Problem checking method and device, electronic equipment and computer readable storage medium

Abstract

The invention relates to the technical field of problem investigation, and provides a problem investigation method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: obtaining operation problem information; extracting user information and scene information from the operation problem information; analyzing and processing the scene information to obtain problem type information; under the condition that the question type information is represented as a newly added question, performing association from a preset question knowledge base to obtain similar question information; carrying out fusion processing on the similar problem information and the user information to obtain overall problem key information; selecting corresponding solution information from a question knowledge base according to the overall question key information; and performing verification processing on the solution information to obtain a problem checking result. According to the technical scheme, the problem checking process can be simplified, and the problem checking efficiency is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to, but are not limited to, the field of problem troubleshooting, and in particular, to a problem troubleshooting method, apparatus, electronic device, and computer-readable storage medium. Background Art

[0002] In the fields of insurance business or intelligent healthcare, intelligent systems are generally used to handle daily operations at present. However, various problems inevitably occur during the operation of the system. These problems may involve multiple links and may also occur at any node, making it difficult to quickly locate them. Moreover, the problems may be concealed and only present under specific conditions. Due to the diversity of system problems, during subsequent problem troubleshooting, it is often necessary for the troubleshooting personnel to troubleshoot the problems one by one based on their past experience and divide the responsibilities for related problems. This will result in a more complicated process for system problem troubleshooting and lack simplicity and speed. Summary of the Invention

[0003] The following is an overview of the subject matter described in detail in this article. This overview is not intended to limit the scope of protection of the claims.

[0004] To solve the problems mentioned in the above background art, the embodiments of the present application provide a problem troubleshooting method, apparatus, electronic device, and computer-readable storage medium, which can simplify the process of problem troubleshooting and improve the efficiency of problem troubleshooting.

[0005] In a first aspect, the embodiments of the present application provide a problem troubleshooting method, including:

[0006] Obtain operation problem information;

[0007] Extract user information and scenario information from the operation problem information;

[0008] Analyze and process the scenario information to obtain problem type information;

[0009] In the case where the problem type information represents a new problem, associate similar problem information from a preset problem knowledge base; and fuse the similar problem information and the user information to obtain overall problem key information;

[0010] Select corresponding solution information from the problem knowledge base according to the overall problem key information;

[0011] Verify the solution information to obtain a problem troubleshooting result.

[0012] In a second aspect, the embodiments of the present application further provide a problem troubleshooting apparatus, including:

[0013] An acquisition unit for acquiring operation problem information;

[0014] An extraction unit for extracting user information and scenario information from the operation problem information;

[0015] An analysis unit for analyzing and processing the scenario information to obtain problem type information;

[0016] An execution unit for, when the problem type information represents a new problem, associating similar problem information from a preset problem knowledge base; and performing fusion processing on the similar problem information and the user information to obtain overall problem key information;

[0017] A selection unit for selecting corresponding solution information from the problem knowledge base according to the overall problem key information;

[0018] A verification unit for performing verification processing on the solution information to obtain a problem troubleshooting result.

[0019] In a third aspect, an embodiment of the present application further provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, the problem troubleshooting method described in the first aspect above is implemented.

[0020] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium storing computer-executable instructions for executing the problem troubleshooting method described in the first aspect above.

[0021] According to the problem troubleshooting method provided by the embodiments of the present application, it has at least the following beneficial effects: In the process of problem troubleshooting, first, operation problem information is acquired; then, user information and scenario information are extracted from the operation problem information; then, the scenario information is analyzed and processed to obtain problem type information; then, when the problem type information represents a new problem, similar problem information is associated from a preset problem knowledge base; and the similar problem information and the user information are fused to obtain overall problem key information; then, corresponding solution information is selected from the problem knowledge base according to the overall problem key information; finally, the solution information is verified to obtain a problem troubleshooting result. Through the above technical solution, when the problem type information represents a new problem, similar problem information is associated from a preset problem knowledge base; and the similar problem information and the user information are fused to obtain overall problem key information; then, corresponding solution information is selected from the problem knowledge base according to the overall problem key information, and there is no need for manual problem troubleshooting, which can simplify the process of problem troubleshooting and improve the efficiency of problem troubleshooting. Description of the Drawings

[0022] The accompanying drawings are used to provide a further understanding of the technical solution of the present application, and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application, and do not constitute a limitation to the technical solution of the present application.

[0023] Figure 1 is a schematic flowchart of a problem troubleshooting method provided by an embodiment of the present application;

[0024] Figure 2 is Figure 1 a schematic flowchart of a specific implementation manner of step S200 in

[0025] Figure 3 is Figure 1 a schematic flowchart of a specific implementation manner of step S300 in

[0026] Figure 4 is Figure 1 a schematic flowchart of a specific implementation manner of step S400 in

[0027] Figure 5 is Figure 1 a schematic flowchart of another specific implementation manner of step S400 in

[0028] Figure 6 is Figure 1 a schematic flowchart of a specific implementation manner of step S500 in

[0029] Figure 7 is Figure 1 a schematic flowchart of a specific implementation manner of step S600 in

[0030] Figure 8 is a schematic diagram of a problem troubleshooting device provided by an embodiment of the present application;

[0031] Figure 9 is a schematic diagram of an electronic device provided by an embodiment of the present application. Specific Embodiments

[0032] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0033] It should be noted that although the functional modules are divided in the device schematic diagram and the logical sequence is shown in the flowchart, in some cases, the steps shown or described can be executed in a different module division from that in the device or a different sequence from that in the flowchart. Terms such as "first" and "second" in the specification, claims, and the above-mentioned drawings are used to distinguish similar objects and do not necessarily describe a specific order or sequence.

[0034] It should be noted that unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0035] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0036] AI is a new technical science that studies, develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence; artificial intelligence is a branch of computer science. Artificial intelligence attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a way similar to human intelligence. The research in this field includes robots, speech recognition, image recognition, natural language processing, and expert systems, etc. Artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is also the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0037] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0038] Artificial intelligence is AI. AI is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0039] The server involved in artificial intelligence technology can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), as well as big data and artificial intelligence platforms.

[0040] This application provides a problem troubleshooting method, device, electronic device, and computer-readable storage medium. During the process of problem troubleshooting, first, obtain operation problem information; then extract user information and scenario information from the operation problem information; then analyze and process the scenario information to obtain problem type information; then, when the problem type information represents a new problem, associate similar problem information from a pre-set problem knowledge base; and fuse the similar problem information and user information to obtain the key information of the overall problem; then select the corresponding solution information from the problem knowledge base according to the key information of the overall problem; finally, verify the solution information to obtain the problem troubleshooting result. Through the above technical solution, when the problem type information represents a new problem, associate similar problem information from a pre-set problem knowledge base; and fuse the similar problem information and user information to obtain the key information of the overall problem; then select the corresponding solution information from the problem knowledge base according to the key information of the overall problem, without the need for manual problem troubleshooting, which can simplify the process of problem troubleshooting and improve the efficiency of problem troubleshooting.

[0041] The problem troubleshooting method provided by the embodiments of this application relates to the field of problem troubleshooting. The problem troubleshooting method provided by the embodiments of this application can be applied to terminals, can also be applied to the server side, or can be software running on the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, can also be configured as a server cluster or distributed system composed of multiple physical servers, or can be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, as well as big data and artificial intelligence platforms.

[0042] This application can be used in numerous general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0043] It should be noted that in each specific embodiment of this application, when it comes to relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first. Moreover, the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when this application embodiment needs to obtain the user's sensitive personal information, the user's separate permission or separate consent will be obtained through methods such as pop-up windows or redirecting to a confirmation page. After clearly obtaining the user's separate permission or separate consent, the necessary user-related data for the normal operation of this application embodiment will be obtained.

[0044] The following further elaborates on the embodiments of this application in conjunction with the accompanying drawings.

[0045] As Figure 1 shown, Figure 1 is a flowchart of a problem troubleshooting method provided by an embodiment of this application. The problem troubleshooting method includes the following steps:

[0046] Step S100: Obtain operation problem information.

[0047] In the problem troubleshooting method provided by the embodiment of this application, during the process of troubleshooting problems, operation problem information generated during the system operation is first obtained; exemplarily, for a property insurance business system, when a user purchases insurance, there may be a situation where online payment fails, and corresponding operation problem information will be generated; for an old-age insurance business system, when a user selects an old-age insurance plan, there may be a problem that the plan selection fails, and corresponding operation problem information will also be generated; in a smart healthcare system, when a patient registers using the system and finds that the registration information is not synchronized and updated according to the time node, corresponding operation problem information will also be generated.

[0048] It should be noted that the operation problem information in the embodiments of the present application is the abnormal failure information generated during the operation of the system; these operation problem information may be caused by human operation errors, may also be triggered by loopholes existing in the system, may also be caused by the limited processing capacity of the system, or may be caused by the system being attacked by an external network.

[0049] Step S200: Extract user information and scenario information from the operation problem information.

[0050] In the problem troubleshooting method provided by the embodiments of the present application, during the process of problem troubleshooting, after obtaining the operation problem information, user information and scenario information can be extracted from the operation problem information; among them, the user information is the registration information of the user on the system, and the user needs to use the previous registration information when logging in to the system; for example, when the user logs in to the property insurance business system, the user needs to perform a registration process on the property insurance business system, and then can log in to the property insurance business system according to the registration information. The scenario information is the information about what business operations the user uses the system to perform. For example, in the intelligent medical system, patients can use the system to perform online appointment registration, and patients can also use the system to perform online inspection payment. System operation and maintenance personnel can also modify the inspection item prices on the system. In the vehicle insurance system, users can log in to the system to perform vehicle insurance renewal services, users can also log in to the system to receive fuel coupons, and users can also perform online fuel payment through the vehicle insurance system. In the endowment insurance business system, users can log in to the system to perform endowment insurance payment, and users can also log in to the system to query endowment insurance business. In the property insurance business system, users can log in to the system to perform insurance reimbursement, and users can also log in to the system to query the details of insurance types, etc.

[0051] It should be noted that extracting user information and scenario information from the obtained operation problem information prepares the premise for subsequent problem troubleshooting. Extracting user information and scenario information from the operation problems makes the subsequent problem troubleshooting more accurate.

[0052] As Figure 2 shown, extracting user information and scenario information from the operation problem information may include the following steps:

[0053] Step S210, perform information splitting processing on the operation problem information to obtain multiple information blocks;

[0054] Step S220, perform keyword recognition processing on all information blocks to obtain multiple keyword information;

[0055] Step S230: Match and obtain user information and scenario information from multiple keyword information according to preset problem keywords.

[0056] For steps S210 to S230, in the process of extracting user information and scenario information from operation problem information, first perform information splitting processing on the operation problem information to obtain multiple information blocks; then perform keyword recognition processing on all information blocks to obtain multiple keyword information; finally, match and obtain user information and scenario information from multiple keyword information according to the preset problem keywords. Through the above technical solution, user information and scenario information can be obtained from multiple keyword information, preparing for subsequent problem troubleshooting.

[0057] It should be noted that in the process of extracting user information and scenario information from operation problem information, first perform information splitting processing on the operation problem information to obtain multiple information blocks; then perform keyword recognition processing on each information block to identify the keyword information in each information block; finally, match and obtain the corresponding user information and scenario information from multiple keyword information according to the preset problem keywords. Exemplarily, in the field of insurance business, the preset problem keywords can be "user", "account", "number", "query", "purchase", "payment", etc. Finally, the corresponding user information can be matched from multiple keyword information according to "account", and the corresponding scenario information can also be matched from multiple keyword information according to "payment".

[0058] Step S300: Analyze and process the scenario information to obtain problem type information.

[0059] For the problem troubleshooting method provided by the embodiments of the present application, after extracting user information and scenario information from operation problem information, the pre-trained large model can be used to analyze and process the scenario information, and then the corresponding problem type information can be obtained; through the above technical solution, the determination of problem type information can be more accurate and fast.

[0060] It should be noted that based on the large model, the scenario information can be analyzed and processed to obtain problem type information. Through the above technical solution, the analysis and processing of scenario information can be well accelerated, and then the analysis efficiency of scenario information can be accelerated, and the confirmation process of problem type information can be accelerated. The whole process can be more simple and fast.

[0061] As Figure 3 shown, analyzing and processing the scenario information to obtain problem type information may include the following steps:

[0062] Step S310: Perform feature extraction processing on the scene information to obtain scene feature information;

[0063] Step S320: Identify scene marker information from the scene feature information;

[0064] Step S330: Match the scene marker information with a preset scene problem marker library to obtain problem type information.

[0065] For steps S310 to S330, in the process of analyzing the scene information to obtain the problem type information, first, performing feature extraction processing on the scene information can obtain the scene feature information; then, identifying the scene marker information from the scene feature information; and then, the scene marker information can be matched with the preset scene problem marker library to obtain the problem type information; through the above technical solution, the determination of the problem type information can be more accurate and rapid.

[0066] It should be noted that, in the process of analyzing the scene information to obtain the problem type information, first, the feature extraction module in the large model can be used to perform feature extraction processing on the scene information to obtain the scene feature information; then, the recognition module in the large model can be used to identify the scene marker information from the scene feature information; finally, the matching module in the large model can be used to match the scene marker information with the preset scene problem marker library to obtain the corresponding problem type information.

[0067] It should be noted that the scene problem marker library includes multiple scene marker information, and each scene marker information corresponds to a problem type information. Therefore, after identifying the scene marker information from the scene feature information, the scene marker information can be matched with the preset scene problem marker library to obtain the corresponding problem type information, making the determination of the problem type information more accurate and rapid.

[0068] Step S400: In the case where the problem type information is characterized as a new problem, associate similar problem information from a preset problem knowledge base; and fuse the similar problem information and user information to obtain overall problem key information.

[0069] For the problem troubleshooting method provided in the embodiments of the present application, after obtaining the problem type information, in the case where the problem type information is characterized as a new problem, similar problem information can be associated from the preset problem knowledge base; then, fusing the similar problem information and user information can obtain the overall problem key information; to prepare for the subsequent selection of solution information.

[0070] It should be noted that when the problem type information represents a new problem, that is, the problem does not exist in the pre-set problem knowledge base, it is necessary to associate and obtain similar problem information from the pre-set problem knowledge base; however, in the case where the problem type information represents a non-new problem, the corresponding problem information can be directly matched from the problem knowledge base, and the corresponding solution information can be directly selected, and the entire process of selecting the solution can be more simple and fast, providing the corresponding solution information for the corresponding user. Exemplarily, for the property insurance business system, when a user encounters a payment failure problem during the process of purchasing insurance using the property insurance business system and needs to make an online payment, corresponding operation problem information can be formed; then user information and scenario information can be extracted from the operation problem information; then the large model can be used to analyze and process the scenario information to obtain the problem type information; in the case where the problem type information represents a previously occurred problem, the corresponding problem information and the corresponding solution information can be directly matched from the problem knowledge base to remind the user how to handle the online payment failure during the process of purchasing insurance, and the entire process is safe and reliable.

[0071] It should be noted that the problem knowledge base in the embodiments of the present application includes multiple problem information and multiple solution information; in the case where the problem type information represents a new problem, the most similar problem information with the highest similarity can be associated from the existing problem information in the problem knowledge base to prepare for selecting the subsequent solution information. Exemplarily, for the intelligent medical system, when a user encounters an unresponsive situation during the process of querying and processing inpatient services using the system, corresponding operation problem information will also be formed; then user information and scenario information can also be extracted from the operation problem information; then the scenario information can be analyzed and processed to obtain the problem type information; in the case where the problem type information represents a new problem, it is necessary to associate and obtain similar problem information from the pre-set problem knowledge base to prepare for selecting the subsequent solution information.

[0072] In an embodiment of the present application, when the problem type information represents a new problem, similar problem information can be associated from a pre-set problem knowledge base; subsequently, the similar problem information and user information can be fused to obtain the corresponding overall problem key information, preparing for the selection of subsequent solution information. Among them, fusing the similar problem information and user information to obtain the overall problem key information combines the similar problem information with the user information, making the selection of subsequent solution information more accurate, because for the same similar problem information, different solution information can be obtained by combining different user information; for example, in an insurance business system, when a system maintenance personnel makes an error during the online payment test, the system maintenance personnel can be reminded to re-test the relevant data interfaces; while when an ordinary user makes an error during the online payment, the user can be reminded to log out and re-perform the payment operation.

[0073] As Figure 4 shown, when the problem type information represents a new problem, associating similar problem information from a pre-set problem knowledge base may include the following steps:

[0074] Step S410, when the problem type information represents a new problem, preprocess the problem type information to obtain preprocessing type information;

[0075] Step S420, perform a similarity speculation process on the preprocessing type information to obtain similarity type information;

[0076] Step S430, perform a similarity matching process on the similarity type information and each problem information in the problem knowledge base to obtain multiple matching degree values, where each matching degree value corresponds to a problem information;

[0077] Step S440, use the problem information corresponding to the maximum value among the multiple matching degree values as the similar problem information.

[0078] For steps S410 to S440, in the process of associating similar problem information from a pre-set problem knowledge base when the problem type information represents a new problem, first preprocess the problem type information to obtain preprocessing type information; then perform a similarity speculation process on the preprocessing type information to obtain similarity type information; then perform a similarity matching process on the similarity type information and each problem information in the problem knowledge base to obtain multiple matching degree values, where each matching degree value corresponds to a problem information; finally, the problem information corresponding to the maximum value among the multiple matching degree values can be used as the similar problem information. Through the above technical solution, similar problem information can be quickly and accurately matched, making the determination of similar problem information more accurate.

[0079] It should be noted that in the process of associating similar problem information, first, the problem type information is preprocessed, that is, the irrelevant information in the problem type information is filtered to obtain the preprocessed type information; then, the similarity speculation process is performed on the preprocessed type information to obtain the similarity type information; then, subsequently, the similarity type information can be matched with each problem information in the problem knowledge base to obtain multiple matching degree values. Among them, each matching degree value corresponds to a problem information; among them, the similarity matching process can include, but is not limited to, the cosine similarity matching method, the Euclidean distance method, etc. After obtaining multiple matching degree values, the problem information corresponding to the maximum value in the matching degree values can be used as the similar problem information, so as to make the association of the similar problem information more accurate. Exemplarily, for the intelligent medical system, when the user fails to query the doctor's on-duty time using the system and this problem is not recorded in the preset problem knowledge base, the problem type information will be characterized as a new problem. Then, the problem type information can be preprocessed to obtain the preprocessed type information; then, the similarity speculation process is performed on the obtained preprocessed type information to obtain the similarity type information; then, the similarity type information is matched with each problem information in the problem knowledge base to obtain multiple matching degree values, and each matching degree value corresponds to a problem information; finally, the problem information corresponding to the maximum value among the multiple matching degree values can be used as the corresponding similar problem information.

[0080] As Figure 5 shown, the process of fusing the similar problem information and the user information to obtain the overall problem key information can include the following steps:

[0081] Step S450, format the similar problem information and the user information respectively to obtain the organized problem information corresponding to the similar problem information and the organized user information corresponding to the user information;

[0082] Step S460, extract the features of the organized problem information and the organized user information respectively to obtain the problem key features corresponding to the organized problem information and the user key features corresponding to the organized user information;

[0083] Step S470, perform weighted fusion processing on the problem key features and the user key features to obtain the overall problem key information.

[0084] For steps S450 to S470, in the process of fusing similar problem information and user information to obtain the key information of the overall problem, first format the similar problem information and user information respectively to obtain the organized problem information corresponding to the similar problem information and the organized user information corresponding to the user information; then extract features from the organized problem information and the organized user information respectively to obtain the key problem features corresponding to the organized problem information and the key user features corresponding to the organized user information; finally, perform weighted fusion processing on the key problem features and the key user features to obtain the corresponding key information of the overall problem. After obtaining the key information of the overall problem, it is possible to prepare for selecting the corresponding solution information from the problem knowledge base according to the key information of the overall problem, so that the subsequent selection of solution information can be more accurate.

[0085] It should be noted that by formatting the similar problem information and user information, the organized problem information and the organized user information can be obtained, preparing for subsequent feature extraction; then features can be extracted from the organized problem information and the organized user information to obtain the key problem features and the key user features, preparing for subsequent information fusion. Finally, weighted fusion processing is performed on the key problem features and the key user features to obtain the corresponding key information of the overall problem, preparing for subsequent selection of solution information.

[0086] Step S500: Select the corresponding solution information from the problem knowledge base according to the key information of the overall problem.

[0087] For the problem troubleshooting method provided by the embodiments of the present application, after fusing similar problem information and user information to obtain the key information of the overall problem, the corresponding solution information can be selected from the problem knowledge base according to the key information of the overall problem, providing a solution for the troubleshooting of operation problem information. Exemplarily, in a vehicle insurance business system, when a user encounters an order anomaly during the process of renewing vehicle insurance, corresponding operation problem information will be generated; then the information of the purchaser and the scenario information of vehicle insurance renewal are extracted from the operation problem information; then the scenario information of vehicle insurance renewal is analyzed and processed to obtain the problem type information; then when the problem type information is characterized as a new problem, similar problem information can be associated from a pre-set problem knowledge base; and the similar problem information and user information are fused to obtain the key information of the overall problem; then the corresponding solution information can be selected from the problem knowledge base according to the key information of the overall problem, and finally the user can correct the order anomaly that occurred during the vehicle insurance renewal process according to the solution information.

[0088] It should be noted that there are multiple solution information in the problem knowledge base. During the process of selecting the corresponding solution information, the corresponding solution information can be selected from the problem knowledge base according to the key information of the overall problem, so that the selection of the solution information can be more accurate.

[0089] As Figure 6 shown, the problem knowledge base includes the original problem information and the original solution information corresponding to the original problem information. Selecting the corresponding solution information from the problem knowledge base according to the key information of the overall problem may include the following steps:

[0090] Step S510: Match the key information of the overall problem with the original problem information to determine the target original problem information;

[0091] Step S520: Determine the original solution information corresponding to the target original problem information as the solution information.

[0092] For steps S510 to S520, during the process of selecting the corresponding solution information from the problem knowledge base according to the key information of the overall problem, the target original problem information can be determined by first matching the key information of the overall problem with the original problem information; then the original solution information corresponding to the target original problem information can be determined as the solution information. Through the above technical solution, the determination of the solution information can be more accurate and fast.

[0093] It should be noted that the problem knowledge base includes the original problem information and the original solution information corresponding to the original problem information. By matching the key information of the overall problem with the original problem information, the corresponding target original problem information can be determined from the problem knowledge base; since each original problem information corresponds to an original solution information, the original solution information corresponding to the target original problem information can be determined as the solution information, so that the determination of the solution information can be more simple and fast.

[0094] Step S600: Verify the solution information to obtain the problem troubleshooting result.

[0095] The problem troubleshooting method provided by the embodiments of the present application can, after selecting the corresponding solution information from the problem knowledge base according to the key information of the overall problem, perform verification processing on the solution information, and use the final solution verification result as the problem troubleshooting result to determine the accuracy of problem troubleshooting. Exemplarily, in a smart healthcare system, when people encounter a query failure during the process of using the smart healthcare system to query hospitalization bills, corresponding operation problem information will be generated. Subsequently, the analyzed solution information corresponding to this operation problem information is to suggest that the user query again after a 5-minute interval. Subsequently, if the user operates according to this suggestion and the query is successful, it is considered that the verification result of this solution information is successful, and it is determined that the previous problem troubleshooting is accurate; otherwise, the previous problem troubleshooting is incorrect.

[0096] As Figure 7 shown, performing verification processing on the solution information to obtain the problem troubleshooting result may include the following steps:

[0097] Step S610, perform data integrity verification on the solution information to obtain a first inspection result;

[0098] Step S620, perform function verification on the solution information to obtain a second inspection result;

[0099] Step S630, perform performance verification on the solution information to obtain a third inspection result;

[0100] Step S640, perform security verification on the solution information to obtain a fourth inspection result;

[0101] Step S650, perform integration processing on the first inspection result, the second inspection result, the third inspection result, and the fourth inspection result to obtain the problem troubleshooting result.

[0102] For steps S610 to S650, during the process of performing verification processing on the solution information to obtain the problem troubleshooting result, first performing data integrity verification on the solution information can obtain the first inspection result; then, function verification processing can be performed on the solution information to obtain the second inspection result; then, performance verification processing can be performed on the solution information to obtain the third inspection result; then, security verification processing can be performed on the solution information to obtain the fourth inspection result; finally, integration processing on the first inspection result, the second inspection result, the third inspection result, and the fourth inspection result can obtain the problem troubleshooting result. Through the above technical solution, the determination of the solution information can be made more comprehensive and accurate, and thus the problem troubleshooting can be made more accurate and reliable.

[0103] It should be noted that data integrity verification processing is performed on the solution information, that is, the integrity of the data in the solution information is verified; function verification processing is performed on the solution information, that is, the feasibility of the function of the solution information is verified; performance verification processing is performed on the solution information, that is, the performance level of the solution information is verified; security verification processing is performed on the solution information, that is, the security in the process of implementing the solution information is verified.

[0104] In addition, as Figure 8 shown, an embodiment of the present application further provides a problem troubleshooting device 10, including:

[0105] An acquisition unit 100, configured to acquire operation problem information;

[0106] An extraction unit 200, configured to extract user information and scenario information from the operation problem information;

[0107] An analysis unit 300, configured to analyze and process the scenario information to obtain problem type information;

[0108] An execution unit 400, configured to, when the problem type information represents a new problem, associate similar problem information from a preset problem knowledge base; and perform fusion processing on the similar problem information and the user information to obtain overall problem key information;

[0109] A selection unit 500, configured to select corresponding solution information from the problem knowledge base according to the overall problem key information;

[0110] A verification unit 600, configured to perform verification processing on the solution information to obtain a problem troubleshooting result.

[0111] It should be noted that during the process of problem troubleshooting, first, operation problem information is obtained; then, user information and scenario information are extracted from the operation problem information; then, the scenario information is analyzed and processed to obtain problem type information; then, when the problem type information is characterized as a new problem, similar problem information is associated from a pre-set problem knowledge base; and the similar problem information and user information are fused and processed to obtain the key information of the overall problem; then, corresponding solution information is selected from the problem knowledge base according to the key information of the overall problem; finally, the solution information is verified to obtain the problem troubleshooting result. Through the above technical solution, when the problem type information is characterized as a new problem, similar problem information is associated from a pre-set problem knowledge base; and the similar problem information and user information are fused and processed to obtain the key information of the overall problem; then, corresponding solution information is selected from the problem knowledge base according to the key information of the overall problem, eliminating the need for manual problem troubleshooting, simplifying the problem troubleshooting process, and improving the efficiency of problem troubleshooting.

[0112] The specific implementation manner of the problem troubleshooting device 10 is basically the same as the specific embodiment of the above problem troubleshooting method, and will not be elaborated here.

[0113] In addition, as Figure 9 shown, an embodiment of the present application further provides an electronic device 700, which includes: a memory 720, a processor 710, and a computer program stored on the memory 720 and executable on the processor 710.

[0114] The processor 710 and the memory 720 can be connected through a bus or other means.

[0115] The non-transitory software program and instructions required to implement the problem troubleshooting method of the above embodiment are stored in the memory 720, and when executed by the processor 710, they execute the problem troubleshooting method of the above embodiments.

[0116] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0117] In addition, an embodiment of the present application further provides a computer-readable storage medium, which stores computer-executable instructions. The computer-executable instructions are executed by a processor 710 or a controller, for example, executed by a processor 710 in the above device embodiment, enabling the above processor 710 to execute the problem troubleshooting method in the above embodiments.

[0118] The above-described embodiments may be used in combination. Modules with the same name in different embodiments may be the same or different.

[0119] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily have to be performed in the particular order shown or in a sequential order to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0120] Each embodiment in the present application is described in a progressive manner. For the parts that are the same or similar among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the apparatus, device, and computer-readable storage medium, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the partial description of the method embodiments.

[0121] The apparatus, device, and computer-readable storage medium provided by the embodiments of the present application correspond to the method. Therefore, the apparatus, device, and non-volatile computer storage medium also have beneficial technical effects similar to the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, device, and computer storage medium will not be elaborated here.

[0122] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements to method flows). However, with the development of technology, many method flow improvements today can be regarded as direct improvements to hardware circuit structures. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement to a method flow cannot be implemented using a hardware entity module. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is an integrated circuit whose logical function is determined by the user programming the device. Designers can program themselves to "integrate" a digital system onto a single PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, today, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compilers used when developing and writing programs. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL), and there is not just one type of HDL, but many, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones currently are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply performing a little logical programming on the method flow using the above-mentioned several hardware description languages and programming it into an integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.

[0123] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to logically program the method steps to enable the controller to be implemented in the form of logic gates, switches, ASICs, programmable logic controllers, embedded microcontrollers, etc. to achieve the same function. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or structures within the hardware component.

[0124] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0125] For the convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing the embodiments of the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0126] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the embodiments of the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0127] This specification is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0128] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0129] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0130] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0131] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (Flash RAM). The memory is an example of computer-readable media.

[0132] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media do not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0133] It should also be noted that the term "comprises," "comprising," or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, commodity, or device that comprises a series of elements includes not only those elements but also other elements not expressly listed, or elements that are inherent to such process, method, commodity, or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity, or device that comprises the element.

[0134] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent the cases of A existing alone, A and B existing simultaneously, and B existing alone. Where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0135] Embodiments of the present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. Embodiments of the present application may also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0136] Each embodiment in the present application is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and reference can be made to the relevant parts of the method embodiments for the relevant content.

[0137] The above description is only for the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A problem troubleshooting method, characterized in that, Including: Obtain operation problem information; Extract user information and scenario information from the operation problem information; Analyze and process the scenario information to obtain problem type information; When the problem type information represents a new problem, associate similar problem information from a preset problem knowledge base; and fuse the similar problem information and the user information to obtain overall problem key information; Select corresponding solution information from the problem knowledge base according to the overall problem key information; Verify the solution information to obtain a problem troubleshooting result.

2. The problem troubleshooting method according to claim 1, wherein The extracting user information and scenario information from the operation problem information includes: Perform information splitting processing on the operation problem information to obtain multiple information blocks; Perform keyword recognition processing on all the information blocks to obtain multiple keyword information; Match the user information and the scenario information from the multiple keyword information according to preset problem keywords.

3. The problem troubleshooting method according to claim 1, wherein The analyzing and processing the scenario information to obtain problem type information includes: Perform feature extraction processing on the scenario information to obtain scenario feature information; Identify scenario marker information from the scenario feature information; Match the scenario marker information with a preset scenario problem marker library to obtain the problem type information.

4. The problem troubleshooting method according to claim 1, wherein The associating similar problem information from a preset problem knowledge base when the problem type information represents a new problem includes: When the problem type information represents a new problem, perform preprocessing on the problem type information to obtain preprocessing type information; Perform similarity speculation processing on the preprocessing type information to obtain similarity type information; Perform similarity matching processing on the similarity type information and each problem information in the problem knowledge base to obtain multiple matching degree values, where each matching degree value corresponds to one problem information; Take the problem information corresponding to the maximum value among the multiple matching degree values as the similar problem information.

5. The problem troubleshooting method according to claim 1, characterized in that, The fusing the similar problem information and the user information to obtain overall problem key information includes: Perform formatting processing on the similar problem information and the user information respectively to obtain organized problem information corresponding to the similar problem information and organized user information corresponding to the user information; Perform feature extraction on the organized problem information and the organized user information respectively to obtain problem key features corresponding to the organized problem information and user key features corresponding to the organized user information; Perform weighted fusion processing on the problem key features and the user key features to obtain the overall problem key information.

6. The problem troubleshooting method according to claim 1, wherein The problem knowledge base includes original problem information and original solution information corresponding to the original problem information. The selecting corresponding solution information from the problem knowledge base according to the overall problem key information includes: Perform matching processing on the overall problem key information and the original problem information to determine target original problem information; Determine the original solution information corresponding to the target original problem information as the solution information.

7. The problem troubleshooting method according to claim 1, characterized in that Perform verification processing on the solution information to obtain a problem troubleshooting result, including: Perform data integrity verification on the solution information to obtain a first inspection result; Perform function verification on the solution information to obtain a second inspection result; Perform performance verification on the solution information to obtain a third inspection result; Perform security verification on the solution information to obtain a fourth inspection result; Perform integration processing on the first inspection result, the second inspection result, the third inspection result, and the fourth inspection result to obtain the problem troubleshooting result.

8. A problem troubleshooting device, characterized in that, Including: An acquisition unit for acquiring operation problem information; An extraction unit for extracting user information and scenario information from the operation problem information; An analysis unit for analyzing and processing the scenario information to obtain problem type information; An execution unit for, when the problem type information represents a new problem, associating similar problem information from a preset problem knowledge base; and performing fusion processing on the similar problem information and the user information to obtain overall problem key information; A selection unit for selecting corresponding solution information from the problem knowledge base according to the overall problem key information; A verification unit for performing verification processing on the solution information to obtain a problem troubleshooting result.

9. An electronic device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the problem troubleshooting method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing computer-executable instructions, characterized in that, The computer-executable instructions are used to execute the problem troubleshooting method according to any one of claims 1 to 7.

Images