminal can also directly send the voice data to the operation and maintenance server, and the operation and maintenance server recognizes the voice data to obtain the aforementioned Q&A information. It can be understood that the specific form of the Q&A information is not limited in this application, and all Q&A information that can be obtained through the chat window and the acquisition of automatic processing suggestions based on this Q&A information with the help of a large language model fall within the protection scope of this application.

[0171] In some other embodiments of this application, the operation and maintenance server is provided with a feedback query mechanism. By associating with the user through the feedback query mechanism, the user can query the alarm information they have feedback at any time. The applicable scenarios of the above feedback query mechanism can be any one of the following scenarios: 1. If the alarm information that has been feedback cannot be resolved in a short time, the alarm information feedback by the previous associated user in the chat window may be lost; 2. Want to manage the alarm information feedback by the associated user themselves.

[0172] In some embodiments of this application, refer to Figure 12 As shown, the above feedback query mechanism can be triggered and implemented by performing the following steps:

[0173] Step 1200: If the feedback query information input by the associated user through the chat window is received, extract the processing instruction to be queried from the feedback query information.

[0174] In some embodiments of this application, the associated user can input feedback query content through the chat window to trigger the user terminal to generate the above feedback query information and send the feedback query information to the operation and maintenance server, thereby triggering the operation and maintenance server to execute step 1200 to query the alarm information that the user has feedback.

[0175] Step 1210: Based on the user identification of the associated user and the processing instruction to be queried, screen out the target alarm information feedback by the associated user from the recorded alarm information that has been feedback.

[0176] In some embodiments of this application, after the operation and maintenance server receives the feedback query information of the user, it executes step 1200 to obtain the processing instruction to be queried, and then executes step 1210 to query the target alarm information of the processing instruction to be queried feedback by the associated user from the recorded alarm information that has been feedback.

[0177] Step 1220: Push the target alarm information to the chat window of the associated user.

[0178] In some embodiments of the present application, by executing step 1220, the associated user can see the target alarm information he / she has feedback in the chat window with the operation and maintenance robot, so as to perform reference or management on the target alarm information, etc.

[0179] Still as Figure 9 shown, if the associated user inputs " / list-accept" through the input box of the chat window, the user terminal encapsulates " / list-accept" to obtain the above-mentioned feedback query information, and sends the feedback query information to the operation and maintenance server. The operation and maintenance server extracts the processing instruction to be queried, that is, " / accept", from the feedback query information, and filters out the target alarm information fed back by the associated user with the processing instruction of " / accept" from the recorded feedback alarm information. Then, the operation and maintenance server pushes the target alarm information to the chat window of the associated user. In this way, the associated user can clearly see the target alarm information he / she has feedback and perform subsequent alarm management, analysis, etc.

[0180] Based on the above detailed description of the solution, in some embodiments of the present application, by innovatively setting up a feedback mechanism, and the feedback mechanism is a two-way information interaction feedback mechanism between the operation and maintenance server and the user terminal. As Figure 13 shown, for an alarm information, from fault discovery, to fault claim, to fault (collaborative) processing, further fault repair, fault recording, and finally fault recovery, it not only effectively filters out invalid or duplicate alarm information, improves the processing efficiency and accuracy of alarm information, but also realizes the full-process monitoring and closed-loop control of alarm processing, and reduces the operation and maintenance cost.

[0181] Next, a specific embodiment is used to illustrate the operation adjustment of the software system by using the feedback mechanism to complete the actions expected by the user.

[0182] As Figure 14 shown, in some embodiments of the present application, the operation and maintenance server can also complete the actions expected by the user based on the instructions input by the user through the chat window by performing the following steps:

[0183] Step 1401: The user terminal generates an operation event based on the instruction input by the user in the chat window.

[0184] Among them, the above instruction can be a keyword / instruction, such as "the 5 machines with the highest memory occupancy"; it can also be a certain instruction + content that references the alarm information pushed by the operation and maintenance robot and replies, such as " / complete the disk has been expanded", etc.

[0185] Step 1402: The user terminal sends the operation event to the operation and maintenance server.

[0186] Step 1403: After receiving the operation event, the operation and maintenance server makes a callback to the operation and maintenance robot service.

[0187] Step 1404: After receiving the callback, the operation and maintenance robot parses the operation event and data.

[0188] Step 1405: The operation and maintenance robot calls the data or interfaces provided by the infrastructure platform according to the parsed data to complete a certain operation.

[0189] In some embodiments of the present application, the infrastructure platform may include, but is not limited to, a log platform, a monitoring platform, a feedback platform, other platforms, etc.

[0190] Step 1406: After the operation of the infrastructure platform is completed, the result is returned to the operation and maintenance robot, or an alarm message is actively pushed.

[0191] Step 1407: The operation and maintenance robot formats the data and renders the result according to the returned result or the pushed alarm message to obtain a result message.

[0192] Step 1408: The operation and maintenance robot sends the result message to the user terminal.

[0193] In the present application, through the two-way information interaction and feedback mechanism of the chat window, the real-time response and personalized management of alarms are realized, effectively improving the IT operation and maintenance efficiency and the accuracy of alarm handling; at the same time, the operation and maintenance server in the present application can support the access of rich alarm data sources, not only limited to the WeChat subscription alarm push of the log platform and the push of all medium and high fault level alarms of the monitoring platform in the foregoing examples, etc., but also can support the access of more data sources, such as the feedback platform, etc., which will not be elaborated here.

[0194] Based on the same inventive concept, refer to Figure 15 As shown, an intelligent feedback device for alarm information is provided in an embodiment of the present application, which is applied to an operation and maintenance server with an instant messaging function. The device includes:

[0195] An identification module 1510, configured to, when receiving alarm information sent by a monitoring platform each time, identify whether the abnormal event corresponding to the alarm information has been fed back based on each already-fed-back alarm information, where each already-fed-back alarm information includes the corresponding alarm information and a push feedback message, and the push feedback message includes a processing instruction for subsequent alarm information of the abnormal event corresponding to the corresponding alarm information;

[0196] A processing module 1520, configured to, if it is determined that the abnormal event corresponding to the alarm information has been fed back, process the alarm information based on the processing instruction in the push feedback message included in the already-fed-back alarm information that matches the alarm information;

[0197] A push module 1530, configured to push the alarm information to the chat window of the associated user if it is determined that the abnormal event corresponding to the alarm information has not been reported back.

[0198] In a possible implementation, the push module 1530 is specifically configured to:

[0199] Identify the fault level information in the alarm information to obtain the fault level of the abnormal event;

[0200] Based on the correspondence between the fault level and the associated user, determine the associated user corresponding to the fault level, where if the fault level is lower than or equal to the fault level threshold, there is one associated user corresponding thereto, and if the fault level is higher than the fault level threshold, there are multiple associated users corresponding thereto;

[0201] If there is one associated user, push the alarm information to the chat window of the associated user;

[0202] If there are multiple associated users, establish a collaborative processing group based on the user identifiers of the multiple associated users, and push the alarm information to the chat window of the collaborative processing group.

[0203] In a possible implementation, after pushing the alarm information to the chat window of the associated user or the collaborative processing group, the push module 1530 is further configured to:

[0204] If receiving a claiming information input by the associated user through the chat window for the alarm information, extract a processing instruction for the abnormal event from the claiming information;

[0205] Generate a push feedback information for the alarm information using the receiving time of the claiming information, the user identifier of the associated user, and the processing instruction;

[0206] If the alarm information is reported back for the first time, record the alarm information and the push feedback information of the alarm information as new reported-back alarm information;

[0207] If the alarm information is not reported back for the first time, add the push feedback information of the alarm information to the reported-back alarm information corresponding to the alarm information.

[0208] In a possible implementation, the processing instruction includes any one of the following instructions:

[0209] A confirmation instruction, which is used to indicate that after the receiving time, perform a deletion process on the alarm information of the abnormal event until a completion instruction for the alarm information is received.

[0210] A rejection instruction for instructing to perform a deletion process on the alarm information of the abnormal event within a first duration after the receiving moment;

[0211] An ignore instruction for instructing to perform a deletion process on the alarm information of the abnormal event within a second duration after the receiving moment;

[0212] A completion instruction for instructing to perform a re - push process on the alarm information of the abnormal event after the receiving moment.

[0213] In a possible implementation manner, the first duration is a first default duration or the duration carried in the claim information;

[0214] The second duration is a second default duration or the duration carried in the claim information.

[0215] In a possible implementation manner, after pushing the alarm information to the chat window of the associated user or the collaborative processing group, the pushing module 1530 is further configured to:

[0216] If receiving the Q&A information input by the associated user through the chat window for the abnormal event, then based on the Q&A information, using a large - language model to reply to the operation and maintenance suggestions of the abnormal event to obtain a reply message;

[0217] Push the reply message to the chat window.

[0218] In a possible implementation manner, the pushing module 1530 is further configured to:

[0219] If receiving the feedback query information input by the associated user through the chat window, then extract the processing instruction to be queried from the feedback query information;

[0220] Based on the user identifier of the associated user and the processing instruction to be queried, screen out the target alarm information fed back by the associated user from the recorded fed - back alarm information;

[0221] Push the target alarm information to the chat window of the associated user.

[0222] In a possible implementation manner, the recognition module 1510 is specifically configured to:

[0223] Compare the alarm information included in each fed - back alarm information with the alarm information respectively;

[0224] If it is determined that the alarm information matches the alarm information included in any of the previously reported alarm information, it is determined that the abnormal event corresponding to the alarm information has been reported;

[0225] If it is determined that the alarm information does not match the alarm information included in each of the previously reported alarm information, it is determined that the abnormal event corresponding to the alarm information has not been reported.

[0226] Refer to Figure 16 As shown, an embodiment of the present application provides a server, which can implement the functions of the foregoing method. Refer to Figure 16 , the server includes:

[0227] At least one processor 161, and a memory 162 connected to at least one processor 161. In the embodiments of the present application, the specific connection medium between the processor 161 and the memory 162 is not limited. Figure 16 In [the figure], it is taken as an example that the processor 161 and the memory 162 are connected through a bus 160. The bus 160 is Figure 16 represented by a thick line in [the figure]. The connection manners between other components are only for illustrative purposes and are not to be taken as limitations. The bus 160 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 16 it is only represented by a thick line in [the figure], but it does not mean that there is only one bus or one type of bus. Alternatively, the processor 161 can also be referred to as a controller, and the name is not limited.

[0228] In the embodiments of the present application, the memory 162 stores instructions executable by at least one processor 161. By executing the instructions stored in the memory 162, at least one processor 161 can execute the method described above. The processor 161 can implement the functions of the foregoing device.

[0229] In a possible implementation manner, the processor 161 may include one or more processing units. The processor 161 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, the user interface, application programs, etc., and the modem processor mainly processes wireless communications. It can be understood that the above-mentioned modem processor may not be integrated into the processor 161. In some embodiments, the processor 161 and the memory 162 can be implemented on the same chip, and in some embodiments, they can also be separately implemented on independent chips.

[0230] The processor 161 may be a general-purpose processor, for example, a Central Processing Unit (CPU), a digital signal processor, an application specific integrated circuit, a field programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application may be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0231] The memory 162, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The memory 162 may include at least one type of storage medium, for example, it may include flash memory, a hard disk, a multimedia card, a card-type memory, a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Programmable Read Only Memory (PROM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 162 is any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 162 in the embodiments of the present application may also be a circuit or any other device capable of implementing a storage function, for storing program instructions and / or data.

[0232] By designing and programming the processor 161, the code corresponding to the method introduced in the foregoing embodiments can be solidified into the chip, so that the chip can execute the steps of the method in the foregoing embodiments when running. How to design and program the processor 161 is a well-known technology to those skilled in the art and will not be elaborated here.

[0233] Based on the same inventive concept, the embodiments of the present application provide a computer-readable storage medium, when the instructions in the storage medium are executed by a processor, enabling the processor to execute any one of the methods in the above various embodiments.

[0234] In some possible implementations, aspects of the methods provided in this application can also be implemented in the form of a program product, which includes program code. When the program product runs on a device, the program code is used to cause the device to execute the steps in the methods according to various exemplary implementations of this application described above in this specification.

[0235] Those skilled in the art should understand that the embodiments of this application can be provided as a method, a system, or a computer program product. Therefore, this application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0236] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to this application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in one or more flows in the flowchart and / or one or more blocks in the block diagram.

[0237] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that realizes the functions specified in one or more flows in the flowchart and / or one or more blocks in the block diagram.

[0238] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in one or more flows in the flowchart and / or one or more blocks in the block diagram.

[0239] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to include these changes and modifications.

Claims

1. An intelligent feedback method for alarm information, characterized in that: Applied to an operation and maintenance server with an instant messaging function, the method comprises: Each time an alarm message sent by the monitoring platform is received, based on each fed-back alarm message, it is identified whether the abnormal event corresponding to the alarm message has been fed-back, wherein each fed-back alarm message includes the corresponding alarm message and push feedback information, and the push feedback information includes a processing instruction for the subsequent alarm message of the abnormal event corresponding to the corresponding alarm message; If it is determined that the abnormal event corresponding to the alarm information has been fed back, the alarm information is processed based on the processing instruction in the push feedback information included in the fed back alarm information matching the alarm information; If it is determined that the abnormal event corresponding to the alarm information has not been fed back, the alarm information is pushed to the chat window of the associated user.

2. The method according to claim 1, characterized in that The step of pushing the warning information to the chat window of the associated user includes: Identify the fault level information in the alarm information to obtain the fault level of the abnormal event; Based on the correspondence between the fault level and the associated users, determining the associated users corresponding to the fault level, wherein if the fault level is lower than or equal to the fault level threshold, then one associated user corresponds to the fault level, and if the fault level is higher than the fault level threshold, then multiple associated users correspond to the fault level; If there is a related user, pushing the warning information to the chat window of the related user; If there are multiple associated users, a collaborative processing group is established based on the user identifiers of the multiple associated users, and the alarm information is pushed to the chat window of the collaborative processing group.

3. The method according to claim 2, characterized in that After pushing the alarm information to the chat window of the associated user or the collaborative processing group, the method further includes: If claim information for the alarm information input by the associated user through the chat window is received, extracting a processing instruction for the abnormal event from the claim information; Generate push feedback information for the alarm information using the time of receipt of the claim information, the user identifier of the associated user and the processing instruction; If the alarm information is fed back for the first time, the alarm information and the push feedback information of the alarm information are recorded as new fed back alarm information; If the alarm information is not fed back for the first time, the push feedback information of the alarm information is added to the fed back alarm information corresponding to the alarm information.

4. The method according to claim 3, characterized in that The processing instruction includes any one of the following instructions: A confirmation instruction, wherein the confirmation instruction is used to instruct to perform deletion processing on the alarm information of the abnormal event after the receiving time until a completion instruction of the alarm information is received; A rejection instruction, wherein the rejection instruction is used to instruct to delete the alarm information of the abnormal event within a first time period after the receiving time; an ignore instruction, the ignore instruction being used to instruct to delete the alarm information of the abnormal event within a second time period after the receiving time; A completion instruction is used to instruct to re-push the alarm information of the abnormal event after the receiving time.

5. The method according to claim 4, characterized in that The first duration is a first default duration or a duration carried in the claiming information; The second duration is a second default duration or a duration carried in the claim information.

6. The method according to claim 2, characterized in that After pushing the alarm information to the chat window of the associated user or the collaborative processing group, the method further includes: If the question and answer information regarding the abnormal event is received from the associated user through the chat window, then based on the question and answer information, the large language model is used to reply to the operation and maintenance suggestions for the abnormal event to obtain reply information; The reply information is pushed to the chat window.

7. The method according to claim 3, characterized in that The method further comprises: If feedback query information input by the associated user through the chat window is received, extracting the processing instruction to be queried from the feedback query information; Based on the user identifier of the associated user and the processing instruction to be queried, the target alarm information fed back by the associated user is filtered out from the recorded fed back alarm information; The target alarm information is pushed to the chat window of the associated user.

8. The method according to any one of claims 1 to 7, characterized in that: The step of identifying, based on each piece of feedback alarm information, whether an abnormal event corresponding to the alarm information has been fed back includes: Comparing the alarm information included in each feedback alarm information with the alarm information; If it is determined that the alarm information matches the alarm information included in any alarm information that has been fed back, it is determined that the abnormal event corresponding to the alarm information has been fed back; If it is determined that the alarm information does not match the alarm information included in each fed-back alarm information, it is determined that the abnormal event corresponding to the alarm information has not been fed back.

9. A server, characterized in that: include: Memory, used to store computer programs or instructions; A processor is used to execute the computer program or instructions in the memory so that the method according to any one of claims 1 to 8 is performed.

10. A computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor, the processor is enabled to perform the method according to any one of claims 1 to 8.

Images