Production problem inspection method and device based on Markov chain

Abstract

The present invention discloses a production problem inspection method and device based on Markov chain, which relates to the field of big data technology, wherein the method comprises: receiving the current production problem number input by the user; determining the flowchart corresponding to the current production problem number according to the current production problem number and a pre-established branch diagram for assisting in the inspection of production problems; the branch diagram includes the operation behaviors recorded in the form of Markov chain when multiple staff members exceeding a preset level inspect historical production problems; and displaying the corresponding nodes and / or lines in the flowchart in a preset prominent display mode according to the operation behaviors of the user inspecting the current production problem. The present invention can display the operation behaviors of staff members exceeding the preset level in real time during the production problem inspection process, which improves the accuracy and safety of production problem inspection and reduces the operation and maintenance costs compared to experienced staff members personally guiding the problem analysis.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a production problem inspection method and device based on Markov chain. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] The current production problem analysis assistance technology mainly focuses on AI (Artificial Intelligence), establishing an automated operation and maintenance platform, using AI to automatically analyze the causes of problems, and automatically solving some production problems. The defects of AI in solving and analyzing production problems are as follows:

[0004] 1. AI features require a large number of samples for learning, but the fewer production problems there are, the better. In addition, the probability of production problems occurring will be reduced as much as possible during the software production process. Therefore, this is a fundamental contradiction. We can only rely on problems actively created by humans and problems discovered during the development and testing process. The sample coverage is limited and the reliability is low.

[0005] 2. The instability of AI itself and the possibility of misjudgment may further expand the risks brought by the original production problems and cause more losses.

[0006] In summary, the existing production problem inspection methods have low accuracy and security, and high operation and maintenance costs. Summary of the invention

[0007] The embodiment of the present invention provides a production problem detection method based on Markov chain, which is used to improve the accuracy and safety of production problem detection and reduce operation and maintenance costs. The method includes:

[0008] Receiving a current production problem number input by a user; the production problem number is pre-assigned according to a business type and a technical type;

[0009] Determine the flowchart corresponding to the current production problem number according to the current production problem number and a pre-established branch diagram for assisting in checking production problems; the branch diagram includes operation behaviors recorded in the form of a Markov chain when multiple staff members exceeding a preset level check historical production problems;

[0010] According to the user's operational behavior of checking the current production problem, the corresponding nodes and / or lines in the flowchart are displayed in a preset highlighting manner.

[0011] The embodiment of the present invention further provides a production problem inspection device based on a Markov chain, which is used to improve the accuracy and safety of production problem inspection and reduce operation and maintenance costs. The device includes:

[0012] A receiving unit, used to receive a current production problem number input by a user; the production problem number is pre-assigned according to a business type and a technical type;

[0013] A determination unit, configured to determine a flow chart corresponding to the current production problem number according to the current production problem number and a pre-established branch diagram for assisting in checking the production problem; the branch diagram includes operation behaviors recorded in the form of a Markov chain when a plurality of staff members exceeding a preset level check historical production problems;

[0014] The auxiliary display unit is used to display the corresponding nodes and / or lines in the flow chart in a preset prominent display manner according to the user's operation behavior of checking the current production problem.

[0015] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned Markov chain-based production problem inspection method when executing the computer program.

[0016] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for executing the above-mentioned Markov chain-based production problem inspection method.

[0017] In an embodiment of the present invention, a production problem inspection scheme based on a Markov chain, compared with the technical scheme in the prior art that requires a large number of samples for learning to inspect AI production problems, has low accuracy, low security and high operation and maintenance costs, comprises: receiving a current production problem number input by a user; the production problem number is pre-assigned according to the business type and the technical type; determining a flowchart corresponding to the current production problem number according to the current production problem number and a pre-established branch graph for assisting in inspecting production problems; the branch graph includes operational behaviors recorded in the form of a Markov chain when multiple staff members exceeding a preset level inspect historical production problems; according to the operational behaviors of the user inspecting the current production problem, the corresponding nodes and / or lines in the flowchart are displayed in a preset prominent display manner, so that the operational behaviors of the staff members exceeding the preset level can be displayed in real time during the production problem inspection process, which improves the accuracy and security of the production problem inspection and reduces the operation and maintenance costs compared to experienced staff members personally guiding the problem analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0019] Figure 1 Schematic diagram of the process of the production problem inspection method based on Markov chain in an embodiment of the present invention;

[0020] Figure 2 A schematic diagram of a branch diagram for assisting in checking production problems in an embodiment of the present invention;

[0021] Figure 3 A schematic diagram of a process of pre-establishing the branch graph in an embodiment of the present invention;

[0022] Figure 4 A schematic diagram of a process of pre-establishing the branch graph in another embodiment of the present invention;

[0023] Figure 5 Schematic diagram of the structure of a production problem inspection device based on Markov chain in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0025] Before introducing the embodiments of the present invention, the terms involved in the embodiments of the present invention are first introduced.

[0026] 1. Markov Chain (MC): It is a random process in probability theory and mathematical statistics that has Markov properties and exists in discrete exponential sets and state spaces.

[0027] 2. Production problems: Software products need to undergo testing and verification in several environments, such as development, function, and simulation during the development and testing process. After passing the test, the formal environment used by customers and bank staff is the production environment. Problems that occur in production (including program code problems, hardware failure problems, and staff operation problems) are collectively referred to as production problems.

[0028] 3. Production problem analysis platform: Analysis of production problems requires information such as program logs and database data. The required data is often scattered. In order to facilitate developers to analyze problems, a production problem analysis platform will be established. Almost all the data needed to analyze production problems can be viewed on the platform, and various security mechanisms such as encryption are provided.

[0029] The embodiment of the present invention is mainly to reduce the time cost and the probability of misjudgment of developers in the process of analyzing production problems, and reduce the manpower cost invested in operation and maintenance. Therefore, the embodiment of the present invention proposes a production problem inspection solution based on Markov chain, which is a production problem inspection platform auxiliary solution based on Markov chain. The production problem inspection solution based on Markov chain is introduced in detail below.

[0030] Figure 1 FIG. 1 is a flow chart of a method for inspecting production problems based on a Markov chain in an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0031] Step 101: receiving a current production problem number input by a user; the production problem number is pre-assigned according to business type and technical type;

[0032] Step 102: Determine a flowchart corresponding to the current production problem number according to the current production problem number and a pre-established branch diagram for assisting in checking production problems; the branch diagram includes operation behaviors recorded in the form of a Markov chain when a plurality of staff members exceeding a preset level check historical production problems;

[0033] Step 103: Based on the user's operation behavior of checking the current production problem, the corresponding nodes and / or lines in the flowchart are displayed in a preset highlighting manner.

[0034] The Markov chain-based production problem inspection method provided by the embodiment of the present invention can display the operation behavior of the staff exceeding the preset level in real time during the production problem inspection process, which improves the accuracy and safety of the production problem inspection and reduces the operation and maintenance cost compared with the experienced staff personally guiding the problem analysis. The various steps involved in the method are described in detail below.

[0035] The basic core concept of the embodiment of the present invention is to make the analysis process of experienced developers better reference for less experienced developers. The core is divided into two parts: learning the analysis process of experienced developers (collecting data, that is, the process of pre-establishing branch graphs) and the auxiliary troubleshooting application part (that is, the actual inspection steps) for other developers to refer to. The following is a detailed introduction.

[0036] 1. First, we will introduce the part of collecting data, which is the step of building a branch diagram in advance.

[0037] 1.1. The developer uses the production problem analysis platform (the production problem inspection device based on Markov chain provided by the embodiment of the present invention), inputs the production problem number (i.e., step 201 below), and determines whether the employee is an experienced employee (developer above level xx, i.e., staff above the preset level, i.e., step 202 below). If yes, start recording, otherwise, end directly. The process of allocating production problem numbers can be: design a set of production problem classification numbering mechanism for the problem, and the corresponding number can be corresponded when the production problem occurs, and the number is allocated according to the business type and technical type. For example, a corresponding relationship between the production problem number and the business type and technical type is pre-designed. When a production problem is received, the business type and technical type of the production problem are first determined, and then the business type and technical type of the production problem are searched in the above corresponding relationship, and the production problem number is matched, that is, a production problem number is allocated to the received production problem. Regarding determining whether the employee is an experienced employee, the specific process can be: match the production problem number to the relationship between the production problem number and the staff level, and obtain the staff level corresponding to the production problem number. The relationship between the production problem number and the staff level can also be a table, or of course, a relational model.

[0038] 1.2. Record the operations performed by the developers (staff) in sequence, such as Figure 2 As shown, such as which SQL statement was used to check the database in the first step, and which keywords were used to check the log in the second step.

[0039] 1.3. Record to database, such as Figure 2 As shown, it is recorded in the form of a Markov chain, where the first choice is the problem number entered in the above step "1.1", and each operation in step "1.2" starts with the second choice (where the "problem number" column belongs to the first choice; the next step directly after the problem number is the second choice, and the next step directly after the second choice is the third choice. The second, third, fourth, ... N choices are of the same nature and are all specific operations for troubleshooting problems).

[0040] In specific implementation, the above steps "1.2" and "1.3" are the detailed implementation methods of the following step 203.

[0041] 1.4. Arrange and count the process relationships, i.e., the following steps 204 and 205, as Figure 2As shown, if the first choice is to enter the problem number numbered xxxx, then the next step is how many percent of people (one person checking a production problem once is counted as one person, and two different people checking the same production problem as long as they use two different accounts to log in are counted as two people) use a certain SQL statement to check the database, and how many percent of people use which keywords to check the log; then if you choose to use a certain SQL statement, how many percent (proportion) of people use a certain SQL statement to check the database, and how many percent of people use which keywords to check the log; and so on (choices with a proportion below 5% are skipped and not displayed, and the optimal branch diagram is obtained.

[0042] From the above, it can be seen that in one embodiment, if Figure 3 As shown, the above-mentioned production problem inspection method based on Markov chain can also include pre-establishing the branch graph according to the following method:

[0043] Step 201: Obtaining a production problem number when a staff member checks a historical production problem; the production problem number is pre-assigned according to a business type and a technical type;

[0044] Step 202: Determine the staff level corresponding to the production problem number when checking historical production problems, according to the production problem number when checking historical production problems, and the relationship between the production problem number and the staff level;

[0045] Step 203: When it is determined that the staff level corresponding to the production problem number when checking the historical production problem exceeds the preset level, all the operation behaviors of the staff in checking the historical production problem are recorded in the form of a Markov chain; wherein the first selection is the problem number, each selection starting from the second selection is each operation behavior of checking the production problem, and each selection starting from the second selection includes multiple sub-selections with the same attributes (equivalent to each selection starting from the second selection being a layer of selection, and the layer of selection includes multiple sub-selections, such as Figure 2 "Use XX keyword to check XX log" is a sub-selection, and "use XXsql statement to check database" is a sub-selection. These two sub-selections belong to the second selection, which is equivalent to the second-level operation behavior record);

[0046] Step 204: determining the proportion of the operation behaviors of multiple staff members who check historical production problems exceeding a preset level corresponding to each sub-selection;

[0047] Step 205: Based on the operation behaviors recorded according to the Markov chain and the ratio, a branch graph for assisting in checking production problems is formed, and the branch graph is stored in a database.

[0048] In addition, in one embodiment, Figure 4As shown, based on the operation behavior recorded according to the Markov chain and the ratio, a branch graph for assisting in the inspection of production problems is formed, and the branch graph is stored in a database, which may include step 2051: deleting the branches corresponding to the sub-selections in the branch graph that are smaller than a preset ratio to obtain a preferred branch graph; and storing the preferred branch graph in the database to further improve the accuracy and efficiency of the inspection of production problems.

[0049] 2. Next, we will introduce the application part for other developers to refer to for auxiliary troubleshooting, that is, the steps of using the pre-established branch graph to check production problems.

[0050] 2.1. The developer uses the production problem analysis platform and enters the problem number, which is step 101 above.

[0051] 2.2. Find the subsequent operation flow of the problem number that is the first choice input from the database (that is, the flow chart corresponding to the current production problem number, for example Figure 2 The subsequent flowchart of the branch corresponding to the problem number 1 in the problem is displayed on the right side of the program interface (preset position) (selections with a share of less than 5% are skipped and not displayed), and the operation of each step is displayed in the form of a branch diagram, and the percentage of people who have the corresponding step. That is, in one embodiment, according to the user's operation behavior of checking the current production problem, the corresponding nodes and / or lines in the flowchart are displayed in a preset prominent display manner, which may include: according to the user's operation behavior of checking the current production problem, at a preset position, the corresponding nodes and / or lines in the flowchart are displayed in a preset prominent display manner.

[0052] 2.3. Figure 2 For example, a problem numbered 1 occurs. When troubleshooting, enter "problem number 1" first. At this time, it shows that x% of people use xx (here xx is assumed to be "account reconciliation error") to check xx (here xx is assumed to be system_out.log log file) log, y% of people use xx sql statement to check the database, and z% of people do xx operation; if the number of users takes an operation other than these three operations, the operation items displayed on the interface will remain here until an operation similar to these three operations is taken; if the keyword "account reconciliation error" (50% of the same keywords are considered the same operation, and 50% is the set threshold) is used to check system_out.log at this time, it will show that x% of people use yy keyword to check yy log, y% of people use yy sql statement to check the database, and z% of people do yy operation; (assuming that Figure 2 Only 3 layers of operations are recorded) At this time, if you use the yy keyword to check the yy log, the subsequent operations will no longer be displayed (because there is nothing behind).

[0053] In specific implementation, the above “2.2” and “2.3” are the detailed implementation methods of step 102.

[0054] 2.4. If the developer follows the process on the branch diagram, the lines and / or nodes of the corresponding branches are highlighted; if the operation is separated from the branch in the middle, the currently highlighted part is kept unchanged; if the developer returns to the point of the operation that was separated, and the next step is one of the displayed branches, the highlighting is restarted. For example: if the current point is to query the log with the keyword "accounting abnormality", the next step displayed at this time is that 75% of people choose to use "select * from accounting table" to query the database, 22% of people use "accounting details" to query the log, and you check javacore. At this time, the point "querying the log with the keyword "accounting abnormality"" is highlighted. If similar operations such as "using "select * from accounting table" to query the database" or "using "accounting details" to query the log" are performed later, then the corresponding point of the operation will continue to be highlighted, that is, the above step 103.

[0055] From the above, it can be seen that in one embodiment, based on the user's operational behavior of checking the current production problem, the corresponding nodes and / or lines in the flowchart are displayed in a preset highlighting manner, which may include: if the operational behavior of the current production problem is separated from the current branch, keeping the nodes and / or lines displayed in the current highlighting manner unchanged.

[0056] From the above, it can be seen that in one embodiment, the above-mentioned Markov chain-based production problem inspection method may also include: if you return to the node and / or line corresponding to the operational behavior of the current production problem that has been detached, and it is determined that the next selection is one of the branches currently displayed, restart the display in a preset highlighted display manner.

[0057] As can be seen from the above, in one embodiment, the preset highlighting display mode can be a display mode with brightness exceeding a preset value. The highlighting display mode helps to more clearly display the operation of experienced staff to troubleshoot production problems in real time, helping staff to check production problems more efficiently.

[0058] The beneficial effect of the Markov chain-based production problem inspection method provided by the embodiment of the present invention is that the experience of experienced developers is displayed in real time during the analysis process, which can reduce manpower input compared to experienced employees personally guiding the problem analysis. At the same time, it can also allow inexperienced employees to avoid detours in the problem analysis process, for example, they can avoid checking some unnecessary information, reduce manpower input, and improve the accuracy of analysis. For example, by allowing developers (staff) not to look at some information that is actually not needed, they can reduce their focus on the problem and prevent being misled by some information.

[0059] The embodiment of the present invention also provides a production problem inspection device based on Markov chain, as described in the following embodiment. Since the principle of solving the problem by the device is similar to the production problem inspection method based on Markov chain, the implementation of the device can refer to the implementation of the production problem inspection method based on Markov chain, and the repeated parts will not be repeated.

[0060] Figure 5 FIG. 1 is a schematic diagram of the structure of a production problem inspection device based on a Markov chain in an embodiment of the present invention. Figure 5 As shown, the production problem inspection device based on Markov chain includes:

[0061] Receiving unit 01, used to receive the current production problem number input by the user; the production problem number is pre-assigned according to the business type and the technical type;

[0062] Determining unit 02, used to determine the flow chart corresponding to the current production problem number according to the current production problem number and a pre-established branch diagram for assisting in checking the production problem; the branch diagram includes operation behaviors recorded in the form of a Markov chain when a plurality of staff members exceeding a preset level check historical production problems;

[0063] The auxiliary display unit 03 is used to display the corresponding nodes and / or lines in the flow chart in a preset prominent display manner according to the user's operation behavior of checking the current production problem.

[0064] In one embodiment, the Markov chain-based production problem inspection device may further include an establishment unit for pre-establishing the branch graph according to the following method:

[0065] Obtaining a production problem number when a staff member checks a historical production problem; the production problem number is pre-assigned according to a business type and a technical type;

[0066] According to the production problem number when checking historical production problems, and the relationship between the production problem number and the staff level, determine the staff level corresponding to the production problem number when checking historical production problems;

[0067] When it is determined that the staff level corresponding to the production problem number when checking historical production problems exceeds the preset level, all the operation behaviors of the staff in checking historical production problems are recorded in the form of a Markov chain; wherein the first choice is the problem number, each choice starting from the second choice is each operation behavior of checking the production problem, and each choice starting from the second choice includes multiple sub-choices with the same attributes;

[0068] Determine the proportion of operational behaviors of multiple staff members checking historical production problems exceeding a preset level corresponding to each sub-selection;

[0069] According to the operation behaviors recorded by the Markov chain and the ratio, a branch diagram for assisting in checking production problems is formed, and the branch diagram is stored in a database.

[0070] In one embodiment, a branch graph for assisting in checking production problems is formed based on the operation behaviors recorded according to the Markov chain and the ratio, and the branch graph is stored in a database, which may include: deleting branches corresponding to sub-selections in the branch graph that are smaller than a preset ratio to obtain a preferred branch graph; and storing the preferred branch graph in the database.

[0071] In one embodiment, the auxiliary display unit is specifically used for: if the operation behavior of the current production problem is out of the current branch, keeping the nodes and / or lines displayed in the current highlighting display mode unchanged.

[0072] In one embodiment, the auxiliary display unit can also be used for: if you return to the node and / or line corresponding to the operational behavior of the current production problem that has been detached, and determine that the next selection is one of the current branches displayed, restart the display in a preset prominent display manner.

[0073] In one embodiment, the auxiliary display unit can be specifically used to: display corresponding nodes and / or lines in the flow chart at a preset position and in a preset prominent display manner according to the user's operational behavior of checking the current production problem.

[0074] In one embodiment, the preset prominent display mode may be a display mode in which the brightness exceeds a preset value.

[0075] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned Markov chain-based production problem inspection method when executing the computer program.

[0076] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for executing the above-mentioned Markov chain-based production problem inspection method.

[0077] In an embodiment of the present invention, a production problem inspection scheme based on a Markov chain, compared with the technical scheme in the prior art that requires a large number of samples for learning to inspect AI production problems, has low accuracy, low security and high operation and maintenance costs, comprises: receiving a current production problem number input by a user; the production problem number is pre-assigned according to the business type and the technical type; determining a flowchart corresponding to the current production problem number according to the current production problem number and a pre-established branch graph for assisting in inspecting production problems; the branch graph includes operational behaviors recorded in the form of a Markov chain when multiple staff members exceeding a preset level inspect historical production problems; according to the operational behaviors of the user inspecting the current production problem, the corresponding nodes and / or lines in the flowchart are displayed in a preset prominent display manner, so that the operational behaviors of the staff members exceeding the preset level can be displayed in real time during the production problem inspection process, which improves the accuracy and security of the production problem inspection and reduces the operation and maintenance costs compared to experienced staff members personally guiding the problem analysis.

[0078] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0080] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0082] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A production problem inspection method based on Markov chain, characterized in that: include: Receiving a current production problem number input by a user; the production problem number is pre-assigned according to a business type and a technical type; According to the current production problem number and the pre-established branch diagram for assisting in checking production problems, the flowchart corresponding to the current production problem number is determined; the branch diagram includes the operation behaviors recorded in the form of a Markov chain when a plurality of staff members exceeding a preset level check historical production problems; wherein the flowchart corresponding to the current production problem number is found from the database, and the operation of each step is displayed in the form of a branch diagram, and the percentage of people who have the corresponding step; According to the user's operation behavior of checking the current production problem, the corresponding nodes and / or lines in the flow chart are displayed in a preset highlighting manner; The method also includes pre-establishing the branch diagram as follows: Obtaining a production problem number when a staff member checks a historical production problem; the production problem number is pre-assigned according to a business type and a technical type; According to the production problem number when checking historical production problems, and the relationship between the production problem number and the staff level, determine the staff level corresponding to the production problem number when checking historical production problems; When it is determined that the corresponding staff level exceeds the preset level, all the operational behaviors of the staff in checking historical production problems are recorded in the form of a Markov chain; wherein the first choice is the problem number, and each choice starting from the second choice is each operational behavior of checking the production problem, and each choice starting from the second choice includes multiple sub-choices with the same attributes; Determine the proportion of operational behaviors of multiple staff members checking historical production problems exceeding a preset level corresponding to each sub-selection; According to the operation behaviors recorded by the Markov chain and the ratio, a branch diagram for assisting in checking production problems is formed, and the branch diagram is stored in a database.

2. The Markov chain-based production problem detection method according to claim 1, characterized in that: According to the operation behavior recorded by the Markov chain and the said ratio, a branch diagram for assisting in checking the production problem is formed, and the said branch diagram is stored in a database, including: deleting the branches corresponding to the sub-selections in the branch diagram that are smaller than a preset ratio to obtain an optimized branch diagram; and storing the optimized branch diagram in the database.

3. The Markov chain-based production problem detection method according to claim 1, characterized in that: Based on the user's operational behavior in checking the current production problem, the corresponding nodes and / or lines in the flowchart are displayed in a preset highlighting manner, including: if the operational behavior of the current production problem is separated from the current branch, the nodes and / or lines displayed in the current highlighting manner remain unchanged.

4. The Markov chain-based production problem detection method according to claim 3, characterized in that: Also includes: If you return to the node and / or line corresponding to the operational behavior of the current production problem that has been detached, and it is determined that the next selection is one of the branches currently displayed, the display will be restarted in the preset highlighted display mode.

5. The Markov chain-based production problem detection method according to claim 1, characterized in that: According to the user's operational behavior of checking the current production problem, the corresponding nodes and / or lines in the flowchart are displayed in a preset prominent display method, including: according to the user's operational behavior of checking the current production problem, the corresponding nodes and / or lines in the flowchart are displayed in a preset prominent display method at a preset position.

6. The Markov chain-based production problem detection method according to claim 1, characterized in that: The preset prominent display mode is a display mode in which the brightness exceeds a preset value.

7. A production problem inspection device based on Markov chain, characterized in that: include: A receiving unit, used for receiving a current production problem number input by a user; Said production issue number is pre-assigned according to the business type and technology type; A determination unit is used to determine the flowchart corresponding to the current production problem number according to the current production problem number and a pre-established branch diagram for assisting in checking production problems; the branch diagram includes operation behaviors recorded in the form of a Markov chain when a plurality of staff members exceeding a preset level check historical production problems; wherein the flowchart corresponding to the current production problem number is found from a database, and the operation of each step is displayed in the form of a branch diagram, and the percentage of people who have the corresponding step; An auxiliary display unit, used to display corresponding nodes and / or lines in the flow chart in a preset prominent display manner according to the user's operation behavior of checking the current production problem; It also includes an establishing unit, which is used to pre-establish the branch diagram according to the following method: Obtaining a production problem number when a staff member checks a historical production problem; the production problem number is pre-assigned according to a business type and a technical type; According to the production problem number when checking historical production problems and the relationship between the production problem number and the staff level, determine the staff level corresponding to the production problem number when checking historical production problems; When it is determined that the staff level corresponding to the production problem number when checking historical production problems exceeds the preset level, all the operation behaviors of the staff in checking historical production problems are recorded in the form of a Markov chain; wherein the first choice is the problem number, each choice starting from the second choice is each operation behavior of checking the production problem, and each choice starting from the second choice includes multiple sub-choices with the same attributes; Determine the proportion of operational behaviors of multiple staff members checking historical production problems exceeding a preset level corresponding to each sub-selection; According to the operation behaviors recorded by the Markov chain and the ratio, a branch diagram for assisting in checking production problems is formed, and the branch diagram is stored in a database.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images