CN113781068B

CN113781068B - Online problem solving method, device, electronic equipment and storage medium

Info

Publication number: CN113781068B
Application number: CN202111059047.1A
Authority: CN
Inventors: 夏杰
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2021-09-09
Filing date: 2021-09-09
Publication date: 2024-05-14
Anticipated expiration: 2041-09-09
Also published as: CN113781068A

Abstract

The application relates to the technical field of artificial intelligence, and particularly discloses an online problem solving method, an online problem solving device, electronic equipment and a storage medium, wherein the online problem solving method comprises the following steps: acquiring first data according to the error reporting information of the on-line problem, wherein the first data is used for identifying data of operation of the system by on-line personnel corresponding to the system after error reporting; extracting features of the first data according to the data type of the first data to obtain key feature information of the first data; according to the key characteristic information, matching a solution; displaying the solution to a user and receiving feedback information of the user; according to the feedback information and the solution, matching at least one script combination in a preset script library to obtain a solution script; and running the solving script to solve the online problem.

Description

Online problem solving method, device, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to an online problem solving method, an online problem solving device, electronic equipment and a storage medium.

Background

At present, when an online production problem occurs, the online service personnel often find the online production problem and report the online production problem to corresponding responsible persons, and then the responsible persons further communicate with the service personnel, for example, inquire the reasons of the online service personnel that the online service personnel has the problem, and the online service personnel operate after the problem occurs. After the related data is acquired through inquiry, the problem can be processed. In this way, some problem data are difficult to obtain, for example, online service personnel often cannot describe the condition of the system and the processing procedure thereof in detail and comprehensively when the problem occurs, which results in low processing efficiency. Meanwhile, when the problem occurs, the processing is reported only after waiting for the online business personnel to actively find out, so that the processing timeliness is low. In addition, each time a problem report is received, a responsible person needs to analyze from scratch and reformulate a solution, and the requirement on the responsible person is high, so that the labor cost is high.

Disclosure of Invention

In order to solve the above problems in the prior art, embodiments of the present application provide a method, an apparatus, an electronic device, and a storage medium for solving the problems on line, which can report the problems on line in time, and simultaneously provide a corresponding solution, so as to improve timeliness and efficiency of on-line problem processing, reduce dependence on manpower, and further reduce manpower cost.

In a first aspect, embodiments of the present application provide an online problem solving method, including:

Acquiring first data according to the error reporting information of the on-line problem, wherein the first data is used for identifying data of operation of on-line personnel corresponding to the system after error reporting;

According to the data type of the first data, extracting the characteristics of the first data to obtain key characteristic information of the first data;

According to the key characteristic information, matching the solution;

the method comprises the steps of displaying a solution to a user and receiving feedback information of the user;

According to the feedback information and the solution, matching at least one script combination in a preset script library to obtain a solution script;

and running a solving script to solve the online problem.

In a second aspect, embodiments of the present application provide an online problem solving apparatus, including:

The acquisition module is used for acquiring first data according to the error reporting information of the on-line problem, wherein the first data is used for identifying data of operation of the system by on-line personnel corresponding to the error reporting of the system;

The identification module is used for carrying out feature extraction on the first data according to the data type of the first data to obtain key feature information of the first data;

the matching module is used for matching the solution according to the key characteristic information;

the display module is used for displaying the solution to the user and receiving feedback information of the user;

the solution module is used for matching at least one script combination in a preset script library to be a solution script according to the feedback information and the solution, and running the solution script to solve the online problem.

In a third aspect, an embodiment of the present application provides an electronic device, including: and a processor coupled to the memory, the memory for storing a computer program, the processor for executing the computer program stored in the memory to cause the electronic device to perform the method as in the first aspect.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium storing a computer program, the computer program causing a computer to perform the method as in the first aspect.

In a fifth aspect, embodiments of the present application provide a computer program product comprising a non-transitory computer readable storage medium storing a computer program, the computer being operable to cause a computer to perform a method as in the first aspect.

The implementation of the embodiment of the application has the following beneficial effects:

In the embodiment of the application, when a problem occurs in an online system, the first data of the operation of the system is automatically identified by the corresponding online personnel after the error of the identification system is reported, and then the corresponding key characteristic information is obtained. Then, matching similar solved problems through comparison of key characteristic information, and then using the solution of the solved problems as a reference solution of the error, and displaying the solution to a user. And finally, acquiring a corresponding script combination to be a solution script through feedback information of a user and combining a solution, and running the solution script to solve the problem of on-line system occurrence. Therefore, when an online system goes wrong, the operation information of an online person after the online system goes wrong is automatically reported, and compared with the prior art that the online person reports the operation information after the online system goes wrong, the accuracy and timeliness are higher. Meanwhile, the acquired data can be automatically analyzed, and then the corresponding solution which is automatically matched according to the analysis result is displayed to the system responsible person, so that the system responsible person only needs to confirm whether the solution is normal or not, if so, the system responsible person can directly run, the system responsible person is not required to compose the solution from 0, the professional requirements on the responsible person are reduced, the labor cost is further reduced, and meanwhile, the automatic solution of the on-line problem is realized.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic hardware structure of an on-line problem-solving apparatus according to an embodiment of the present application;

FIG. 2 is a schematic flow chart of an on-line problem solving method according to an embodiment of the present application;

FIG. 3 is a flowchart illustrating a method for acquiring first data according to error reporting information of an online problem according to an embodiment of the present application;

fig. 4 is a flow chart of a method for extracting features of first data according to a data type of the first data to obtain key feature information of the first data according to an embodiment of the present application;

FIG. 5 is a flowchart of a method for matching each screenshot with a history error screenshot in a history error database according to error reporting information, and calculating a similarity between each screenshot and a corresponding history error screenshot according to the error reporting information according to the embodiment of the present application;

FIG. 6 is a flowchart illustrating a method for calculating a similarity between a first screenshot and a corresponding first historical error screenshot according to an embodiment of the present application;

fig. 7 is a schematic diagram of a numbered image obtained by numbering a segmented image according to an embodiment of the present application;

FIG. 8 is a functional block diagram of an on-line problem-solving apparatus according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the present application. All other embodiments, based on the embodiments of the application, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the application.

The terms "first," "second," "third," and "fourth" and the like in the description and in the claims and drawings are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, result, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

First, referring to fig. 1, fig. 1 is a schematic hardware structure of an on-line problem solving apparatus according to an embodiment of the present application. The online problem solving apparatus 100 includes at least one processor 101, a communication line 102, a memory 103, and at least one communication interface 104.

In this embodiment, the processor 101 may be a general-purpose central processing unit (central processing unit, CPU), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program according to the present application.

Communication line 102 may include a pathway to transfer information between the above-described components.

The communication interface 104, which may be any transceiver-like device (e.g., antenna, etc.), is used to communicate with other devices or communication networks, such as ethernet, RAN, wireless local area network (wireless local area networks, WLAN), etc.

The memory 103 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (random access memory, RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ-only memory, EEPROM), a compact disc (compact disc read-only memory) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.

In this embodiment, the memory 103 may be independently provided and connected to the processor 101 via the communication line 102. Memory 103 may also be integrated with processor 101. The memory 103 provided by embodiments of the present application may generally have non-volatility. The memory 103 is used for storing computer-executable instructions for executing the scheme of the present application, and is controlled by the processor 101 to execute the instructions. The processor 101 is configured to execute computer-executable instructions stored in the memory 103 to implement the methods provided in the embodiments of the present application described below.

In alternative embodiments, computer-executable instructions may also be referred to as application code, as the application is not particularly limited.

In alternative embodiments, processor 101 may include one or more CPUs, such as CPU0 and CPU1 in fig. 1.

In alternative embodiments, the online problem-solving apparatus 100 may include a plurality of processors, such as the processor 101 and the processor 107 in fig. 1. Each of these processors may be a single-core (single-CPU) processor or may be a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (e.g., computer program instructions).

In an alternative embodiment, if the online problem-solving apparatus 100 is a server, for example, it may be a stand-alone server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery network (ContentDelivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platform. The online problem solving apparatus 100 may further include an output device 105 and an input device 106. The output device 105 communicates with the processor 101 and may display information in a variety of ways. For example, the output device 105 may be a Liquid Crystal Display (LCD) CRYSTAL DISPLAY, a Light Emitting Diode (LED) display device, a Cathode Ray Tube (CRT) display device, or a projector (projector), or the like. The input device 106 is in communication with the processor 101 and may receive user input in a variety of ways. For example, the input device 106 may be a mouse, a keyboard, a touch screen device, a sensing device, or the like.

The above-described on-line problem solving apparatus 100 may be a general-purpose device or a special-purpose device. Embodiments of the present application are not limited to the type of on-line problem-solving device 100.

Secondly, it should be noted that, the embodiment of the present disclosure may acquire and process related data based on artificial intelligence technology. Wherein artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results.

Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

The on-line problem solving method disclosed by the application will be described as follows:

Referring to fig. 2, fig. 2 is a flow chart of an on-line problem solving method according to an embodiment of the application. The on-line problem solving method comprises the following steps:

201: and acquiring first data according to the error reporting information of the on-line problem.

Generally, when a system reports an error, a corresponding expression is generated. For example: if a background url is requested and return 404, 302 or return value contains Exception or other exception keys, then the request is declared to be in error. Thus, in this embodiment, the system may monitor whether the returned information includes the error exception information, and if the corresponding error exception information is monitored, may automatically generate the error reporting information to report an error.

In an alternative embodiment, the error reporting information may also be triggered by the form of an error reporting by the system user. In particular, some faulty systems may not be perceived and therefore, system reporting of the fault may not be achieved. For example: the page is filled with a form of information, such as a "mail address". At this time, the user fills in data of one mail format, but the page directly prompts the user for "mail format error". For such errors, the system cannot autonomously perceive and therefore does not actively report errors. At this time, the user can trigger the error reporting process through the form of active reporting, and then generate error reporting information. In particular, the system may maintain an error-reporting window that may be accessed to submit a system problem when a user encounters a problem.

Meanwhile, in this embodiment, the first data is used to identify data of the operation of the system by the on-line personnel corresponding to the system after the error is reported. Illustratively, the first data may include: operation data, log data, and underlying data. The operation data can be a group of screenshot, which is an acquisition instruction triggered by error reporting information after the system reports errors, and acquired online personnel perform operation actions on the system after the system reports errors.

Specifically, in this embodiment, a method for acquiring first data according to error reporting information of an online problem is provided, as shown in fig. 3, and specifically includes:

301: and determining at least one display device corresponding to the system with the error according to the error reporting information.

In this embodiment, the display device is used to display the operation condition of the corresponding system to the on-line personnel, assist the on-line personnel to interact with the corresponding system, and display the feedback of the operation of the on-line personnel by the corresponding system.

302: And sending an acquisition instruction to each display device in the at least one display device, so that each display device performs screen capturing operation according to the acquisition instruction, and at least one screen capturing is obtained as operation data.

After the system reports errors, on-line personnel can process the error reporting system at the first time. Typically, these processes will display feedback in the form of a visual interface through a corresponding display. Therefore, in this embodiment, it is possible to monitor whether or not error and abnormality information occurs in the system, and if so, immediately trigger an automatic screen capturing operation of the corresponding display, and record page information and action information of an on-line person operating the system after reporting an error.

In an alternative embodiment, the operational data may also be a video recording. Specifically, when error abnormal information occurs in the system, the automatic screen recording operation of the corresponding display can be immediately triggered, and page information and action information of on-line personnel operating the system are recorded and reported for a period of time.

303: Determining occurrence time of error reporting information, and acquiring a system log of a system with errors in a first time period as log data according to the occurrence time.

In this embodiment, the first period may be determined by the occurrence time. By way of example, all system logs within 3 minutes before the error time may be intercepted.

304: And analyzing the log data to obtain at least one keyword.

In this embodiment, first, the log type of the log data may be acquired, and then, at least one candidate word included in the log data may be determined according to the log type. In particular, different types of log data contain different information, such as: the operating system log is often used for recording information of hardware, software and system problems in the system, and can monitor events occurring in the system; application logs are often used to record the running information of a corresponding application in a system. Based on this, for different log types, it is possible to determine in advance which of the information names corresponding to the information possibly related to the system error in the log of the type, and the information corresponding to these information names is the key information in the log data. Thus, when the log is analyzed, the corresponding information name can be quickly extracted as a candidate word according to the log type.

Then, a degree of association between each candidate word and the error information may be determined. At least one keyword is then determined among the at least one candidate word. Specifically, the association degree corresponding to each keyword in the screened at least one keyword is larger than a threshold value.

305: And grabbing the bottom-layer operation information of the system according to at least one keyword, and taking the grabbed operation information as bottom-layer data.

In this embodiment, the keywords in the log data may be: table names, column names, etc. Based on the above, according to the database configuration corresponding to the operation business in the error reporting system, some operation information of the bottom layer can be automatically captured through the obtained keywords to be used as the bottom layer data. For example, after the obtained log data is automatically analyzed, table names, primary keys and the like related to error reporting information can be obtained, then sql sentences are automatically generated according to the primary keys, and then all column data of the table are queried in a corresponding database.

Specifically, sql may be: select from table name where id= [ primary key ]. Thus, the corresponding result can be found by executing the sql. Wherein, the sql represents all columns, and the data of different tables are different, that is, the table defines several columns, so that the data of several columns can be found.

For example: the t_user table defines id, name, email, addr, age columns, and the searched data includes the 5 columns of data, which is specifically as follows:

id:1001

name:zhangwuji

email:skycloud@aa.com

addr, shanghai region

age:20

202: And extracting the characteristics of the first data according to the data type of the first data, and acquiring key characteristic information of the first data.

As can be seen from the above examples, the first data includes three data types, namely operation data, log data, and underlying data. In this embodiment, the analysis method to be adopted is also different for the first data of different data types. Specifically, the application provides a method for extracting features of first data according to the data type of the first data to obtain key feature information of the first data, as shown in fig. 4, the method includes:

401: and for each screenshot of the at least one screenshot, performing text recognition on each screenshot respectively to obtain at least one characteristic index as a first key characteristic index of the first data.

In this embodiment, the at least one feature index corresponds to at least one screenshot in a one-to-one manner. Specifically, for the text recognition result of each screenshot, key information features contained therein may be extracted, for example: the http request address returns a value such as "404", "302", exception and so on as the feature index corresponding to the screenshot.

402: And matching each screenshot with the historical error screenshot in the historical error reporting database according to the error reporting information, and calculating the similarity between each screenshot and the corresponding historical error screenshot to obtain at least one similarity as a second key characteristic index of the first data.

In this embodiment, the at least one similarity corresponds to the at least one screenshot one-to-one.

Meanwhile, the application provides a method for matching each screenshot with a historical error screenshot in a historical error reporting database according to error reporting information respectively, and calculating the similarity between each screenshot and the corresponding historical error screenshot, as shown in fig. 5, wherein the method comprises the following steps:

501: and screening the historical error reporting information which is the same as the error event of the error reporting information from the historical error reporting database according to the error reporting information.

Specifically, the error event corresponding to the error reporting information may be a historical error event that is historically the same as the error event reported by the current error reporting information.

502: And obtaining at least one historical error screenshot corresponding to the historical error reporting information.

In this embodiment, since the processing modes of the error events are the same, when the error event corresponding to the history error report information occurs, the corresponding acquisition instruction is triggered, and the same number of shots are acquired at the same frequency. In short, the number of the at least one historical error screenshot is the same as the number of the at least one screenshot.

503: And acquiring a first historical error screenshot corresponding to the first screenshot from at least one historical error screenshot.

In this embodiment, the first screenshot is any one of the at least one screenshot, and the first history error screenshot is in the order of the at least one history error screenshot and is the same as the order of the first screenshot in the at least one screenshot.

Specifically, since the number of at least one historical error screenshot is the same as the number of at least one screenshot, the at least one historical error screenshot is arranged in a time-series order. Thus, the same order screenshot is taken with the same time interval between the time that the screenshot was taken to occur from the error event. In short, the same order screen shots are taken after the same time interval after the time of occurrence of the error event.

For example, in the case of screenshot, a screenshot is performed in a rule of one graph per 2s, and 200 sheets are intercepted in total. The interception time of the 20 th screenshot is 38s after the error event occurs. Therefore, the same order means that the interception times are relatively identical, and therefore, in the present embodiment, the screen shots having the same order are associated. Specifically, the order 1 screenshot corresponds to the order 1 historical error screenshot, the order 2 screenshot corresponds to the order 2 historical error screenshot, and so on.

504: And calculating the similarity between the first screenshot and the corresponding first historical error screenshot.

In this embodiment, a method for calculating a similarity between a first screenshot and a corresponding first historical error screenshot is provided, as shown in fig. 6, where the method includes:

601: the first screenshot is partitioned into at least one subgraph.

In this embodiment, the first screenshot may be divided into 16 sub-images uniformly by a 4X4 method. Of course, other dividing methods may be applied to the present application, and the present application is not limited thereto.

602: And for each sub-graph in the at least one sub-graph, determining the weight of each sub-graph according to the position of each sub-graph in the first screenshot, and obtaining at least one weight.

In this embodiment, at least one weight corresponds to at least one sub-graph one by one. Along the example with the 16 subgraphs described above, each subgraph may be assigned a weight according to the distance of the center of each subgraph from the center of the first screenshot. That is, the closer the distance is, the greater the weight, and the farther the distance is, the smaller the weight.

In an alternative embodiment, the center of each sub-graph and the center of the first screenshot may be the center of gravity determined from the contour of the corresponding image.

603: And dividing the first historical error screenshot corresponding to the first screenshot into at least one historical error subgraph according to a dividing mode of the first screenshot.

604: And acquiring a first historical error subgraph corresponding to the first subgraph from the at least one historical error subgraph.

In this embodiment, the first sub-graph is any one of at least one sub-graph, and the position of the first history error sub-graph in the first history error screenshot is the same as the position of the first sub-graph in the first screenshot. In short, following the example of the above 16 sub-graphs, the divided sub-graphs are respectively numbered from left to right and from top to bottom, resulting in a numbered image as shown in fig. 7.

Thus, 16 historical error subgraphs of the first historical error screenshot divided in the same form are also numbered. That is, the numbers corresponding to the sub-graphs at the same position are the same. Therefore, the subgraphs with the same numbers and the historical error subgraphs are matched.

605: And respectively calculating the first similarity between each first sub-graph and the corresponding first historical error sub-graph finger to obtain at least one first similarity.

In this embodiment, at least one first similarity corresponds to at least one sub-graph one by one.

606: And carrying out weighted summation on at least one first similarity according to at least one weight to obtain the similarity between the first screenshot and the corresponding first historical error screenshot.

403: And extracting the characteristics of the log data to obtain at least one log characteristic serving as a third key characteristic index of the first data.

In this embodiment, the method for extracting features of the log data to obtain at least one log feature is similar to the method for extracting the keywords in the log data in step 304, and will not be described herein.

404: And querying the database according to the bottom data to obtain at least one query result as a fourth key characteristic index of the first data.

In this embodiment, the method for obtaining at least one query result by querying the database according to the underlying data is similar to the method for capturing the underlying operation information of the system in step 305, and will not be described herein.

405: And taking the first key characteristic index, the second key characteristic index, the third key characteristic index and the fourth key characteristic index as key characteristic information of the first data.

203: According to the key feature information, matching the solution.

In this embodiment, at least one historical error reporting event with the same error type as that of the error reporting information may be screened out from the historical error reporting database according to the error reporting information. Then, for each of the at least one historical error reporting event, a first historical key feature index, a second historical key feature index, a third historical key feature index and a fourth historical key feature index of each historical error reporting event are respectively obtained.

Based on this, a second similarity between the first key feature index and the first historical key feature index, a third similarity between the second key feature index and the second historical key feature index, a fourth similarity between the third key feature index and the third historical key feature index, and a fifth similarity between the fourth key feature index and the fourth historical key feature index are calculated.

And taking the historical error reporting event with the second similarity, the third similarity, the fourth similarity and the fifth similarity being larger than the first threshold value as a target alarm event to acquire a historical solution corresponding to the target alarm event. Finally, the history solution is taken as a matching solution.

204: And displaying the solution to the user and receiving feedback information of the user.

In this embodiment, the solution may be sent to the user's terminal device to present the solution to the user. The user referred to herein may be a decision maker of the system.

205: And matching at least one script combination in a preset script library according to the feedback information and the solution to obtain a solution script.

In this embodiment, if the user feedback information is confirmation, that is, the user sees the solution presented to the user and analyzes and confirms that the solution can be executed, it is described that the solution can be applied to the online problem that occurs currently without modification and adjustment. In this case, each script corresponding to the solution may be directly called in a preset script library, and combined according to the sequence of steps in the solution, to obtain a solution script. Specifically, in the present embodiment, a series of execution steps are described in the solution in order of execution, and each execution step corresponds to one execution script. Based on the above, the corresponding script of each execution step can be matched in the preset script library through the corresponding relation, and the matched scripts are combined according to the arrangement sequence of the corresponding execution steps in the solution, so as to obtain the solution script.

For solution a, an execution scheme is recorded, illustratively: step 1 is executed first, step 2 is executed then, step 3 is executed again, and step 4 is executed finally. Meanwhile, the solution a records that the script corresponding to the step 1 is the script 5, the script corresponding to the step 2 is the script 5, the script corresponding to the step 3 is the script 1, and the script corresponding to the step 4 is the script 20. Based on this, according to the correspondence, script 1, script 5, script 9 and script 20 are extracted from a preset script library, and according to the ordering of the corresponding steps in the solution, namely: step 1, step 2, step 3 and step 4 are combined in sequence, and then the script execution sequence is obtained: script 5, script 9, script 1, and script 20 as a solution script.

Also, in this embodiment, if the feedback information is to be modified, that is, the user is seeing the solution presented to him, and analyzing and confirming that the solution is insufficient to solve the current on-line problem requires corresponding modification or adjustment. In this case, the feedback information also includes modification advice, based on which certain steps in the solution can be replaced according to the modification advice in the feedback information, and a new solution can be obtained. In particular, the modification suggestion may include a location in the solution of a step that needs to be modified and a storage location of a script corresponding to the modified step.

Therefore, each corresponding script is called according to the new solution, and the corresponding scripts are combined according to the sequence of the steps in the new solution, so that the solution script is obtained. The specific combination mode is consistent with the combination mode of the feedback information when the error is confirmed, and the detailed description is omitted.

206: And running a solving script to solve the online problem.

In summary, in the on-line problem solving method provided by the invention, when a problem occurs in an on-line system, the first data of the operation of the system, which is performed by the on-line personnel corresponding to the error reporting of the identification system, is automatically acquired for AI identification, and then the corresponding key characteristic information is obtained. Then, matching similar solved problems through comparison of key characteristic information, and then using the solution of the solved problems as a reference solution of the error, and displaying the solution to a user. And finally, acquiring a corresponding script combination to be a solution script through feedback information of a user and combining a solution, and running the solution script to solve the problem of on-line system occurrence. Therefore, when an online system goes wrong, the operation information of an online person after the online system goes wrong is automatically reported, and compared with the prior art that the online person reports the operation information after the online system goes wrong, the accuracy and timeliness are higher. Meanwhile, the acquired data can be automatically analyzed, and then the corresponding solution which is automatically matched according to the analysis result is displayed to the system responsible person, so that the system responsible person only needs to confirm whether the solution is normal or not, if so, the system responsible person can directly run, the system responsible person is not required to compose the solution from 0, the professional requirements on the responsible person are reduced, the labor cost is further reduced, and meanwhile, the automatic solution of the on-line problem is realized.

Referring to fig. 8, fig. 8 is a functional block diagram of an on-line problem solving apparatus according to an embodiment of the present application. As shown in fig. 8, the online problem solving apparatus 800 includes:

The acquisition module 801 is configured to acquire first data according to error reporting information of an online problem, where the first data is used to identify data of an operation of a system by online personnel corresponding to the error reporting of the system;

the identification module 802 is configured to perform feature extraction on the first data according to a data type of the first data, and obtain key feature information of the first data;

A matching module 803 for matching the solution according to the key feature information;

the display module 804 is configured to display a solution to a user and receive feedback information of the user;

The solution module 805 is configured to match at least one script combination in a preset script library to be a solution script according to the feedback information and the solution, and run the solution script to solve the online problem.

In an embodiment of the present invention, the first data may include: operation data, log data and underlying data;

based on this, in acquiring the first data according to the error information of the on-line problem, the acquisition module 801 is specifically configured to:

according to the error reporting information, determining at least one display device corresponding to the system with the error;

Sending an acquisition instruction to each display device in the at least one display device, so that each display device performs screen capturing operation according to the acquisition instruction to obtain at least one screen capturing as operation data;

Determining occurrence time of error reporting information, and acquiring a system log of a system with errors in a first time period as log data according to the occurrence time, wherein the first time period is determined by the occurrence time;

analyzing the log data to obtain at least one keyword;

And grabbing the bottom-layer operation information of the system according to at least one keyword, and taking the grabbed operation information as bottom-layer data.

In the embodiment of the present invention, in analyzing the log data to obtain at least one keyword, the collecting module 801 is specifically configured to:

Acquiring a log type of log data;

Determining at least one candidate word contained in the log data according to the log type, wherein each candidate word in the at least one candidate word is an information name corresponding to key information in the log data;

Determining the association degree between each candidate word and the error reporting information;

at least one keyword is determined in the at least one candidate word, wherein the association degree corresponding to each keyword in the at least one keyword is larger than a threshold value.

In an embodiment of the present invention, in extracting features of the first data according to the data type of the first data, to obtain key feature information of the first data, the identifying module 802 is specifically configured to:

For each screenshot of the at least one screenshot, respectively performing text recognition on each screenshot to obtain at least one characteristic index as a first key characteristic index of the first data, wherein the at least one characteristic index corresponds to the at least one screenshot one by one;

matching each screenshot with a historical error screenshot in a historical error reporting database according to error reporting information, and calculating the similarity between each screenshot and the corresponding historical error screenshot to obtain at least one similarity as a second key characteristic index of the first data, wherein the at least one similarity corresponds to the at least one screenshot one by one;

extracting features of the log data to obtain at least one log feature serving as a third key feature index of the first data;

Inquiring a database according to the bottom data to obtain at least one inquiry result as a fourth key characteristic index of the first data;

And taking the first key characteristic index, the second key characteristic index, the third key characteristic index and the fourth key characteristic index as key characteristic information of the first data.

In an embodiment of the present invention, in terms of matching each screenshot with a history error screenshot in a history error database according to error reporting information, and calculating a similarity between each screenshot and a corresponding history error screenshot, the identifying module 802 is specifically configured to:

according to the error reporting information, historical error reporting information which is the same as the error event of the error reporting information is screened out from a historical error reporting database;

acquiring at least one historical error screenshot corresponding to the historical error information, wherein the number of the at least one historical error screenshot is the same as that of the at least one screenshot;

Acquiring a first historical error screenshot corresponding to a first screenshot from at least one historical error screenshot, wherein the first screenshot is any one of the at least one screenshot, and the first historical error screenshot is in the same order of the at least one historical error screenshot as the first screenshot in the at least one screenshot;

and calculating the similarity between the first screenshot and the corresponding first historical error screenshot.

In an embodiment of the present invention, the identifying module 802 is specifically configured to, in calculating a similarity between the first screenshot and the corresponding first historical error screenshot:

Dividing the first screenshot into at least one sub-graph;

for each sub-graph in at least one sub-graph, determining the weight of each sub-graph according to the position of each sub-graph in the first screenshot, and obtaining at least one weight, wherein the at least one weight corresponds to the at least one sub-graph one by one;

Dividing a first historical error screenshot corresponding to the first screenshot into at least one historical error subgraph according to a dividing mode of the first screenshot;

Acquiring a first historical error subgraph corresponding to the first subgraph from at least one historical error subgraph, wherein the first subgraph is any one of the at least one subgraph, and the position of the first historical error subgraph in the first historical error screenshot is the same as the position of the first subgraph in the first screenshot;

respectively calculating first similarity between each first sub-graph and the corresponding first historical error sub-graph finger to obtain at least one first similarity, wherein the at least one first similarity corresponds to the at least one sub-graph one by one;

And carrying out weighted summation on at least one first similarity according to at least one weight to obtain the similarity between the first screenshot and the corresponding first historical error screenshot.

In an embodiment of the present invention, the solution module 805 is specifically configured to:

Screening at least one historical error reporting event with the same error type as the error reporting information from the historical error reporting database according to the error reporting information;

For each history error reporting event in at least one history error reporting event, respectively acquiring a first history key feature index, a second history key feature index, a third history key feature index and a fourth history key feature index of each history error reporting event;

calculating a second similarity between the first key feature index and the first historical key feature index;

calculating a third similarity between the second key feature index and the second historical key feature index;

calculating a fourth similarity between the third key feature index and the third historical key feature index;

calculating a fifth similarity between the fourth key feature index and the fourth historical key feature index;

Determining a target alarm event in at least one historical error reporting event according to the second similarity, the third similarity, the fourth similarity and the fifth similarity, wherein the second similarity, the third similarity, the fourth similarity and the fifth similarity corresponding to the target alarm event are all larger than a first threshold;

Acquiring a historical solution corresponding to a target alarm event;

Historical solutions are taken as matching solutions.

Referring to fig. 9, fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 9, the electronic device 900 includes a transceiver 901, a processor 902, and a memory 903. Which are connected by a bus 904. The memory 903 is used to store computer programs and data, and the data stored in the memory 903 may be transferred to the processor 902.

The processor 902 is configured to read a computer program in the memory 903 to perform the following operations:

According to the key characteristic information, matching the solution;

and running a solving script to solve the online problem.

based on this, the processor 902 is specifically configured to perform the following operations in acquiring the first data according to the error information of the online problem:

analyzing the log data to obtain at least one keyword;

In an embodiment of the present invention, the processor 902 is specifically configured to, in analyzing the log data to obtain at least one keyword:

Acquiring a log type of log data;

In an embodiment of the present invention, the processor 902 is specifically configured to perform the following operations in terms of extracting features of the first data according to the data type of the first data and obtaining key feature information of the first data:

In an embodiment of the present invention, the processor 902 is specifically configured to perform the following operations in terms of matching each screenshot with a history error screenshot in the history error database according to the error reporting information, and calculating a similarity between each screenshot and a corresponding history error screenshot, where the similarity is calculated by the processor according to the error reporting information:

In an embodiment of the present invention, the processor 902 is specifically configured to, in calculating the similarity between the first screenshot and the corresponding first historical error screenshot, perform the following operations:

Dividing the first screenshot into at least one sub-graph;

In an embodiment of the present invention, the processor 902 is specifically configured to perform the following operations in terms of matching solutions based on key feature information:

Acquiring a historical solution corresponding to a target alarm event;

Historical solutions are taken as matching solutions.

It should be understood that the online problem solving apparatus in the present application may include a smart Phone (such as an Android Phone, an iOS Phone, a Windows Phone, etc.), a tablet computer, a palm computer, a notebook computer, a Mobile internet device MID (Mobile INTERNET DEVICES, abbreviated as MID), a robot, a wearable device, etc. The above-described in-line problem-solving means are merely examples and are not exhaustive, including but not limited to the above-described in-line problem-solving means. In practical applications, the above-mentioned on-line problem solving apparatus may further include: intelligent vehicle terminals, computer devices, etc.

From the above description of embodiments, it will be apparent to those skilled in the art that the present invention may be implemented in software in combination with a hardware platform. With such understanding, all or part of the technical solution of the present invention contributing to the background art may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the methods described in the various embodiments or parts of the embodiments of the present invention.

Accordingly, embodiments of the present application also provide a computer-readable storage medium storing a computer program that is executed by a processor to implement some or all of the steps of any one of the on-line problem solving methods described in the above-described method embodiments. For example, the storage medium may include a hard disk, a floppy disk, an optical disk, a magnetic tape, a magnetic disk, a flash memory, etc.

The present application also provides a computer program product comprising a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the on-line problem-solving methods described in the method embodiments above.

It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are alternative embodiments, and that the acts and modules involved are not necessarily required for the present application.

In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, such as the division of the units, merely a logical function division, and there may be additional divisions when actually implemented, such as multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, or may be in electrical or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units described above may be implemented either in hardware or in software program modules.

The integrated units, if implemented in the form of software program modules, may be stored in a computer-readable memory for sale or use as a stand-alone product. Based on this understanding, the technical solution of the present application may be embodied essentially or partly in the form of a software product or all or part of the technical solution, which is stored in a memory, and includes several instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned memory includes: a usb disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Those of ordinary skill in the art will appreciate that all or a portion of the steps in the various methods of the above embodiments may be implemented by a program that instructs associated hardware, and the program may be stored in a computer readable memory, and the memory may include: flash disk, read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk.

The foregoing has outlined rather broadly the more detailed description of the embodiments of the application in order that the detailed description of the principles and embodiments of the application may be implemented in conjunction with the detailed description of the embodiments that follows, the claims being merely intended to facilitate the understanding of the method and concepts underlying the application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

Claims

1. An on-line problem solving method, characterized in that the method comprises:

determining at least one display device corresponding to the system with the error according to the error reporting information of the on-line problem;

Sending an acquisition instruction to each display device in the at least one display device, so that each display device performs screen capturing operation according to the acquisition instruction to obtain at least one screenshot as operation data, wherein the at least one screenshot is used for recording page information and action information of on-line personnel operating a system after error reporting;

Determining the occurrence time of the error reporting information, and acquiring a system log of the error generating system in a first time period as log data according to the occurrence time, wherein the first time period is determined by the occurrence time;

analyzing the log data to obtain at least one keyword;

Grabbing bottom layer operation information of the system with the error according to the at least one keyword, and taking the grabbed operation information as bottom layer data;

The operation data, the log data and the bottom data are used as first data, wherein the first data are used for identifying data of operations of on-line personnel corresponding to the system with the error after the system is in error;

Extracting features of the first data according to the data type of the first data to obtain key feature information of the first data;

according to the key characteristic information, matching a solution;

displaying the solution to a user and receiving feedback information of the user;

running the solution script to solve the online problem;

The feature extraction is performed on the first data according to the data type of the first data, and key feature information of the first data is obtained, including:

Matching each screenshot with a historical error screenshot in a historical error reporting database according to the error reporting information, and calculating the similarity between each screenshot and the corresponding historical error screenshot to obtain at least one similarity as a second key characteristic index of the first data, wherein the at least one similarity corresponds to the at least one screenshot one by one;

And taking the first key feature index, the second key feature index, the third key feature index and the fourth key feature index as key feature information of the first data.

2. The method of claim 1, wherein the analyzing the log data to obtain at least one keyword comprises:

acquiring the log type of the log data;

And determining the at least one keyword in the at least one candidate word, wherein the association degree corresponding to each keyword in the at least one keyword is larger than a threshold value.

3. The method according to claim 1, wherein the matching each screenshot with a history error screenshot in the history error database according to the error reporting information, and calculating a similarity between each screenshot and a corresponding history error screenshot, includes:

according to the error reporting information, historical error reporting information which is the same as the error event of the error reporting information is screened out from the historical error reporting database;

Acquiring a first historical error screenshot corresponding to a first screenshot from the at least one historical error screenshot, wherein the first screenshot is any one of the at least one screenshot, and the order of the first historical error screenshot in the at least one historical error screenshot is the same as the order of the first screenshot in the at least one screenshot;

4. The method of claim 3, wherein the calculating a similarity between the first screenshot and the corresponding first historical error screenshot comprises:

Dividing the first screenshot into at least one sub-graph;

For each sub-graph in the at least one sub-graph, determining the weight of each sub-graph according to the position of each sub-graph in the first screenshot, and obtaining at least one weight, wherein the at least one weight corresponds to the at least one sub-graph one by one;

dividing the first historical error screenshot corresponding to the first screenshot into at least one historical error subgraph according to the dividing mode of the first screenshot;

Acquiring a first historical error subgraph corresponding to a first subgraph from the at least one historical error subgraph, wherein the first subgraph is any one of the at least one subgraph, and the position of the first historical error subgraph in the first historical error screenshot is the same as the position of the first subgraph in the first screenshot;

Respectively calculating first similarity between each first sub-graph and a corresponding first historical error sub-graph finger to obtain at least one first similarity, wherein the at least one first similarity corresponds to the at least one sub-graph one by one;

And carrying out weighted summation on the at least one first similarity according to the at least one weight to obtain the similarity between the first screenshot and the corresponding first historical error screenshot.

5. The method according to any of claims 1-4, wherein said matching a solution based on said key feature information comprises:

For each history error reporting event in the at least one history error reporting event, respectively acquiring a first history key feature index, a second history key feature index, a third history key feature index and a fourth history key feature index of each history error reporting event;

Calculating a second similarity between the first key feature indicator and the first historical key feature indicator;

calculating a fourth similarity between the third key feature indicator and the third historical key feature indicator;

Determining a target alarm event in the at least one historical error reporting event according to the second similarity, the third similarity, the fourth similarity and the fifth similarity, wherein the second similarity, the third similarity, the fourth similarity and the fifth similarity corresponding to the target alarm event are all larger than a first threshold;

acquiring a historical solution corresponding to the target alarm event;

the historical solution is taken as the matching solution.

6. An on-line problem solving apparatus, characterized in that the apparatus comprises:

The acquisition module is used for determining at least one display device corresponding to the system with the error according to the error reporting information of the online problem; sending an acquisition instruction to each display device in the at least one display device, so that each display device performs screen capturing operation according to the acquisition instruction to obtain at least one screenshot as operation data, wherein the at least one screenshot is used for recording page information and action information of on-line personnel operating a system after error reporting; determining the occurrence time of the error reporting information, and acquiring a system log of the error generating system in a first time period as log data according to the occurrence time, wherein the first time period is determined by the occurrence time; analyzing the log data to obtain at least one keyword; grabbing bottom layer operation information of the system with the error according to the at least one keyword, and taking the grabbed operation information as bottom layer data; the operation data, the log data and the bottom data are used as first data, wherein the first data are used for identifying data of operations of on-line personnel corresponding to the system with the error after the system is in error;

the display module is used for displaying the solution to a user and receiving feedback information of the user;

the solution module is used for matching at least one script combination in a preset script library to form a solution script according to the feedback information and the solution, and running the solution script to solve the online problem;

The identification module is configured to, in terms of extracting features of the first data according to the data type of the first data and obtaining key feature information of the first data:

7. An electronic device comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured for execution by the processor, the one or more programs comprising instructions for performing the steps of the method of any of claims 1-5.

8. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program, which is executed by a processor to implement the method of any of claims 1-5.