Method, device and electronic equipment for detecting service failure

Abstract

The present disclosure provides a business failure detection method and device and electronic equipment, relates to the technical field of artificial intelligence, in particular to the technical field of cloud computing, big data, deep learning and the like. The specific implementation scheme is: obtaining at least one user question and at least one reply content fed back by a to-be-detected application for the at least one user question, wherein the at least one user question is a question fed back by at least one user for business use of the to-be-detected application; determining a target question corresponding to the at least one user question according to the at least one reply content; and determining whether the to-be-detected application has a business failure according to the number of occurrences of the target question within a preset time length.

Description

Technical Field

[0001] It involves the field of artificial intelligence technology, especially cloud computing, big data, and deep learning, and specifically involves methods, devices, and electronic equipment for detecting business failures. Background Technology

[0002] In related technologies, business failures in client applications are mainly handled by human customer service representatives. For example, feedback issues in client applications are statistically analyzed and categorized. However, this method is prone to problems such as unclear classification by operators, and each feedback issue needs to be manually counted and summarized, requiring a huge investment of human and material resources. Summary of the Invention

[0003] This disclosure provides a method, apparatus, and electronic device for detecting service failures.

[0004] According to one aspect of this disclosure, a method for detecting business failures is provided, comprising: acquiring at least one user question and at least one response from an application under test in response to the at least one user question, wherein the at least one user question is a question raised by at least one user regarding the business usage of the application under test; determining a target question corresponding to the at least one user question based on the at least one response; and determining whether the application under test has a business failure based on the number of times the target question occurs within a preset time period.

[0005] According to another aspect of this disclosure, a business failure detection device is provided, comprising: an acquisition module, configured to acquire at least one user problem and at least one response from an application under test in response to the at least one user problem, wherein the at least one user problem is a problem reported by at least one user regarding the business usage of the application under test; a determination module, configured to determine a target problem corresponding to the at least one user problem based on the at least one response; wherein the determination module is further configured to determine whether the application under test has a business failure based on the number of times the target problem occurs within a preset time period.

[0006] According to another aspect of this disclosure, an electronic device is provided, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the service fault detection method of the embodiments of this disclosure.

[0007] According to another aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute the business fault detection method of the embodiments of this disclosure.

[0008] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the business fault detection method of the embodiments of this disclosure.

[0009] As described above, in this disclosure, the intelligent customer service server can determine the target problem corresponding to the user's question by obtaining the response content. Since the target problem corresponding to the response content is usually fixed, the response content can more accurately determine the target problem, thus avoiding the low accuracy problem of determining the target problem corresponding to the user's question through keyword matching in the prior art. Furthermore, the target problem corresponding to the user's question can reflect the business faults existing in the application under test. Therefore, by statistically analyzing the number of times the target problem occurs within a preset time period, it can be determined whether the application under test has a fault. Furthermore, the fault type of the application under test can be determined based on the target problem. This process does not require manual statistical analysis and classification, thereby improving the timeliness of fault detection for the application under test. Therefore, the solution provided in this disclosure solves the problems of low accuracy and incomplete data coverage in manual customer service monitoring of business faults, achieving the technical effect of improving the stability of the application under test and the user experience.

[0010] 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

[0011] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0012] Figure 1 This is a flowchart of a service fault detection method according to an embodiment of the present disclosure;

[0013] Figure 2 This is a schematic diagram of a response content-based monitoring and alarm according to an embodiment of this disclosure;

[0014] Figure 3 This is a schematic diagram of a service fault detection device according to an embodiment of the present disclosure;

[0015] Figure 4 This is a schematic diagram of an electronic device used to implement the service fault detection method of the embodiments of this disclosure. Detailed Implementation

[0016] 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.

[0017] The following describes a method for detecting service failures according to an embodiment of this disclosure.

[0018] Figure 1 This is a flowchart of a service failure detection method according to an embodiment of the present disclosure, such as... Figure 1 As shown, the method may include the following steps:

[0019] Step S102: Obtain at least one user question and at least one response from the application under test in response to the at least one user question.

[0020] Optionally, the execution subject in this embodiment is an intelligent customer service server. Other electronic devices and processors can also serve as the execution subject, and no further limitations are imposed here.

[0021] In the technical solution provided in step S102 of this disclosure, the intelligent customer service terminal can obtain user questions through a help and feedback system. This help and feedback system can be a functional module within the application being tested. For example, when the application being tested is a cloud storage service, the help and feedback system can be a functional module integrated into the cloud storage application, through which users can report problems encountered while using the cloud storage (e.g., crashes, inability to upload and / or download files). Alternatively, the help and feedback system can be a functional module separate from the application being tested. For example, when the application being tested is a cloud storage service, the help and feedback system can be another application, such as an application from the same manufacturer as the application being tested. This application primarily collects problems encountered by users while using applications produced by the same manufacturer.

[0022] User issues can be technical problems reported by users to the help and feedback system while using the application under test, such as crashes or lag issues that occur during the use of the application. Figure 2 As shown, the intelligent customer service server can obtain user data collected periodically by the help and feedback system, such as... Figure 2In step S201, the intelligent customer service server periodically collects intelligent customer service data (i.e., user data), which includes user information, the content of each round of user feedback, and the corresponding response content. Then, the intelligent customer service server stores the data in its database according to the order of the conversations, for use by the intelligent customer service monitoring system. This avoids the problem that the manual customer service's classification and statistics capabilities are insufficient to cover all customer complaints, thus preventing omissions or missing information in fault statistics.

[0023] Optionally, the response content can be relational data corresponding to the user's question. For example, developers can store pre-set questions and their corresponding responses in the intelligent customer service server's database. When a user submits a pre-set question, the intelligent customer service server can retrieve the corresponding response from the database and automatically display the reply. Furthermore, developers can also build a comprehensive framework for the intelligent customer service server. For instance, when a user submits a question, the intelligent customer service server can understand the user's question based on the comprehensive framework, extract the central idea, and automatically generate the corresponding response content based on that central idea.

[0024] Optionally, such as Figure 2 As shown, the intelligent customer service monitoring system can read user data from the intelligent customer service server and monitor user data in real time through the monitoring program, issuing early warning information (i.e., Figure 2 Step S202 in the process.

[0025] Optionally, the application under test can write the collected user data into a table, for example, write the user Q&A data (user questions and reply content) into the table, and then send the table to the intelligent customer service server, so that the intelligent customer service server can read the data in the table to obtain the user Q&A data (user questions and reply content).

[0026] Optionally, the application under test can automatically generate a document from the collected user data. For example, it can generate a readable document from the user data (user questions and replies), so that the intelligent customer service server can directly read the document to obtain the user data.

[0027] It should be noted that the above content is only for illustrative purposes, and the specific implementation methods for obtaining user questions and the responses of the application under test to user questions are not limited here. Other implementation methods that can obtain user questions and the responses of the application under test to user questions are all within the protection scope of this disclosure.

[0028] Optionally, when monitoring user data, the intelligent customer service monitoring system can acquire user data at preset time intervals. In addition, the intelligent customer service server can determine the time interval based on the distribution information of the frequency of user feedback issues. For example, if users report issues more frequently between 10:00 AM and 3:00 PM, the time interval for collecting data between 10:00 AM and 3:00 PM can be shortened.

[0029] Step S104: Determine the target question corresponding to at least one user question based on at least one response.

[0030] In the technical solution provided by step S104 of this disclosure, the intelligent customer service monitoring system can traverse the reply content in each newly created feedback record in the intelligent customer service database, and then perform target question matching operations on different types of reply content according to predefined priorities (such as...). Figure 2 In step S203), when the target problem data is matched, it means that the user has encountered the problem corresponding to the target problem, thereby obtaining the target problem corresponding to the user's problem. This solves the technical problem that human customer service may have ambiguity in handling content classification, which leads to the failure to detect faults in a timely manner, and improves the accuracy of the application under test in identifying business faults.

[0031] Optionally, different types of response content may include: response content directly fed back by the intelligent customer service server and response content selected by the user, wherein the response content directly fed back by the intelligent customer service server has a higher priority than the response content selected by the user.

[0032] Optionally, the intelligent customer service server can obtain different types of response content, such as response content A and response content B. When response content A has a higher priority than response content B, only the target question matching operation needs to be performed for response content A to obtain the corresponding target question, without performing the target question matching operation for response content B. The final target question corresponding to the response content is the target question corresponding to response content A.

[0033] Optionally, the intelligent customer service server can obtain different types of response content, such as response content A and response content B. When response content A has a higher priority than response content B, the target question matching operation is performed on response content A and response content B in turn to obtain the corresponding target questions. Then, the intersection of their corresponding target questions is taken to obtain the final target question corresponding to the response content.

[0034] Optionally, the intelligent customer service server can obtain different types of response content, such as response content A and response content B. When the priority of response content A and response content B are the same, response content A and response content B can be matched according to the time sequence of the user's question feedback corresponding to the response content. For example, if the user's question A corresponding to response content A was fed at 9:00 AM, while the user's question B corresponding to response content B was fed at 3:00 PM, the intelligent customer service server will prioritize matching response content A.

[0035] Optionally, different criteria can be used to prioritize different responses. Priority can be determined by the chronological order of user feedback corresponding to the response; for example, a user issue reported at 9:00 AM will have higher priority than one reported at 3:00 PM. Alternatively, priority can be determined by the severity of the target issue corresponding to the response; for example, a target issue of an app crashing will have higher priority than a target issue of an app lagging. Furthermore, priority can also be determined by the frequency of occurrence of the target issue corresponding to the response within a certain period; for example, if target issue A occurs 10 times in a week and target issue B occurs 50 times in a week, then target issue B will have higher priority than target issue A.

[0036] Step S106: Determine whether the application to be tested has a business failure based on the number of times the target problem occurs within a preset time period.

[0037] In the technical solution provided by step S106 of this disclosure, the intelligent customer service server can obtain the matching target question based on the reply content, then count the number of different target questions appearing within a preset time period, and match the alarm thresholds corresponding to different target questions. When the number of times the target question appears reaches or exceeds the corresponding alarm threshold, it is determined that the application under test has a business failure, and the R&D personnel and customer service personnel are notified in a timely manner to perform alarm operations. This avoids the problem that manual customer service has low efficiency due to the large number of manual interventions when performing fault statistics, and the failure is not detected in time, thus expanding the impact.

[0038] Optionally, the preset alarm threshold can be an empirical value, such as 10 times / hour. That is, when the target problem occurs more than or equal to 10 times within 1 hour, the intelligent customer service monitoring system determines that the application under test has a business failure and performs an alarm operation.

[0039] Optionally, there are various forms of notification to R&D and customer service personnel to perform alarm operations. For example, when the intelligent monitoring system detects a business failure, it can generate a fault notification and send it to R&D and customer service personnel as a warning. Alternatively, the intelligent customer service server can pop up an emergency notification in the target control interface of the application to be tested to perform an emergency alarm operation for on-duty management personnel.

[0040] Optionally, after the intelligent monitoring system triggers an alarm, the intelligent customer service server can automatically generate a fault detection report for R&D personnel and customer service personnel to review later. The fault detection report can be a readable document or a piece of fault code data, without specific limitations.

[0041] Optionally, different types of target issues can correspond to different alarm thresholds. For example, there are target issues A and target issues B. The alarm threshold for target issue A is 5 times / hour, and the alarm threshold for target issue B is 15 times / hour. That is, when target issue A occurs more than or equal to 5 times in 1 hour, the intelligent customer service monitoring system will issue an alarm operation, while when target issue B occurs more than or equal to 5 times in 1 hour, the intelligent customer service monitoring system will not issue an alarm operation.

[0042] Steps S102 to S106 above show that, in this disclosure, at least one user question and at least one response from the application under test to the at least one user question are obtained. The target question corresponding to the at least one user question is determined based on the at least one response. The application under test is determined to have a business failure based on the number of times the target question occurs within a preset time period.

[0043] It is noteworthy that, in this embodiment of the disclosure, the intelligent customer service server can determine the target question corresponding to the user's question by obtaining the response content corresponding to the user's question. Since the target question corresponding to the response content is usually fixed, the target question corresponding to the user's question can be determined more accurately through the response content, thereby avoiding the low accuracy problem of determining the target question corresponding to the user's question through keyword matching in the prior art. In addition, the target question corresponding to the user's question can reflect the business failure of the application under test. Therefore, by counting the number of times the target question occurs within a preset time period, it can be determined whether the application under test has a failure. Furthermore, the failure type of the application under test can be determined based on the target question. This process does not require manual participation in statistics and classification, thereby improving the timeliness of failure detection of the application under test.

[0044] The method described in this embodiment will now be described in further detail.

[0045] As an optional implementation, step S102, obtaining at least one user question and at least one response from the application under test in response to at least one user question, includes: obtaining a data list sent by the application under test, wherein the data list is used to record at least one user question and at least one response in the order of the session in which at least one user questions are reported, and reading at least one user question and at least one response from the data list.

[0046] In this embodiment, for data security reasons, the user data stored in the help and feedback system cannot be read directly. The application to be tested will write the user data collected in the help and feedback system into a data list. The intelligent customer service server can read the user data from the data list through a timed task with adjustable duration to complete the collection of customer complaint data, thus avoiding the situation of missing data collection during the data collection process. The user data includes at least one user question and at least one reply.

[0047] Alternatively, a data list is a data structure for storing and organizing data, where each element is a data record, and each data record consists of several fields.

[0048] Optionally, the data list can be used to store data in a database, process data in data analysis, etc. In this embodiment, the data list can be used to store various types of data, such as text, numbers, images, etc.

[0049] Optionally, the preset time interval can be an empirical value, such as once per hour. That is, the intelligent customer service server can perform a read operation every hour to retrieve user data from the data list, thereby improving the efficiency of user data acquisition. Alternatively, the aforementioned time interval can also be determined by the intelligent customer service server based on the distribution information of the frequency of user feedback issues. For example, if users provide feedback issues more frequently between 10:00 AM and 3:00 PM, the time interval for collecting data between 10:00 AM and 3:00 PM can be shortened.

[0050] As an optional implementation, step S104, determining the target question corresponding to at least one user question based on at least one reply content, includes: determining the reply type of each reply content to obtain at least one reply type, determining the priority of at least one reply content based on the at least one reply type, then determining the matching order for at least one reply content to match the target question based on the priority of the at least one reply content, and reading the target question corresponding to the at least one reply content from a preset storage area according to the matching order, and finally determining the target question corresponding to at least one user question based on the target question corresponding to the at least one reply content. Here, at least one reply type represents the way the application to be detected provides feedback on the reply content, and the preset storage area is used to store at least one reply content, the target question, and the association between at least one reply content and the target question.

[0051] In this embodiment, the intelligent customer service monitoring system periodically executes a traversal task, iterating through the response content of each newly created feedback record in the intelligent customer service database. Based on the different ways the response content of the application to be detected is presented, different response types are determined. Different types of response content are then matched against target questions in a pre-defined storage area within the intelligent customer service system according to a predefined priority. This pre-defined storage area stores response content, target questions, and the association between the response content and the target question. When a target question is matched, it means the user has encountered the problem corresponding to that target question. This embodiment clarifies the process of determining the target question, avoiding conflicts when multiple response contents are matched, and achieving the technical effect of providing a more stable business fault detection method.

[0052] Optionally, different types of response content may include: response content directly fed back by the intelligent customer service server and response content selected by the user, wherein the response content directly fed back by the intelligent customer service server has a higher priority than the response content selected by the user.

[0053] Optionally, such as Figure 2 As shown in step S204, different types of response content can be preset with different priorities. For example, the preset priority of response content A is level 1, and the preset priority of response content B is level 2. When response content A and response content B have a conflict, the target question is matched with response content A first.

[0054] Optionally, such as Figure 2As shown in step S204, when different types of response content have the same preset priority, for example, when response content A and response content B both have a preset priority of level 2, when response content A and response content B have a conflict, the order can be determined according to the feedback time of the user's question corresponding to response content A and response content B, or according to the severity of the target question corresponding to the response content. Alternatively, the order can be determined according to the number of times the target question corresponding to the response content appears within a certain period of time. No specific limitation is made here.

[0055] As an optional implementation, after reading the target questions corresponding to at least one reply content from a preset storage area according to the matching order, the number of target questions corresponding to each reply content is determined, the target reply content is determined from the at least one reply content, then the target user question corresponding to the target reply content is determined, and a first target question is determined based on the similarity between the target user question and the target questions in the preset storage area. The number of target questions corresponding to the target reply content is multiple.

[0056] In this embodiment, when there are multiple target questions in the response content, the target question is determined as the target response content. Then, the target user question corresponding to the target response content is determined, and the target user question is matched with the multiple corresponding target questions. Thus, a first target question is determined based on the similarity between the target user question and target questions in a preset storage area. This embodiment determines that when there are multiple target questions in the response content, the target question can be determined through similarity matching, avoiding the problem of unclear classification when multiple target questions exist in the response content.

[0057] Optionally, when there are multiple target questions in the response content, the target user question is matched with the corresponding multiple target questions. When there are two or more target questions with the same similarity to the target user question, in order to avoid the problem of inaccurate matching results, a higher precision matching algorithm can be used for matching, or the matching mechanism can be changed to re-match the target user question with the corresponding multiple target questions to filter out the most accurate matching results.

[0058] As an optional implementation, determining the first target question based on the similarity between the target user question and target questions in a preset storage area includes: extracting target keywords from the target user question; performing similarity matching between the target user question and target questions in the preset storage area based on the target keywords to obtain a matching result; and determining the first target question corresponding to the target response content from the target questions in the preset storage area based on the matching result.

[0059] In this embodiment, such as Figure 2 As shown in step S204, when a response corresponds to multiple target questions, the intelligent customer service server can use string keywords and a similarity matching algorithm to match the target user's question with multiple target questions in a preset storage area, thereby determining the target question with the highest similarity to the target user's question as the first target question. This embodiment clarifies that the target question is determined by using keywords and a similarity matching algorithm, achieving the technical effect of matching each response with the target question with the highest similarity.

[0060] Optionally, string similarity matching algorithms can be applied to multiple computing scenarios. Common string similarity algorithms include EditDistance, N-gram, JaroWinkler, and Soundex.

[0061] It should be noted that the above content is only for illustrative purposes, and the specific implementation algorithm of the intelligent customer service server using string keywords and similarity matching algorithm for matching is not limited here. Other implementation algorithms that enable the intelligent customer service server to use string keywords and similarity matching algorithm for matching are all within the protection scope of this disclosure.

[0062] Optionally, for example, a target user problem can correspond to multiple target problems: target problem A, target problem B, and target problem C. Assuming that target problem A has a 90% similarity to the target user problem, target problem B has a 70% similarity to the target user problem, and target problem C has a 50% similarity to the target user problem, since target problem A has the highest similarity to the target user problem, target problem A can be determined as the first target problem.

[0063] Optionally, for example, a target user question can correspond to multiple target questions: target question A, target question B, and target question C. Suppose that target question A has a similarity of 90% with the target user question, target question B has a similarity of 90% with the target user question, and target question C has a similarity of 50% with the target user question. That is, there are cases where two target questions have the same similarity. In this case, different algorithms can be used to perform similarity matching operations again to obtain new similarity results.

[0064] As an optional implementation, step S108 determines whether the application under test has a business failure based on the number of times the target problem occurs within a preset time period, including: when the number of occurrences is greater than or equal to a preset threshold, determining that the application under test has a business failure and generating a warning message; when the number of occurrences is less than the preset threshold, determining that the application under test does not have a business failure.

[0065] In this embodiment, after obtaining the matching target question based on the response content, the intelligent customer service server can count the number of times different target questions appear within a preset time interval, such as... Figure 2 As shown in step S206, when the number of times the target problem occurs reaches or exceeds a preset alarm threshold, it is determined that the application under test has a business fault, and the R&D personnel and customer service personnel are notified in a timely manner to generate a warning message. When the number of times the target problem occurs does not reach the preset alarm threshold, it is determined that the application under test does not have a business fault. This embodiment clarifies that the presence of a fault in the application under test can be determined based on the number of times the target problem occurs, achieving the technical effect of issuing a timely warning message when the application under test malfunctions, providing users with a more stable and secure user experience.

[0066] Optionally, the preset alarm threshold can be an empirical value, such as 10 times / hour. That is, when the target problem occurs more than or equal to 10 times within 1 hour, the intelligent customer service monitoring system determines that the application under test has a business failure and performs an alarm operation. When the target problem occurs less than 10 times within 1 hour, the intelligent customer service monitoring system determines that the application under test does not have a business failure and no operation is required.

[0067] Optionally, different alarm thresholds can be preset for different times. For example, between 9:00 AM and 3:00 PM, the alarm threshold can be set relatively low, such as 10 alarms per hour. This period is the peak time for user activity, so any problems should be addressed promptly to avoid more serious system failures. Meanwhile, a higher alarm threshold can be set between midnight and 7:00 AM, such as 30 alarms per hour. Since fewer users are using the application at night, manpower can be saved, and problems can be addressed more efficiently.

[0068] As an optional implementation method, such as Figure 2 As shown in step S205, after determining that the application to be tested has a business fault, the intelligent customer service server can also determine the problem type of the second target problem, and determine the fault type corresponding to the business fault based on the problem type of the second target problem. The second target problem is a target problem whose occurrence frequency is greater than or equal to a preset threshold.

[0069] In this embodiment, the intelligent customer service server can identify a target problem that occurs more than or equal to a preset threshold as a second target problem, determine the problem type of the second target problem, and then determine the fault type corresponding to the business failure based on the problem type of the second target problem. This embodiment clarifies that the fault type can be determined based on the problem type of the target problem, achieving the technical effect of more accurately and clearly determining the fault type of the business failure.

[0070] Optionally, different types of target issues can correspond to different alarm thresholds. For example, different types of target issues include target issue A and target issue B. The alarm threshold for target issue A is 5 times / hour, and the alarm threshold for target issue B is 15 times / hour. That is, when target issue A occurs more than or equal to 5 times in 1 hour, the intelligent customer service monitoring system will issue an alarm operation; when target issue B occurs more than or equal to 15 times in 1 hour, the intelligent customer service monitoring system will issue an alarm operation.

[0071] Optionally, the fault types can be divided into several categories, including: early-onset fault types, sudden fault types, progressive fault types, latent fault types, and compound fault types. For example, the lag problem in the application under test belongs to the progressive fault type, while the crash problem in the application under test belongs to the sudden fault type.

[0072] Optionally, different fault types can correspond to different early warning information and countermeasures. At the same time, different fault types can be equipped with different solutions and technical personnel, which can achieve the technical effect of reducing the time for problem solving and saving manpower.

[0073] Optionally, after determining the fault type corresponding to the business fault based on the problem type of the second target problem, a corresponding fault report can also be generated. The fault report can exist as a readable document in the intelligent customer service monitoring system, or it can be a piece of code that stores fault data for other applications to analyze and improve.

[0074] Figure 3 This is a schematic diagram of a service fault detection device according to an embodiment of the present disclosure, such as... Figure 3 As shown, the service fault detection device 300 may include: an acquisition module 301, a first determination module 302, and a second determination module 303.

[0075] The acquisition module 301 is used to acquire at least one user question and at least one response from the application under test in response to the at least one user question, wherein the at least one user question is a question raised by at least one user regarding the business usage of the application under test;

[0076] The first determining module 302 is used to determine the target question corresponding to the at least one user question based on the at least one reply content;

[0077] The second determining module 303 is used to determine whether the application to be detected has a business failure based on the number of times the target problem occurs within a preset time period.

[0078] Optionally, the acquisition module 301 includes: an acquisition unit, configured to acquire a data list sent by the application to be detected, wherein the data list is used to record at least one user question and at least one reply content in the order of the session in which at least one user reported a user question; and a first reading unit, configured to read at least one user question and at least one reply content from the data list.

[0079] Optionally, the first determining module 302 includes: a first determining unit, configured to determine the response type of each response content to obtain at least one response type, wherein the at least one response type characterizes the way the application to be detected provides feedback on the response content; a second determining unit, configured to determine the priority of at least one response content based on the at least one response type; a third determining unit, configured to determine the matching order for matching the at least one response content with the target question based on the priority of the at least one response content; a second reading unit, configured to read the target question corresponding to the at least one response content from a preset storage area according to the matching order, wherein the preset storage area is used to store at least one response content, the target question, and the association relationship between the at least one response content and the target question; and a fourth determining unit, configured to determine the target question corresponding to at least one user question based on the target question corresponding to the at least one response content.

[0080] Optionally, the first determining module 302 further includes: a fifth determining unit, used to determine the number of target questions corresponding to each reply content; a sixth determining unit, used to determine target reply content from at least one reply content, wherein the number of target questions corresponding to the target reply content is multiple; a seventh determining unit, used to determine the target user question corresponding to the target reply content; and an eighth determining unit, used to determine a first target question based on the similarity between the target user question and target questions in a preset storage area.

[0081] Optionally, the eighth determining unit includes: an extraction subunit for extracting target keywords from the target user's question; a matching subunit for performing similarity matching between the target user's question and target questions in a preset storage area based on the target keywords, and obtaining a matching result; and a first determining subunit for determining the first target question corresponding to the target response content from the target questions in the preset storage area based on the matching result.

[0082] Optionally, the second determining module 303 includes: a ninth determining unit, used to determine that the application under test has a business failure when the number of occurrences is greater than or equal to a preset threshold, and to generate a warning message; and a tenth determining unit, used to determine that the application under test does not have a business failure when the number of occurrences is less than a preset threshold.

[0083] Optionally, the second determining module 303 further includes: an eleventh determining unit, used to determine the problem type of the second target problem, wherein the second target problem is a target problem whose occurrence frequency is greater than or equal to a preset threshold; and a twelfth determining unit, used to determine the fault type corresponding to the business fault based on the problem type of the second target problem.

[0084] 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.

[0085] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0086] Figure 4 A schematic block diagram of an example electronic device 400 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.

[0087] like Figure 4 As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 402 or a computer program loaded from storage unit 408 into random access memory (RAM) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0088] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0089] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 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 401 performs the various methods and processes described above, such as a business fault detection method. For example, in some embodiments, the business fault detection method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the business fault detection method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the business fault detection method by any other suitable means (e.g., by means of firmware).

[0090] 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), payload-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.

[0091] 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.

[0092] 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.

[0093] 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).

[0094] 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 embodiments 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.

[0095] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0096] 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.

[0097] 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 method for detecting service failures, comprising: Obtain at least one user question and at least one response from the application under test in response to the at least one user question, wherein the at least one user question is a question raised by at least one user regarding the use of the application under test. The response type of each response is determined to obtain at least one response type, wherein the at least one response type represents the way the application under test responds to the response content, and the response type includes the type directly fed back by the intelligent customer service terminal and the type selected by the user; The priority of the at least one response content is determined based on the at least one response type; The matching order of the at least one reply content to the target question corresponding to the at least one user question is determined based on the priority of the at least one reply content; The target question corresponding to the at least one reply content is read from a preset storage area according to the matching order, wherein the preset storage area is used to store the at least one reply content, the target question, and the association between the at least one reply content and the target question; The target question corresponding to the at least one user question is determined based on the target question corresponding to the at least one response content; Based on the number of times the target problem occurs within a preset time period, it is determined whether the application to be tested has a business failure.

2. The method according to claim 1, wherein, The acquisition of at least one user question and at least one response from the application under test to the at least one user question includes: Obtain a list of data sent by the application to be detected, wherein the list of data is used to record the at least one user question and the at least one reply content in the order of the conversation in which the at least one user reported the user question; Read the at least one user question and the at least one reply from the data list.

3. The method according to claim 1, after reading the target question corresponding to the at least one reply content from the preset storage area according to the matching order, the method further includes: Determine the number of target questions corresponding to each response; Determine the target response content from the at least one response content, wherein the number of target questions corresponding to the target response content is multiple; Determine the target user's question corresponding to the target response content; The first target question is determined based on the similarity between the target user question and the target question in the preset storage area.

4. The method according to claim 3, wherein, The step of determining the first target question based on the similarity between the target user question and the target questions in the preset storage area includes: Extract target keywords from the questions asked by the target users; Based on the target keywords, a similarity match is performed between the target user's question and the target question within the preset storage area to obtain a matching result; Based on the matching result, determine the first target question corresponding to the target response content from the target questions in the preset storage area.

5. The method according to claim 1, wherein, The step of determining whether the application under test has a business failure based on the number of times the target problem occurs within a preset time period includes: When the number of occurrences is greater than or equal to a preset threshold, it is determined that the application to be detected has the business failure, and an early warning message is generated; When the number of occurrences is less than the preset threshold, it is determined that the application to be detected does not have the business fault.

6. The method according to claim 5, further comprising, after determining that the application to be detected has the service failure: Determine the problem type of the second target problem, wherein the second target problem is the target problem whose occurrence frequency is greater than or equal to the preset threshold; The fault type corresponding to the business fault is determined based on the problem type of the second target problem.

7. A device for detecting service failures, comprising: The acquisition module is used to acquire at least one user question and at least one response from the application under test in response to the at least one user question, wherein the at least one user question is a question raised by at least one user regarding the business usage of the application under test; A first determining module is used to determine the response type of each response content, obtaining at least one response type, wherein the at least one response type represents the way the application under test responds to the response content, and the response type includes the type directly responded by the intelligent customer service terminal and the type selected by the user; determining the priority of the at least one response content according to the at least one response type; determining the matching order for the at least one response content to match the target questions corresponding to the at least one user question according to the priority of the at least one response content; reading the target questions corresponding to the at least one response content from a preset storage area according to the matching order, wherein the preset storage area is used to store the at least one response content, the target questions, and the association relationship between the at least one response content and the target questions; and determining the target question corresponding to the at least one user question according to the target question corresponding to the at least one response content. The second determining module is used to determine whether the application to be tested has a business failure based on the number of times the target problem occurs within a preset time period.

8. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

10. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images