Artificial intelligence-based problem diagnosis method, device and system
By automatically acquiring and merging client and server logs using an AI-based intelligent agent to diagnose problems and updating the model after confirming the confidence threshold, the problem of low efficiency and poor accuracy of manual diagnosis is solved, achieving efficient and reliable application problem diagnosis.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING BAIDU NETCOM SCI & TECH CO LTD
- Filing Date
- 2026-02-06
- Publication Date
- 2026-06-26
AI Technical Summary
In existing technologies, application problem diagnosis mainly relies on manual methods, which leads to low efficiency and accuracy, and is prone to error accumulation.
An AI-based approach is adopted, in which a first agent acquires and merges client and server logs, a second agent is used to diagnose problems, and the diagnosis results are confirmed when the confidence level reaches a threshold. During the review process, the agent model is updated to improve accuracy.
It improves the efficiency and accuracy of problem diagnosis, reduces error accumulation, and enhances the reliability of diagnostic results.
Smart Images
Figure CN122285332A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of artificial intelligence technology, particularly to the fields of large models, intelligent agents, and cloud computing, and specifically to a problem diagnosis method, apparatus, system, device, medium, and product based on artificial intelligence. Background Technology
[0002] If users encounter any problems while using the application, they can submit feedback through the feedback portal.
[0003] In related technologies, problems are usually diagnosed manually, and conclusions are then drawn. Summary of the Invention
[0004] This disclosure provides a problem diagnosis method, apparatus, system, device, medium, and product based on artificial intelligence.
[0005] According to one aspect of this disclosure, an artificial intelligence-based problem diagnosis method is provided, comprising: generating a diagnosis request, the diagnosis request including a target problem; employing a first intelligent agent to obtain a target client log corresponding to the target problem from candidate client logs, and to obtain a target server log corresponding to the target problem from candidate server logs, merging the target client log and the target server log to obtain a target log; employing a second intelligent agent to diagnose the target problem based on the target log to obtain an initial diagnosis result and a confidence level; and, in response to the confidence level being greater than or equal to a preset threshold, using the initial diagnosis result as the target diagnosis result for the target problem.
[0006] According to another aspect of this disclosure, an artificial intelligence-based problem diagnosis device is provided, comprising: a generation module for generating a diagnosis request, the diagnosis request including a target problem; a merging module for employing a first intelligent agent to obtain a target client log corresponding to the target problem from candidate client logs, and a target server log corresponding to the target problem from candidate server logs, and merging the target client log and the target server log to obtain a target log; a diagnosis module for employing a second intelligent agent to diagnose the target problem based on the target log to obtain an initial diagnosis result and a confidence level; and a sending module for sending the initial diagnosis result as a target diagnosis result for the target problem in response to the confidence level being greater than or equal to a preset threshold.
[0007] According to another aspect of this disclosure, an artificial intelligence-based problem diagnosis system is provided, comprising: a first intelligent agent, configured to obtain a target client log corresponding to the target problem from candidate client logs, obtain a target server log corresponding to the target problem from candidate server logs, and merge the target client log and the target server log to obtain a target log; a second intelligent agent, configured to diagnose the target problem based on the target log to obtain an initial diagnosis result and a confidence level; an interaction module, configured to generate a diagnosis request, the diagnosis request including the target problem; and, in response to the confidence level being greater than or equal to a preset threshold, using the initial diagnosis result as the target diagnosis result for the target problem.
[0008] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to said at least one processor; wherein the memory stores instructions executable by said at least one processor, said instructions being executed by said at least one processor to enable said at least one processor to perform the method as described in any of the foregoing aspects.
[0009] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method according to any of the preceding aspects.
[0010] According to another aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method according to any of the preceding aspects.
[0011] According to embodiments of this disclosure, the efficiency and accuracy of problem diagnosis can be improved.
[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description
[0013] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:
[0014] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure;
[0015] Figure 2 This is a schematic diagram according to the second embodiment of the present disclosure;
[0016] Figure 3 This is a flowchart illustrating log-related operations provided in the embodiments of this disclosure;
[0017] Figure 4 This is a schematic diagram of the review process provided according to embodiments of this disclosure;
[0018] Figure 5 This is a schematic diagram according to the third embodiment of the present disclosure;
[0019] Figure 6 This is a schematic diagram according to the fourth embodiment of the present disclosure;
[0020] Figure 7 This is a schematic diagram of an electronic device used to implement the AI-based problem diagnosis method according to the embodiments of this disclosure. Detailed Implementation
[0021] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.
[0022] Taking customer service scenarios as an example, the problem diagnosis process typically includes: the user reports a problem to customer service personnel; the customer service personnel report the problem to the client-side developers; the client-side developers obtain the relevant client-side logs and forward the problem to the server-side developers; the server-side developers obtain the relevant server-side logs; the client-side developers summarize the relevant client-side and server-side logs, and perform manual troubleshooting.
[0023] The above methods are mainly implemented manually, which results in low efficiency and accuracy.
[0024] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure. This embodiment provides a problem diagnosis method based on artificial intelligence. Figure 1 As shown, the method includes:
[0025] 101. Generate a diagnostic request, which includes the target problem.
[0026] 102. Using a first intelligent agent, obtain the target client log corresponding to the target problem from the candidate client logs, obtain the target server log corresponding to the target problem from the candidate server logs, and merge the target client log and the target server log to obtain the target log.
[0027] 103. Employ a second intelligent agent to diagnose the target problem based on the target log, in order to obtain initial diagnostic results and confidence levels.
[0028] 104. In response to the confidence level being greater than or equal to a preset threshold, the initial diagnostic result is used as the target diagnostic result for the target problem.
[0029] The target problem refers to the problem to be diagnosed, such as the problem encountered by users when using the application.
[0030] Diagnostic requests can be generated based on user actions. For example, after discovering a problem, a user can submit the issue through the feedback button on the application's interface, generating a diagnostic request based on this submission. Alternatively, after discovering a problem, a user can report it to customer service, who will then generate a support ticket containing the target issue, serving as a diagnostic request.
[0031] An agent is an autonomous entity that can perceive the external environment, make autonomous decisions, and execute actions to achieve a specific goal.
[0032] The first intelligent agent refers to the intelligent agent that obtains problem-related logs and merges the logs.
[0033] The second intelligent agent refers to the intelligent agent that diagnoses problems based on the merged logs.
[0034] Client-side logs are logs generated based on user behavior on the client's local machine, such as recording buttons clicked by the user on the client's webpage.
[0035] Server-side logs are generated based on user calls to the server, such as recording the server-side application programming interfaces (APIs) called by the user when using the client.
[0036] Candidate client logs and candidate server logs are generated based on the user's historical behavior. For example, candidate client logs are generated based on the user's historical behavior on the client's local machine, and candidate server logs are generated based on the user's historical call information to the server's API.
[0037] Target client logs and target server logs refer to client logs and server logs related to the target issue.
[0038] Upon receiving the target question, the target question is input into the first intelligent agent. The first intelligent agent retrieves the target client log from the candidate client log and the target server log from the candidate server log. Then, the target client log and the target server log are merged to obtain the merged log, which is used as the target log.
[0039] After obtaining the target log, the target log and the target problem are input into the second agent. The second agent diagnoses the target problem based on the target log and obtains the initial diagnosis result and its corresponding confidence level.
[0040] When the confidence level is greater than or equal to a preset threshold (e.g., 0.85), the initial diagnostic result is used as the target diagnostic result.
[0041] In addition, when the confidence level is less than the preset threshold, the initial diagnostic results can be reviewed manually to obtain the target diagnostic results.
[0042] Initial diagnostic results and target diagnostic results can specifically include root causes and remediation suggestions. Root causes indicate the cause of the target problem, while remediation suggestions are used to resolve the target problem. For example, if a user reports the target problem of "2GB of data was used up last night" when using cloud storage, the root cause could be "repeatedly downloading file chunks in the background," and the remediation suggestion could be "configuration has been pushed and will take effect on the next startup."
[0043] After obtaining the target diagnostic results, the target diagnostic results can be fed back to the user.
[0044] In this embodiment, a first intelligent agent acquires target client logs and target server logs, and merges them to obtain the target log. This enables automatic log acquisition and merging. A second intelligent agent then diagnoses the target problem based on the target log, obtaining an initial diagnostic result. This achieves automated problem diagnosis, improving efficiency and accuracy compared to manual diagnostic processes. Furthermore, using two intelligent agents for problem diagnosis, compared to a single-agent approach, avoids error accumulation and improves the reliability of the diagnostic results.
[0045] Figure 2 This is a schematic diagram based on the second embodiment of the present disclosure, which provides a problem diagnosis method based on artificial intelligence.
[0046] The method in this embodiment can be executed by an AI-based problem diagnosis system, which includes an interaction module, a first intelligent agent, and a second intelligent agent.
[0047] Combining the above modules, such as Figure 2 As shown, the method includes:
[0048] 201. The interaction module generates a diagnostic request, which includes the target problem.
[0049] The interaction module can generate a diagnostic request based on the target problem after receiving feedback from the user. Specifically, the target problem can be added to the diagnostic request. In addition, a target user identifier can be added to the diagnostic request to identify the user who reported the target problem.
[0050] The target issue can include issue description information and issue time information. For example, when a user is using cloud storage, the target issue reported is "2GB wasted last night". Here, "last night" is the issue time information and "2GB wasted" is the issue description information.
[0051] 202. The first intelligent agent obtains the target client log corresponding to the target problem from the candidate client logs, obtains the target server log corresponding to the target problem from the candidate server logs, and merges the target client log and the target server log to obtain the target log.
[0052] Among them, candidate client logs and candidate server logs can be recorded in the log platform. After the first intelligent agent receives the diagnostic request, it can interact with the log platform to obtain the target client log corresponding to the target problem from the candidate client logs, and obtain the target server log corresponding to the target problem from the candidate server logs.
[0053] Each time a user uses the application, a unique trace ID is generated to track their actions during that single use. For example, if a user performs actions such as querying or downloading during a single use of the application, these actions will correspond to the same trace ID. When a user exits the application and uses it again, a new trace ID will be generated.
[0054] In addition, after generating the tracking identifier, a mapping relationship between the user identifier and the tracking identifier can be established.
[0055] Upon receiving a diagnostic request, the target user identifier is mapped to a target tracking identifier based on the target user identifier contained in the diagnostic request and the mapping relationship described above.
[0056] Both candidate client logs and candidate server logs can record trace identifiers (traceIDs) and timestamps. After obtaining the target trace identifier, candidate client logs and candidate server logs containing the target trace identifier and with matching timestamps can be used as the target client logs and target server logs, respectively, and then merged based on timestamps. Time matching means that there are at least some identical time points.
[0057] Taking client logs as an example, assuming the target tracking identifier is the first identifier and the target time information is 9 o'clock, assuming the first candidate client log contains the first identifier and the timestamp corresponding to the first candidate client log is from 8:50 to 9:05, then the first candidate client log will be used as the target client log.
[0058] The tracking identifiers and timestamps in the logs are generated based on the user's historical behavior.
[0059] Figure 3 This is a flowchart illustrating log-related operations provided in the embodiments of this disclosure.
[0060] like Figure 3 As shown, the log operation process may include:
[0061] 301. Based on the user's local behavior on the client, generate a tracking identifier and timestamp, and record them in the candidate client log.
[0062] 302. When it is necessary to call the server-side interface, send a call request to the server, and the call request includes a trace identifier.
[0063] 303. The server obtains the trace identifier from the call request, generates a timestamp when the server receives the call request, and records the trace identifier and timestamp in the candidate server log.
[0064] Based on the above operations, tracking identifiers and timestamps can be recorded in candidate client logs and candidate server logs. Subsequently, when the target log is needed, the following process can be executed:
[0065] 304. The first intelligent agent obtains the target client log from the candidate client log based on the tracking identifier and timestamp.
[0066] 305. The first intelligent agent obtains the target server log from the candidate server log based on the tracking identifier and timestamp.
[0067] 306. The first intelligent agent merges the target client logs and the target server logs based on the timestamps.
[0068] Upon receiving a diagnostic request, the first agent maps the target user identifier contained in the request to a target tracking identifier. It then obtains the target time information from the target question within the request. Candidate client logs and candidate server logs containing the target tracking identifier and whose timestamps match the target time information are designated as the target client log and target server log, respectively. Next, the logs are merged based on their timestamps, for example, by arranging the logs in chronological order. If the target client logs include A (containing timestamp t1) and B (containing timestamp t2), and the target server logs include C (containing timestamp t3), assuming t1 is earlier than t3 and t3 is earlier than t2, the merged target logs would be: A, C, B.
[0069] In some embodiments, the diagnostic request further includes a target user identifier, and the target problem includes target time information;
[0070] Both the candidate client logs and the candidate server logs contain a tracking identifier and a timestamp;
[0071] The first intelligent agent includes: a mapping module, a first acquisition module, a second acquisition module, and a first large model;
[0072] The first intelligent agent is used to obtain the target client log corresponding to the target problem from the candidate client logs and the target server log corresponding to the target problem from the candidate server logs. The target client log and the target server log are then merged to obtain the target log, including:
[0073] Using the mapping module, based on a pre-determined mapping relationship between user identifiers and tracking identifiers, the target user identifier is mapped to a target tracking identifier;
[0074] Using the first acquisition module, a client log containing the target tracking identifier and whose timestamp matches the target time information is acquired from the candidate client logs and used as the target client log;
[0075] Using the second acquisition module, server logs containing the target tracking identifier and whose timestamps match the target time information are acquired from the candidate server logs and used as the target server logs;
[0076] Using the first major model, the target client log and the target server log are merged based on the timestamp contained in the target client log and the timestamp contained in the target server log to obtain the target log.
[0077] In this embodiment, the target client logs and target server logs can be obtained efficiently and accurately based on the tracking identifier and timestamp, and the accuracy can be improved by merging the target client logs and target server logs based on the first major model.
[0078] 203. Employ a second intelligent agent to diagnose the target problem based on the target log, in order to obtain initial diagnostic results and confidence levels.
[0079] In some embodiments, the second intelligent agent includes: a knowledge query module and a second main model;
[0080] The second intelligent agent is used to diagnose the target problem based on the target log to obtain an initial diagnostic result and confidence level, including:
[0081] The knowledge query module is used to obtain log features corresponding to the target log from a preset knowledge base;
[0082] The second major model is used to process the target problem and the log features to obtain the initial diagnostic results and confidence levels.
[0083] The knowledge base can record feature data, such as keyword vectors. During a query, the target log can be vectorized, and its similarity to the keyword vectors can be calculated. A preset number of keywords with high similarity are used as log features. Then, the target question and log features are sent to the second model along with a prompt message. The second model generates an initial diagnosis and confidence score based on this prompt message.
[0084] In this embodiment, using a large model for diagnosis can improve diagnostic efficiency and accuracy. In addition, since the amount of log feature data is smaller than the target log, processing the log features can further improve processing efficiency.
[0085] 204. In response to the confidence level being greater than or equal to a preset threshold, the initial diagnostic result is used as the target diagnostic result for the target problem.
[0086] 205. In response to the confidence level being less than a preset threshold, the initial diagnostic result is reviewed to obtain a review result, the review result including: the target diagnostic result.
[0087] 206. Based on the verification results, update the first agent and / or the second agent.
[0088] For example, taking a cloud storage application as an example, when a user is using the cloud storage, the target problem reported is "2GB was used up last night". After starting the automatic diagnosis system, the target problem is input into the first intelligent agent. The first intelligent agent obtains the target client log and the target server log corresponding to the target problem, merges the two, and outputs the target log.
[0089] The target log and target problem are input into the second agent. After the second agent diagnoses the target problem based on the target log, the output is the initial diagnosis result and confidence level.
[0090] The initial diagnostic results may include: root cause and repair suggestions. For example, if the root cause is "repeatedly downloading file fragments in the background", the repair suggestion is "configuration has been pushed and will take effect on the next startup".
[0091] If the confidence level of the initial diagnosis is greater than or equal to a preset threshold, the initial diagnosis will be returned to the user. If the confidence level of the initial diagnosis is less than the preset threshold, a review process will be executed.
[0092] Figure 4 This is a schematic diagram of the review process provided according to embodiments of this disclosure.
[0093] like Figure 4 As shown, the review process may include:
[0094] 401. Display annotation interface.
[0095] Once the review process is triggered, the annotation interface can be displayed to the annotators, and the positive and negative samples annotated by them can be received through the annotation interface. For example, if the annotators believe that the initial diagnostic result meets the requirements, they will annotate it as a positive sample; otherwise, they will annotate it as a negative sample. In addition, for initial diagnostic results that do not meet the requirements, they can be corrected, and the corrected diagnostic result can be used as the target diagnostic result, and the target diagnostic result can be annotated as a positive sample.
[0096] 402. Update training data.
[0097] That is, positive and negative samples with the above annotations can be added to the existing training data.
[0098] 403. Regular incremental training.
[0099] That is, the updated training data can be used to retrain the large model when the preset training period is reached.
[0100] 404, LLM update.
[0101] The LLM can be the largest model in the first agent and / or the second largest model in the second agent. The LLM can be updated through periodic incremental training.
[0102] In this embodiment, when the confidence level is less than a preset threshold, the initial diagnostic result is reviewed to obtain a review result, which includes the target diagnostic result. This can improve the reliability of the target diagnostic result.
[0103] In addition, the review results are used to update the agent, specifically the large model in the agent. This enables the agent to evolve automatically and improves its accuracy.
[0104] Figure 5 This is a schematic diagram based on a third embodiment of the present disclosure, which provides an artificial intelligence-based problem diagnosis device. Figure 5 As shown, the device 500 includes: a generation module 501, a merging module 502, a diagnostic module 503, and a sending module 504.
[0105] The generation module 501 is used to generate a diagnostic request, which includes a target problem; the merging module 502 is used to use a first intelligent agent to obtain the target client log corresponding to the target problem from the candidate client logs, obtain the target server log corresponding to the target problem from the candidate server logs, and merge the target client log and the target server log to obtain the target log; the diagnostic module 503 is used to use a second intelligent agent to diagnose the target problem based on the target log to obtain an initial diagnostic result and a confidence level; the sending module 504 is used to send the initial diagnostic result as the target diagnostic result of the target problem in response to the confidence level being greater than or equal to a preset threshold.
[0106] In this embodiment, a first intelligent agent acquires target client logs and target server logs, and merges them to obtain the target log. This enables automatic log acquisition and merging. A second intelligent agent then diagnoses the target problem based on the target log, obtaining an initial diagnostic result. This achieves automated problem diagnosis, improving efficiency and accuracy compared to manual diagnostic processes. Furthermore, using two intelligent agents for problem diagnosis, compared to a single-agent approach, avoids error accumulation and improves the reliability of the diagnostic results.
[0107] In some embodiments, the diagnostic request further includes a target user identifier, and the target problem includes target time information; both the candidate client log and the candidate server log include a tracking identifier and a timestamp; the first intelligent agent includes: a mapping module, a first acquisition module, a second acquisition module, and a first large model; the merging module 502 is further used for:
[0108] Using the mapping module, based on a pre-determined mapping relationship between user identifiers and tracking identifiers, the target user identifier is mapped to a target tracking identifier;
[0109] Using the first acquisition module, a client log containing the target tracking identifier and whose timestamp matches the target time information is acquired from the candidate client logs and used as the target client log;
[0110] Using the second acquisition module, server logs containing the target tracking identifier and whose timestamps match the target time information are acquired from the candidate server logs and used as the target server logs;
[0111] Using the first major model, the target client log and the target server log are merged based on the timestamp contained in the target client log and the timestamp contained in the target server log to obtain the target log.
[0112] In this embodiment, the target client logs and target server logs can be obtained efficiently and accurately based on the tracking identifier and timestamp, and the accuracy can be improved by merging the target client logs and target server logs based on the first major model.
[0113] In some embodiments, the second intelligent agent includes: a knowledge query module and a second main model;
[0114] Diagnostic module 503 is further used for:
[0115] The knowledge query module is used to obtain log features corresponding to the target log from a preset knowledge base;
[0116] The second major model is used to process the target problem and the log features to obtain the initial diagnostic results and confidence levels.
[0117] In this embodiment, using a large model for diagnosis can improve diagnostic efficiency and accuracy. In addition, since the amount of log feature data is smaller than the target log, processing the log features can further improve processing efficiency.
[0118] In some embodiments, the device 500 further includes:
[0119] The verification module is used to verify the initial diagnosis result in response to the confidence level being less than a preset threshold, so as to obtain a verification result, the verification result including: the target diagnosis result.
[0120] In this embodiment, when the confidence level is less than a preset threshold, the initial diagnostic result is reviewed to obtain a review result, which includes the target diagnostic result. This can improve the reliability of the target diagnostic result.
[0121] In some embodiments, the device 500 further includes:
[0122] Based on the verification results, update the first agent and / or the second agent.
[0123] In this embodiment, the review results are used to update the agent, specifically the large model in the agent. This enables the agent to evolve automatically and improves its accuracy.
[0124] Figure 6 This is a schematic diagram based on the fourth embodiment of the present disclosure, which provides an artificial intelligence-based problem diagnosis system. For example... Figure 6 As shown, the system includes: an interaction module 601, a first intelligent agent 602, and a second intelligent agent 603.
[0125] The first intelligent agent 602 is used to obtain the target client log corresponding to the target problem from the candidate client logs, obtain the target server log corresponding to the target problem from the candidate server logs, and merge the target client log and the target server log to obtain the target log;
[0126] The second intelligent agent 603 is used to diagnose the target problem based on the target log to obtain an initial diagnosis result and confidence level;
[0127] An interaction module 601 is configured to generate a diagnostic request, the diagnostic request including a target problem; and, in response to the confidence level being greater than or equal to a preset threshold, to use the initial diagnostic result as the target diagnostic result for the target problem.
[0128] In this embodiment, a first intelligent agent acquires target client logs and target server logs, and merges them to obtain the target log. This enables automatic log acquisition and merging. A second intelligent agent then diagnoses the target problem based on the target log, obtaining an initial diagnostic result. This achieves automated problem diagnosis, improving efficiency and accuracy compared to manual diagnostic processes. Furthermore, using two intelligent agents for problem diagnosis, compared to a single-agent approach, avoids error accumulation and improves the reliability of the diagnostic results.
[0129] It is understood that the same or similar content in different embodiments of this disclosure can be referred to each other.
[0130] It is understood that the terms "first" and "second" in the embodiments of this disclosure are only used for distinction and do not indicate the degree of importance or the order of events.
[0131] It is understandable that, unless otherwise specified, the order of steps in the process indicates that the temporal relationship between these steps is not limited.
[0132] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0133] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.
[0134] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device 700 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0135] like Figure 7 As shown, the electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. The RAM 703 may also store various programs and data required for the operation of the electronic device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.
[0136] Multiple components in electronic device 700 are connected to I / O interface 705, including: input unit 706, such as keyboard, mouse, etc.; output unit 707, such as various types of displays, speakers, etc.; storage unit 708, such as disk, optical disk, etc.; and communication unit 709, such as network card, modem, wireless transceiver, etc. Communication unit 709 allows electronic device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0137] The computing unit 701 can be a variety of general-purpose and / or proprietary processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various proprietary artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as AI-based problem diagnosis methods. For example, in some embodiments, the AI-based problem diagnosis method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the AI-based problem diagnosis method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform AI-based problem diagnosis methods by any other suitable means (e.g., by means of firmware).
[0138] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), proprietary integrated circuits (ASICs), proprietary standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a proprietary or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0139] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to the processor or controller of a general-purpose computer, a proprietary computer, or other programmable problem diagnostic apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0140] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0141] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0142] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.
[0143] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.
[0144] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.
[0145] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.
Claims
1. A problem diagnosis method based on artificial intelligence, comprising: Generate a diagnostic request, which includes the target problem; Using a first intelligent agent, the target client log corresponding to the target problem is obtained from the candidate client logs, and the target server log corresponding to the target problem is obtained from the candidate server logs. The target client log and the target server log are merged to obtain the target log. A second intelligent agent is used to diagnose the target problem based on the target log to obtain an initial diagnosis result and confidence level. In response to the confidence level being greater than or equal to a preset threshold, the initial diagnostic result is used as the target diagnostic result for the target problem.
2. The method according to claim 1, wherein, The diagnostic request also includes a target user identifier, and the target problem includes target time information; Both the candidate client logs and the candidate server logs contain a tracking identifier and a timestamp; The first intelligent agent includes: a mapping module, a first acquisition module, a second acquisition module, and a first large model; The first intelligent agent is used to obtain the target client log corresponding to the target problem from the candidate client logs and the target server log corresponding to the target problem from the candidate server logs. The target client log and the target server log are then merged to obtain the target log, including: Using the mapping module, based on a pre-determined mapping relationship between user identifiers and tracking identifiers, the target user identifier is mapped to a target tracking identifier; Using the first acquisition module, a client log containing the target tracking identifier and whose timestamp matches the target time information is acquired from the candidate client logs and used as the target client log; Using the second acquisition module, server logs containing the target tracking identifier and whose timestamps match the target time information are acquired from the candidate server logs and used as the target server logs; Using the first major model, the target client log and the target server log are merged based on the timestamp contained in the target client log and the timestamp contained in the target server log to obtain the target log.
3. The method according to claim 1, wherein, The second intelligent agent includes: a knowledge query module and a second major model; The second intelligent agent is used to diagnose the target problem based on the target log to obtain an initial diagnostic result and confidence level, including: The knowledge query module is used to obtain log features corresponding to the target log from a preset knowledge base; The second major model is used to process the target problem and the log features to obtain the initial diagnostic results and confidence levels.
4. The method according to claim 1, further comprising: In response to the confidence level being less than a preset threshold, the initial diagnostic result is reviewed to obtain a review result, which includes the target diagnostic result.
5. The method according to claim 4, further comprising: Based on the verification results, update the first agent and / or the second agent.
6. A problem diagnosis device based on artificial intelligence, comprising: The generation module is used to generate a diagnostic request, which contains the target problem; The merging module is used to employ a first intelligent agent to obtain the target client log corresponding to the target problem from the candidate client logs, obtain the target server log corresponding to the target problem from the candidate server logs, and merge the target client log and the target server log to obtain the target log; A diagnostic module is used to diagnose the target problem based on the target log using a second intelligent agent, so as to obtain an initial diagnostic result and confidence level; The sending module is configured to, in response to the confidence level being greater than or equal to a preset threshold, use the initial diagnostic result as the target diagnostic result for the target problem.
7. An artificial intelligence-based problem diagnosis system, comprising: A first intelligent agent is used to obtain the target client log corresponding to the target problem from the candidate client logs, obtain the target server log corresponding to the target problem from the candidate server logs, and merge the target client log and the target server log to obtain the target log; The second intelligent agent is used to diagnose the target problem based on the target log to obtain an initial diagnosis result and confidence level; The interaction module is used to generate a diagnostic request, which includes the target problem. In addition, in response to the confidence level being greater than or equal to a preset threshold, the initial diagnostic result is used as the target diagnostic result for the target problem.
8. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.
9. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-5.
10. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-5.