Question processing method and device, electronic equipment and storage medium

Abstract

The invention discloses a problem processing method and device, electronic equipment and a storage medium, and relates to the technical fields of intelligent search, artificial intelligence and the like. According to the specific implementation scheme, the method comprises the steps of obtaining a scene label and a target timestamp corresponding to a question input by a user; the target timestamp is used for identifying the time when the problem occurs; obtaining a plurality of corresponding logs based on the scene label and the target timestamp; based on a preset key field list, extracting information of key fields from the logs; and reporting the question and the information of the key field to a cloud, so that the cloud processes the question based on the question and the information of the key field.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, specifically to the fields of intelligent search and artificial intelligence, and particularly to a problem-solving method, apparatus, electronic device and storage medium. Background Technology

[0002] In existing technologies, when users encounter problems while using services provided by the server on the application's front end, they can describe the issue via phone, email, or online forms to request technical support. After receiving the user's question, technical support personnel can assess the situation based on experience and interact with the user through remote desktop, screen sharing, or repeated question-and-answer sessions to obtain more information, thereby locating and resolving the problem. Summary of the Invention

[0003] This disclosure provides a problem-solving method, apparatus, electronic device, and storage medium.

[0004] According to one aspect of this disclosure, a problem-solving method is provided, comprising:

[0005] Obtain the scene tag and target timestamp corresponding to the user-input question; the target timestamp is used to identify the time when the question occurred.

[0006] Based on the scene tag and the target timestamp, obtain the corresponding multiple log entries;

[0007] Based on a preset list of key fields, information about the key fields is extracted from the multiple log entries.

[0008] The problem and the information of the key fields are reported to the cloud so that the cloud can process the problem based on the information of the problem and the key fields.

[0009] According to another aspect of this disclosure, a problem-solving method is provided, comprising:

[0010] The system receives the problem reported by the front end, along with information on key fields. The information on key fields is obtained by the front end from multiple log entries based on the scenario tag and target timestamp corresponding to the user's problem, and extracted from these multiple log entries based on a preset list of key fields.

[0011] Based on a pre-built knowledge base, the problem, and information from the key fields, a solution is obtained;

[0012] The solution is fed back to the front end. According to another aspect of this disclosure, a front end is provided, comprising:

[0013] The information acquisition module is used to acquire the scene tag and target timestamp corresponding to the question input by the user; the target timestamp is used to identify the time when the question occurred.

[0014] The log acquisition module is used to acquire multiple corresponding logs based on the scene tag and the target timestamp;

[0015] The field extraction module is used to extract information about key fields from the multiple logs based on a preset list of key fields.

[0016] The reporting module is used to report the problem and the information of the key fields to the cloud, so that the cloud can process the problem based on the information of the problem and the key fields.

[0017] According to another aspect of this disclosure, a cloud platform is provided, comprising:

[0018] The receiving module is used to receive the problem reported by the front end and the information of key fields; the information of key fields is obtained by the front end based on the scene tag and target timestamp corresponding to the user's problem, and extracted from the multiple logs based on a preset list of key fields;

[0019] The solution acquisition module is used to acquire solutions based on a pre-built knowledge base, the problem, and information from the key fields.

[0020] The feedback module is used to provide feedback on the solution to the front end.

[0021] According to another aspect of this disclosure, a problem-solving system is provided, including a front-end and a cloud, wherein the front-end is communicatively connected to the cloud; the front-end and the cloud collaboratively perform problem-solving; the front-end is a front-end employing the aspects and any possible implementations described above; and the cloud is a cloud employing the aspects and any possible implementations described above.

[0022] According to yet another aspect of this disclosure, an electronic device is provided, comprising:

[0023] At least one processor; and

[0024] A memory communicatively connected to the at least one processor; wherein,

[0025] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods described above and any possible implementations.

[0026] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to perform the methods described above and any possible implementation thereof.

[0027] According to yet another aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the aspects and any possible implementations described above.

[0028] The technology disclosed herein can effectively improve the accuracy and efficiency of problem handling.

[0029] 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

[0030] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0031] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure;

[0032] Figure 2 This is a schematic diagram according to the second embodiment of the present disclosure;

[0033] Figure 3 This is a schematic diagram according to the third embodiment of the present disclosure;

[0034] Figure 4 This is a schematic diagram according to the fourth embodiment of the present disclosure;

[0035] Figure 5 This is a schematic diagram according to the fifth embodiment of the present disclosure;

[0036] Figure 6 This is a schematic diagram according to the sixth embodiment of the present disclosure;

[0037] Figure 7 This is a schematic diagram according to the seventh embodiment of the present disclosure;

[0038] Figure 8 This is a block diagram of an electronic device used to implement the methods of the embodiments of this disclosure. Detailed Implementation

[0039] 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.

[0040] Obviously, the described embodiments are only some, not all, of the embodiments disclosed herein. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0041] It should be noted that the terminal devices involved in the embodiments of this disclosure may include, but are not limited to, smart devices such as mobile phones, personal digital assistants (PDAs), wireless handheld devices, and tablet computers; the display devices may include, but are not limited to, personal computers, televisions, and other devices with display functions.

[0042] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0043] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure; as shown Figure 1 As shown, this embodiment provides a problem-solving method, which may specifically include the following steps:

[0044] S101. Obtain the scene tag and target timestamp corresponding to the user-input question; the target timestamp is used to identify the time when the question occurred.

[0045] The problem-solving method in this embodiment is applied in the front end. This front end can be the front end of an application (app).

[0046] When users encounter problems while using services provided by the backend through the frontend, they can input the problem on the frontend to request a solution. Correspondingly, the frontend can retrieve the relevant scenario tag and target timestamp based on the user's input.

[0047] In this embodiment, the scene tag can be used to uniquely identify the scene or service type corresponding to the question. For example, a user can use multiple sub-services provided by the backend in the frontend. If a sub-service encounters an error, when the user inputs a question based on the error corresponding to that sub-service, the corresponding scene tag can be the name or identifier of that sub-service. The name or identifier of the sub-service is used to identify the service type of the sub-service, and it can also be used to identify the scene of the sub-service.

[0048] The target timestamp in this embodiment corresponds to the time when the problem occurred and can be used to identify the time when the problem occurred.

[0049] In this embodiment, the backend refers to the server providing the service. In this embodiment, the backend is set up in the cloud; therefore, the backend in this embodiment also refers to the cloud, and the cloud is the backend.

[0050] S102. Based on the scene tag and target timestamp, obtain the corresponding multiple logs;

[0051] Specifically, based on the scene tag and target timestamp, multiple logs related to the scene tag and the time when the problem occurred can be retrieved locally on the front end.

[0052] S103. Based on a preset list of key fields, extract information about key fields from multiple logs;

[0053] In this embodiment, the preset list of key fields can be a list of multiple key field names pre-configured by the backend based on problem analysis requirements. Specifically, this list of key fields can be obtained from the backend and stored in the frontend before problem processing.

[0054] S104. Report the problem and key field information to the cloud so that the cloud can process the problem based on the problem and key field information.

[0055] In this embodiment, after obtaining the information of the key fields, the problem and the information of the key fields are reported to the cloud together. The cloud then processes the problem based on the information of the problem and the key fields and provides feedback to the front end for the user to view.

[0056] Compared with the manual problem-solving methods in the prior art, the problem-solving method in this embodiment can handle user problems in a timely manner through edge-cloud collaboration, solving the problems of long processing time and low efficiency in manual problem-solving in the prior art, and effectively shortening the problem-solving time; moreover, by reporting the problem and key field information to the cloud, the cloud can process the problem based on the problem and key field information, which can use rich information for problem processing, effectively improving the accuracy and efficiency of problem solving.

[0057] Figure 2 This is a schematic diagram based on the second embodiment of this disclosure; the problem-solving method of this embodiment, in the above... Figure 1 Based on the technical solutions of the illustrated embodiments, the technical solutions of this disclosure will be described in further detail. For example... Figure 2 As shown, the problem-solving method in this embodiment may specifically include the following steps:

[0058] S201. Obtain the user's input question and send the question to the cloud;

[0059] S202. Receive and display the function activation confirmation message sent from the cloud. This function activation confirmation message is triggered when the cloud receives a question sent from the front end. The function activation confirmation message is used to prompt the user to solve the problem through in-depth thinking.

[0060] Correspondingly, after step S201, once the cloud receives the user's question, it determines that the user has entered a problem-related message, not a chat message, and therefore needs to resolve the problem. To improve problem-solving efficiency, a feature activation confirmation message can be sent to the front end, allowing the user to choose whether to enable the feature when it is displayed to them. It should be noted that when displaying the feature activation confirmation message to the user, it should be explained that the feature's purpose is to help them solve their current problem more accurately through deep thinking. If the user enables the feature, it indicates that they agree to solve the current problem through deep thinking, thereby improving the accuracy of problem-solving.

[0061] S203. Intercept the user's confirmation message for enabling a function and trigger a link through the function selected by the human-machine interface module;

[0062] For example, a user can click the confirmation button corresponding to the function activation confirmation message through a human-computer interface module such as a mouse, keyboard, or touchscreen. At this time, a function trigger link is initiated on the front end. Theoretically, this function trigger link is sent from the front end to the cloud, but in this embodiment, the front end intercepts the function trigger link.

[0063] S204. Obtain the scene tag and target timestamp from the function trigger link;

[0064] Specifically, the link that triggers this function can include a Uniform Resource Locator (URL) parameter. After the front-end intercepts the triggered link, it can retrieve parameters that identify the scene tag and the target timestamp from it. For example, a URL parameter like "space=video playback" indicates that the current issue is about a video playback scene.

[0065] Steps S201-S204 of this embodiment are as described above. Figure 1 One implementation of step S101 in the illustrated embodiment. This implementation triggers the execution of the problem-solving method in this embodiment when the user clicks "agree to resolve the problem through deep thinking," thereby improving the accuracy of problem handling.

[0066] Alternatively, in practical applications, in another optional implementation of step S101, the backend can send a hidden signal to the frontend to trigger the execution of the problem handling method of this embodiment without requiring the user to click.

[0067] Alternatively, in one embodiment of this disclosure, the scene tag and target timestamp corresponding to the user's question can be obtained based on a preset detection strategy. Specifically, this can be understood as pre-setting a detection strategy endpoint; when a user inputs a question, the corresponding scene tag and target timestamp are obtained to trigger the question handling method of this embodiment. In practical applications, other triggering times can also be used to obtain the scene tag and target timestamp corresponding to the user's input question, which will not be elaborated upon here.

[0068] S205. Based on the scene tag and target timestamp, obtain the corresponding multiple logs;

[0069] Specifically, the frontend retrieves multiple corresponding logs locally based on the scene tag and the target timestamp.

[0070] In the application scenario of this embodiment, the log format and content can determine whether the problems reported by users can be quickly and accurately located, so the construction and processing of logs are also very important.

[0071] In real-world applications, user problems generally fall into two categories: errors in using a certain function and poor application performance.

[0072] In the event of a functional error, a clear error code will be recorded in the log, along with the identifier / name of the corresponding file / product / service, etc.

[0073] In cases of poor performance, the system monitors and records network conditions, CPU utilization, and heat generation in real time during application operation. When these indicators deteriorate to a certain extent, they are written to the log.

[0074] In this embodiment, the logs have a defined format, and the log content may include information such as the log type, the scenario in which the problem occurred, the relevant core metrics, the values ​​of the core metrics, and the timestamp of the occurrence. Each app can design its own log format and content according to its needs.

[0075] For example, an error log may include the following information: type - error log, scenario - corresponding function, core metric - error code, metric data value - 11xxx, and the timestamp of occurrence, ...

[0076] For example, a performance log may include the following information: type - performance log, scenario - corresponding function, core metric - CPU utilization, metric data value - 98, and the timestamp of occurrence, ...

[0077] In this embodiment, the scene tag represents the scene of the problem the user is currently requesting to resolve. Combined with the target timestamp, multiple log entries can be retrieved locally on the front end. To improve the accuracy of problem handling, this embodiment expands the target timestamp forward and backward by a preset duration when retrieving logs, thus broadening the time range for log acquisition. Multiple log entries are then retrieved based on the scene tag and the time range. This preset duration can be set to a reasonable value based on practical experience, such as 1 second or 2 seconds.

[0078] S206. Extract key field information from multiple logs based on a preset list of key fields;

[0079] Specifically, we can first check whether each retrieved log entry includes a key field from the key field list. If so, we extract the key field information. By analyzing each log entry sequentially, we can obtain information on all key fields included in multiple log entries. The information for each key field includes the name and value of that key field.

[0080] S207. Report the problem and key field information to the cloud so that the cloud can process the problem based on the problem and key field information;

[0081] S208: Receive solutions or prompts from the cloud indicating that the problem is being resolved.

[0082] Specifically, if the cloud platform processes the problem and obtains a solution based on the information in the problem and key fields, it can then provide feedback on the solution to the front end. However, if the cloud platform is unable to process the problem and obtain a solution based on the information in the problem and key fields, it can provide a notification message to the front end indicating that the problem is being resolved. Correspondingly, while providing this notification, the cloud platform has also sent an alert to technical personnel to request manual intervention and obtain a solution.

[0083] In this embodiment, the cloud can provide feedback to the front end with solutions or prompts indicating that the problem is being solved, based on the actual situation of problem handling. The feedback information is very comprehensive and accurate.

[0084] For example, in this embodiment, the solutions received from cloud feedback may include at least one of the following: problem cause prompts, problem-solving suggestions, and links to tools for self-resolved problems. The types of problem solutions provided are very comprehensive and rich, which can more effectively improve the accuracy of problem handling.

[0085] The problem-handling method in this embodiment, by adopting the above scheme, sends a function activation confirmation message to the user when the user inputs a problem, and intercepts the user's function trigger link when the user agrees to think deeply about solving the problem, and obtains the user's problem's scenario tag and target timestamp. This provides a reasonable and effective way to obtain scenario tags and target timestamps, providing effective data support for subsequent problem handling, thereby effectively improving the accuracy and efficiency of problem handling.

[0086] Figure 3 This is a schematic diagram based on the third embodiment of this disclosure; as shown Figure 3 As shown, this embodiment provides a problem-solving method, which may specifically include the following steps:

[0087] S301. Receive the problem reported by the front end and the information of key fields; the information of key fields is obtained by the front end from multiple logs based on the scenario tag and target timestamp corresponding to the user's problem; and extracted from multiple logs based on the preset list of key fields;

[0088] S302. Obtain a solution based on the problem and information from key fields;

[0089] S303, Feedback the solution to the front end.

[0090] In this embodiment, after receiving the problem and key field information reported by the front end on the cloud side, a solution to the problem can be obtained based on the problem and key field information reported by the front end, which can improve the accuracy of problem solving. Finally, the solution is fed back to the front end to inform the user of the solution to the problem.

[0091] The technical solution of this embodiment is similar to that described above. Figure 1 The difference in the illustrated embodiment is that the above Figure 1 The illustrated embodiment describes the technical solution of this disclosure on the front-end side, while this embodiment describes the technical solution of this disclosure on the cloud side, and its implementation principle is the same as described above. Figure 1 The embodiments shown are the same, and details can also be found above. Figure 1 The description of the illustrated embodiments will not be repeated here.

[0092] Compared with the manual problem-solving methods in the prior art, the problem-solving method in this embodiment can handle user problems in a timely manner through edge-cloud collaboration, solving the problems of long processing time and low efficiency in manual problem-solving in the prior art, and effectively shortening the problem-solving time; moreover, by obtaining solutions based on the problem and key field information, it can use rich information for problem-solving, effectively improving the accuracy and efficiency of problem-solving.

[0093] Optionally, in one embodiment of this disclosure, step S302 can be implemented using an intelligent agent, that is, using an intelligent agent to obtain a solution based on a pre-built knowledge base, the problem, and information from key fields. In other words, the cloud side in this embodiment includes not only the backend server providing the service itself, but also the intelligent agent that handles the problem. Furthermore, in this embodiment, obtaining a solution based on a pre-built knowledge base can further improve the accuracy of problem solving, shorten the time required for problem solving, and improve the efficiency of problem solving.

[0094] In this embodiment, by employing an intelligent agent and referring to a pre-built knowledge base for problem processing, the problem processing time can be effectively shortened and the problem processing efficiency improved.

[0095] In practical applications, preset strategies or search methods can also be used to obtain solutions based on knowledge bases, questions, and key field information.

[0096] Figure 4 This is a schematic diagram based on the fourth embodiment of this disclosure; the problem-solving method of this embodiment, based on the technical solutions of the above embodiments, further describes the technical solutions of this disclosure in more detail. For example... Figure 4 As shown, the problem-solving method in this embodiment may specifically include the following steps:

[0097] S401: Receive the problem reported by the front end and the information of key fields; the information of key fields is obtained by the front end from multiple logs based on the scenario tag and target timestamp corresponding to the user's problem; and extracted from multiple logs based on the preset list of key fields;

[0098] S402. Use an intelligent agent to detect whether the information in the key fields includes an error code; if it does, proceed to step S403; if it does not, proceed to step S404.

[0099] S403. Using an intelligent agent, based on error codes and a knowledge base, obtain solutions corresponding to the problems; proceed to step S405.

[0100] For example, this step can be implemented by including the following steps:

[0101] (1) Use an intelligent agent to detect whether the knowledge base includes the error reason corresponding to the error code; if it includes, execute step (2); if it does not include, execute step (4).

[0102] (2) Use an intelligent agent to retrieve the error reason corresponding to the error code from the knowledge base;

[0103] In this embodiment, the pre-built knowledge base includes a mapping relationship between error codes and their corresponding error reasons. In practical applications, the agent searches for error codes in the mapping relationship in the knowledge base. If a code is found, the agent can obtain the error reason corresponding to the error code.

[0104] (3) Using an intelligent agent, based on the cause of the error, generate a prompt about the cause of the problem or a suggestion for solving the problem, and then end.

[0105] For example, in a video playback scenario, the mapping between error codes and error reasons in the knowledge base could include: error code 11xxx, corresponding error reason: playback of the current format is not supported. Based on the error reason, the agent can then generate problem-solving suggestions, such as prompting the user to change to a supported playback format, which could include XXX, YYY, etc.

[0106] For example, the mapping between error codes and error reasons in the knowledge base could include: error code 22xxx, corresponding error reason: video resource does not exist. In this case, the agent can generate a problem reason prompt based on the error reason, such as telling the user that the original video does not exist. Since the error reason in this case is that the video resource does not exist, addressing this reason alone cannot solve the problem. Therefore, only the problem reason prompt is generated as a solution, leaving the user to check whether the original video truly does not exist.

[0107] (4) Use an intelligent agent to detect whether the information of the key fields includes the error reporting interface corresponding to the error code; if it does, execute step (5); if it does not, execute step (8).

[0108] In this embodiment, the key field information corresponding to the error code usually includes not only the error code, but also the corresponding error reporting interface.

[0109] (5) Use an intelligent agent to obtain the logs of the error-reporting interface; execute step (6);

[0110] Normally, the logs of the error-reporting port are stored in the cloud, and the logs of the error-reporting interface can be obtained directly from the cloud.

[0111] (6) Using an intelligent agent, locate the cause of the error based on the logs of the error reporting interface; execute step (7);

[0112] The intelligent agent can locate the cause of the error based on the logs of the error-reporting interface. If the cause cannot be located, the agent can optionally retrieve the logs of the downstream interface based on the error-reporting interface's logs. Specifically, the identifier of the downstream interface can be obtained from the error-reporting interface's logs, and then the logs of the downstream interface can be retrieved from the cloud. Then, the intelligent agent can locate the cause of the error based on the logs of the error-reporting interface and the downstream interface.

[0113] (7) Using an intelligent agent, based on the error reason, generate a problem-solving suggestion and end.

[0114] (8) Use an intelligent agent to generate alarm information, which carries the dialogue identifier corresponding to the problem; issue the alarm information; execute step (9);

[0115] If the key field information includes an error code, but the knowledge base does not include the error reason for that error code, and the key field information does not include the corresponding error reporting interface, then the cause of the problem cannot be located. The only solution is to send an alert and request manual assistance to resolve the issue.

[0116] Specifically, the intelligent system can maintain a mapping table between the scene tags corresponding to the problem and the contact information of the responsible technical personnel. By querying this mapping table, the contact information of the responsible technical personnel, such as email, account, or mobile phone number, can be obtained. Then, an alarm message is sent to the responsible technical personnel's email, account, or mobile phone number, so that the technical personnel can determine the solution to the problem by manually querying all log information related to the dialogue based on the dialogue identifier.

[0117] (9) Use an intelligent agent to generate a prompt message indicating that the problem is being solved; and send the prompt message back to the front end indicating that the problem is being solved; end.

[0118] It should be noted that steps (8) and (9) can be performed in any order. Specifically, step (9) can be performed before step (8), or steps (9) and (9) can be performed in parallel.

[0119] In this embodiment, steps (8) and (9) do not obtain the solution to the problem; they can be considered not as a specific implementation of step S403, but as a fallback solution. In actual application, after the technician solves the problem based on the alarm information in step (8), he can also update the knowledge base based on the problem and the solution to enhance the problem-solving capabilities of the knowledge base.

[0120] S404. Use an intelligent agent to obtain the solution to the problem based on the knowledge base; execute step S405.

[0121] In practical applications, the knowledge base can pre-store the mapping relationship between problems and solutions. In this case, the agent can directly search for the problem in the knowledge base and obtain the corresponding solution.

[0122] In another optional embodiment of this disclosure, the knowledge base may also pre-store the mapping relationship between questions and question location solutions. In this case, the specific implementation of step S404 may include the following steps:

[0123] (a) Use an intelligent agent to search for a problem location solution in the knowledge base; if a solution is found, proceed to step (b); if no solution is found, proceed to step (d).

[0124] (b) Using an intelligent agent, based on the problem localization scheme, obtain the problem localization field information from the information of the key fields; execute step (c);

[0125] (c) Using an intelligent agent, based on the information in the problem location field and the problem location scheme, obtain a solution and end.

[0126] In this embodiment, the pre-built knowledge base may also include questions and corresponding question localization solutions. This way, when searching for a question in the knowledge base, the corresponding question localization solution can be obtained. At this point, the agent can obtain a solution based on the question localization solution.

[0127] In one embodiment of this disclosure, step (c) can be implemented by first using an intelligent agent to locate the cause of the problem based on the information in the problem location field and a problem location scheme; then using an intelligent agent to generate a problem-solving suggestion based on the cause.

[0128] For example, in a video playback scenario, when a user reports a video stuttering issue, the agent can search for the problem in the knowledge base and obtain the following problem localization solution: Query network logs to determine if the network speed (key field: network_speed) is below 100kb / s. Then, the agent obtains the value of the key field `network_speed` from the key field information reported by the front end; and uses the problem localization solution to check if the value of the key field `network_speed` is below 100kb / s. If so, the cause of the problem is low network speed. Based on this cause, the agent can generate a problem-solving suggestion: The current network speed is low; you can change networks.

[0129] Optionally, in one embodiment of this disclosure, if an intelligent agent is used and the problem location scheme is based on the information of the key fields, the problem location field information is not obtained. In this case, the problem location cannot be performed. Alternatively, steps (8) and (9) in the above embodiment can be used to perform alarm and manual location.

[0130] (d) Using an intelligent agent, search the knowledge base for links to tools used to solve the problem autonomously, and then end.

[0131] Within the knowledge base, for certain specific problems, links to tools used for independent problem-solving can also be used as solutions.

[0132] For example, in a video playback scenario, for the problem of a video being blocked, the pre-stored solutions in the knowledge base could include: checking whether the video is a sensitive video; and / or being able to appeal using https: / / www.xxx.xxxx.

[0133] The corresponding solution at this point can include problem-solving suggestions, such as checking whether the video is sensitive, which can be done manually by the user. It can also include links to tools for self-resolved issues. Either type of information can be present, or both can be present simultaneously, allowing the user to check whether the video is sensitive. If the user believes it is not sensitive, they can further use the links to self-resolved issues to file an appeal.

[0134] Further optionally, in one embodiment of this disclosure, if after step (d), the agent also fails to find the tool link for autonomously solving the problem in the knowledge base, it can be considered that the agent cannot obtain the solution to the problem based on the knowledge base. Further, steps (8) and (9) above can also be executed.

[0135] Based on the above, it can be understood that the pre-built knowledge base in this embodiment may include the following types of information:

[0136] The first category is error codes and their corresponding error reasons. In this case, the agent can directly search for the error reason corresponding to the error code in the knowledge base, and generate a problem cause prompt or problem-solving suggestion based on the error reason.

[0137] The second category is problems and corresponding problem localization solutions. In this case, the agent can directly search for the corresponding problem localization solution in the knowledge base and generate problem-solving suggestions based on the problem localization solution.

[0138] The third category is problems and corresponding solutions. The solutions may include problem-solving suggestions and / or links to tools for self-resolved problems; for example, links to tools for self-resolved problems may refer to appeal links.

[0139] If the agent is unable to find a solution to the problem based on the three types of information in the knowledge base, it can generate a prompt message indicating that the problem is being resolved and send the prompt message back to the front end to inform the user. At the same time, it can also generate and issue an alarm message so that the responsible technical personnel can conduct a timely manual query to determine the solution to the problem.

[0140] S405, Feedback the solution to the front end.

[0141] Referring to the above description in this embodiment, when a solution cannot be obtained from the cloud, the above steps (8) and (9) are used to issue an alarm and request manual solution.

[0142] The problem-solving method in this embodiment, through edge-cloud collaboration, employs intelligent agents and references a pre-built knowledge base to process user problems, which can effectively shorten the time spent on problem-solving, improve the accuracy of problem-solving, and thus effectively improve problem-solving efficiency.

[0143] The problem-solving method in this embodiment can be based on a knowledge base, and by conducting detailed analysis of error codes, error causes, and error-reporting interfaces, it can seek solutions to problems, effectively improving the accuracy of solutions. Furthermore, in this embodiment, the cloud can ultimately provide feedback to the front end with solutions or prompts indicating that the problem is being resolved, resulting in comprehensive and accurate feedback information.

[0144] Based on the description of the above embodiments, it can be seen that in this embodiment, the solutions fed back from the cloud to the front end may include at least one of the following: problem cause prompts, problem-solving suggestions, and links to tools for self-solving. The types of problem solutions provided are very comprehensive and rich, which can more effectively improve the accuracy of problem handling.

[0145] The problem-handling method disclosed herein allows users to trigger its execution simply by selecting the function trigger button after receiving a confirmation message on the front end. This makes the user's feedback behavior a "one-click" operation, which can greatly increase the user's willingness to report problems.

[0146] The problem-solving method disclosed herein can handle problems through edge-cloud collaboration. Experimental verification shows that it can push solutions to users within seconds, achieving near real-time problem solutions, and is highly practical.

[0147] Figure 5 This is a schematic diagram according to the fifth embodiment of the present disclosure; the front end 500 provided in this embodiment may specifically include:

[0148] Information acquisition module 501 is used to acquire the scene tag and target timestamp corresponding to the question input by the user; the target timestamp is used to identify the time when the question occurred;

[0149] The log acquisition module 502 is used to acquire multiple corresponding logs based on the scene tag and the target timestamp;

[0150] The field extraction module 503 is used to extract information about key fields from the multiple logs based on a preset list of key fields.

[0151] The reporting module 504 is used to report the problem and the information of the key fields to the cloud so that the cloud can process the problem based on the information of the problem and the key fields.

[0152] The front-end 500 in this embodiment achieves the same implementation principle and technical effect of problem handling by using the above-mentioned modules. For details, please refer to the description of the above-mentioned related method embodiments, which will not be repeated here.

[0153] Further, optionally, in one embodiment of this disclosure, the problem-solving apparatus 500 further includes:

[0154] The receiving module is used to receive solutions or prompts indicating that problems are being resolved from the cloud.

[0155] Further optionally, in one embodiment of this disclosure, the solution includes at least one of the following: a problem cause prompt, a problem-solving suggestion, and a link to tools for independently resolving the problem.

[0156] Further optionally, in one embodiment of this disclosure, the information acquisition module 501 is used for:

[0157] Based on a preset detection strategy, obtain the scene tag and target timestamp corresponding to the user's question.

[0158] Further optionally, in one embodiment of this disclosure, the information acquisition module 501 is used for:

[0159] Obtain the question input by the user; and send the question to the cloud;

[0160] Receive and display the function activation confirmation message sent by the cloud, which is triggered when the cloud receives the question sent by the front end; the function activation confirmation message is used to prompt the user to solve the problem through deep thinking.

[0161] Intercept the user's confirmation message based on the function, and trigger a link through the function selected by the human-machine interface module;

[0162] Obtain the scene tag and the target timestamp from the function trigger link.

[0163] The front-end 500 in the above embodiment achieves the same implementation principle and technical effect of problem handling by using the above module, which is the same as the implementation principle of the above related methods. For details, please refer to the description of the above related method embodiments, which will not be repeated here.

[0164] Figure 6 This is a schematic diagram according to the sixth embodiment of this disclosure; the cloud 600 provided in this embodiment may specifically include:

[0165] The receiving module 601 is used to receive the problem reported by the front end and the information of key fields; the information of key fields is obtained by the front end based on the scene tag and target timestamp corresponding to the user's problem, and extracted from the multiple logs based on a preset list of key fields;

[0166] Solution acquisition module 602 is used to acquire a solution based on the problem and the information of the key fields;

[0167] Feedback module 603 is used to provide feedback on the solution to the front end.

[0168] The cloud-based 600 in this embodiment achieves the same implementation principle and technical effect as the above-mentioned related methods by using the above-mentioned modules. For details, please refer to the description of the above-mentioned related method embodiments, which will not be repeated here.

[0169] Further optionally, in one embodiment of this disclosure, the solution acquisition module 602 is used to employ an intelligent agent to acquire the solution based on a pre-built knowledge base, the problem, and information from the key fields.

[0170] Further optionally, in one embodiment of this disclosure, the scheme acquisition module 602 is used for:

[0171] The intelligent agent is used to detect whether the information in the key field includes an error code;

[0172] When the key field does not include an error code, the agent retrieves the solution corresponding to the problem based on the knowledge base.

[0173] Further optionally, in one embodiment of this disclosure, the scheme acquisition module 602 is used for:

[0174] The intelligent agent is used to search for a problem localization solution corresponding to the problem in the knowledge base.

[0175] Using the aforementioned intelligent agent, based on the aforementioned problem localization scheme, information about the problem localization field is obtained from the information of the key fields;

[0176] Using the intelligent agent, the solution is obtained based on the information in the problem location field and the problem location scheme.

[0177] Further optionally, in one embodiment of this disclosure, the scheme acquisition module 602 is used for:

[0178] Using the aforementioned intelligent agent, based on the information in the problem location field, and employing the aforementioned problem location scheme, the cause of the problem is located;

[0179] Using the aforementioned intelligent agent, problem-solving suggestions are generated based on the stated reasons.

[0180] Further optionally, in one embodiment of this disclosure, the scheme acquisition module 602 is used for:

[0181] The intelligent agent is used to search the knowledge base for tool links for autonomously solving the problem.

[0182] Further optionally, in one embodiment of this disclosure, the scheme acquisition module 602 is used for:

[0183] In response to an error code, the agent uses the error code and the knowledge base to obtain the solution corresponding to the problem.

[0184] Further optionally, in one embodiment of this disclosure, the scheme acquisition module 602 is used for:

[0185] The intelligent agent is used to detect whether the knowledge base includes the error reason corresponding to the error code;

[0186] In response to the knowledge base including the error reason corresponding to the error code, the agent is used to obtain the error reason corresponding to the error code from the knowledge base;

[0187] Using the aforementioned intelligent agent, based on the cause of the error, a problem cause prompt or problem-solving suggestion is generated.

[0188] Further optionally, in one embodiment of this disclosure, the scheme acquisition module 602 is also used for:

[0189] When the knowledge base does not include the error reason corresponding to the error code, the agent is used to detect whether the information of the key field includes the error reporting interface corresponding to the error code.

[0190] In response to the information in the key field including the error reporting interface corresponding to the error code, the intelligent agent is used to obtain the log of the error reporting interface;

[0191] Using the aforementioned intelligent agent, the cause of the error is located based on the logs of the error reporting interface;

[0192] Using the aforementioned intelligent agent, problem-solving suggestions are generated based on the error message.

[0193] Further optionally, in one embodiment of this disclosure, the scheme acquisition module 602 is also used for:

[0194] Using the aforementioned intelligent agent, logs of downstream interfaces of the error reporting interface are obtained based on the logs of the error reporting interface;

[0195] Using the aforementioned intelligent agent, the cause of the error is located based on the logs of the error reporting interface and the logs of the downstream interface.

[0196] Further optionally, in one embodiment of this disclosure, the scheme acquisition module 602 is also used for:

[0197] When the information in the key field does not include the error reporting interface corresponding to the error code, the agent generates an alarm message, which carries a dialogue identifier corresponding to the problem; issues the alarm message; and / or

[0198] The intelligent agent generates a prompt message indicating that the problem is being resolved and then feeds back the prompt message to the front end.

[0199] The cloud-based 600 in the above embodiments achieves the same implementation principle and technical effect of problem handling by using the above modules. For details, please refer to the description of the above-mentioned related method embodiments, which will not be repeated here.

[0200] Figure 7 This is a schematic diagram according to the seventh embodiment of the present disclosure; this embodiment provides a problem handling system 700, including a front-end 701 and a cloud 702, wherein the front-end 701 and the cloud 702 are communicatively connected; the front-end 701 and the cloud 702 cooperate to achieve problem handling; the front-end 701 can specifically adopt the above-described... Figure 5 The front-end of the embodiment shown; the cloud 702 can specifically adopt the above. Figure 6 The cloud-based implementation shown in the example can specifically adopt the methods described above. Figures 1-4 The problem-solving method in the illustrated embodiment is based on edge-cloud collaboration. For details, please refer to the description of the above-mentioned related embodiments, which will not be repeated here.

[0201] The acquisition, storage, and application 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.

[0202] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0203] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, 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.

[0204] like Figure 8 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0205] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0206] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose 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 801 performs the various methods and processes described above, such as the methods of this disclosure. For example, in some embodiments, the methods of this disclosure may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the methods of this disclosure described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the methods of this disclosure by any other suitable means (e.g., by means of firmware).

[0207] 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), application-specific integrated circuits (ASICs), application-specific 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 dedicated 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.

[0208] 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 a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing 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.

[0209] 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.

[0210] 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).

[0211] 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.

[0212] A computer system may include a front-end and a server. The front-end and server are generally geographically separated and typically interact via a communication network. The front-end and server relationship is created by computer programs running on the respective computers and having a front-end-server relationship with each other. The server can be a cloud server, a server in a distributed system, or a server incorporating blockchain technology.

[0213] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in 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.

[0214] 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-solving method, comprising: Obtain the scene tag and target timestamp corresponding to the user's input question; The target timestamp is used to identify the time when the problem occurred; Based on the scene tag and the target timestamp, obtain the corresponding multiple log entries; Based on a preset list of key fields, information about the key fields is extracted from the multiple log entries. The problem and the information of the key fields are reported to the cloud so that the cloud can process the problem based on the information of the problem and the key fields.

2. The method according to claim 1, wherein, After reporting the problem and the key field information to the cloud so that the cloud can process the problem based on the problem and the key field information, the method further includes: Receive solutions or prompts from the cloud indicating that the problem is being resolved.

3. The method according to claim 1, wherein, The solution includes at least one of the following: problem cause prompts, problem-solving suggestions, and links to tools for self-resolved problem-solving.

4. The method according to claim 1, wherein, The acquisition of the user's question, corresponding to the scenario tag and target timestamp, includes: Based on a preset detection strategy, obtain the scene tag and target timestamp corresponding to the user's question.

5. The method according to claim 1, wherein, The acquisition of the user's question, corresponding to the scenario tag and target timestamp, includes: Obtain the question input by the user; and send the question to the cloud; Receive and display the function activation confirmation message sent by the cloud, which is triggered when the cloud receives the question sent by the front end; the function activation confirmation message is used to prompt the user to solve the problem through deep thinking. Intercept the user's confirmation message based on the function, and trigger a link through the function selected by the human-machine interface module; Obtain the scene tag and the target timestamp from the function trigger link.

6. A problem-solving method, comprising: Receive issues and key field information reported from the front end; The key field information is obtained by the front end based on the scenario tag and target timestamp corresponding to the user's question, and extracted from the multiple logs based on a preset key field list; Based on the problem and the information in the key fields, a solution is obtained; The solution is fed back to the front end.

7. The method according to claim 6, wherein, The process of obtaining a solution based on the problem and the information in the key fields includes: An intelligent agent is employed to obtain the solution based on a pre-built knowledge base, the problem, and information from the key fields.

8. The method according to claim 7, wherein, The method employs an intelligent agent to obtain the solution based on a pre-built knowledge base, the problem, and information from the key fields, including: The intelligent agent is used to detect whether the information in the key field includes an error code; When the key field does not include an error code, the agent retrieves the solution corresponding to the problem based on the knowledge base.

9. The method according to claim 8, wherein, The step of using the intelligent agent to obtain the solution corresponding to the problem based on the knowledge base includes: The intelligent agent is used to search for a problem localization solution corresponding to the problem in the knowledge base. Using the aforementioned intelligent agent, based on the aforementioned problem localization scheme, information about the problem localization field is obtained from the information of the key fields; Using the intelligent agent, the solution is obtained based on the information in the problem location field and the problem location scheme.

10. The method according to claim 9, wherein, The step of using the intelligent agent to obtain the solution based on the information in the problem location field and the problem location scheme includes: Using the aforementioned intelligent agent, based on the information in the problem location field, and employing the aforementioned problem location scheme, the cause of the problem is located; Using the aforementioned intelligent agent, problem-solving suggestions are generated based on the stated reasons.

11. The method according to claim 8, wherein, The step of using the intelligent agent to obtain the solution corresponding to the problem based on the knowledge base includes: The intelligent agent is used to search the knowledge base for tool links for autonomously solving the problem.

12. The method according to claim 8, wherein, The method further includes: In response to an error code, the agent uses the error code and the knowledge base to obtain the solution corresponding to the problem.

13. The method according to claim 12, wherein, The step of using the intelligent agent to obtain the solution corresponding to the problem based on the error code and the knowledge base includes: The intelligent agent is used to detect whether the knowledge base includes the error reason corresponding to the error code; In response to the knowledge base including the error reason corresponding to the error code, the agent is used to obtain the error reason corresponding to the error code from the knowledge base; Using the aforementioned intelligent agent, based on the cause of the error, a problem cause prompt or problem-solving suggestion is generated.

14. The method according to claim 13, wherein, The method further includes: When the knowledge base does not include the error reason corresponding to the error code, the agent is used to detect whether the information of the key field includes the error reporting interface corresponding to the error code. In response to the information in the key field including the error reporting interface corresponding to the error code, the intelligent agent is used to obtain the log of the error reporting interface; Using the aforementioned intelligent agent, the cause of the error is located based on the logs of the error reporting interface; Using the aforementioned intelligent agent, problem-solving suggestions are generated based on the error message.

15. The method according to claim 14, wherein, The step of using the intelligent agent to locate the cause of the error based on the logs of the error reporting interface includes: Using the aforementioned intelligent agent, logs of downstream interfaces of the error reporting interface are obtained based on the logs of the error reporting interface; Using the aforementioned intelligent agent, the cause of the error is located based on the logs of the error reporting interface and the logs of the downstream interface.

16. The method of claim 14, wherein, The method further includes: When the information in the key field does not include the error reporting interface corresponding to the error code, the agent generates an alarm message, which carries a dialogue identifier corresponding to the problem; issues the alarm message; and / or The intelligent agent generates a prompt message indicating that the problem is being resolved and then feeds back the prompt message to the front end.

17. A front-end, comprising: The information acquisition module is used to acquire the scene tag and target timestamp corresponding to the question input by the user; The target timestamp is used to identify the time when the problem occurred; The log acquisition module is used to acquire multiple corresponding logs based on the scene tag and the target timestamp; The field extraction module is used to extract information about key fields from the multiple logs based on a preset list of key fields. The reporting module is used to report the problem and the information of the key fields to the cloud, so that the cloud can process the problem based on the information of the problem and the key fields.

18. A cloud computing platform, comprising: The receiving module is used to receive issues and key field information reported by the front end. The key field information is obtained by the front end based on the scenario tag and target timestamp corresponding to the user's question, and extracted from the multiple logs based on a preset key field list; The solution acquisition module is used to acquire a solution based on the problem and the information in the key fields. The feedback module is used to provide feedback on the solution to the front end.

19. A problem-solving system, comprising a front-end and a cloud, wherein the front-end is communicatively connected to the cloud; the front-end and the cloud collaborate to perform problem-solving; the front-end is the front-end as described in claim 17; and the cloud is the cloud as described in claim 18.

20. An electronic device, characterized in that, include: 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 according to any one of claims 1-16.

21. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-16.

22. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-16.

Images