Cloud platform operation and maintenance recommendation method and device based on knowledge base, equipment and medium

Abstract

The invention relates to the technical field of operation and maintenance recommendation based on an operation and maintenance knowledge base, in particular to a cloud platform operation and maintenance recommendation method and device based on a knowledge base, equipment and a medium. Performing word segmentation on the abnormal description statement to obtain a plurality of entity segmented words; determining a plurality of alternative operation and maintenance knowledge texts from an operation and maintenance knowledge base according to the occurrence frequency of the plurality of entity segmented words in the operation and maintenance knowledge texts and the reverse file frequency; and finally, according to the probability of a plurality of abnormal reasons, the probability of occurrence of entity word segmentation and the probability of occurrence of entity word segmentation in the operation and maintenance knowledge text under the abnormal reason condition, determining the reliability probability of the plurality of reasons, and according to the reliability probability of the plurality of reasons, determining a target operation and maintenance knowledge text from the plurality of alternative operation and maintenance knowledge texts. According to the method, the query speed and accuracy of the operation and maintenance knowledge base are improved, help is provided for operation and maintenance work, and the operation and maintenance efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of operation and maintenance recommendation based on an operation and maintenance knowledge base, and in particular to a cloud platform operation and maintenance recommendation method, device, equipment and medium based on a knowledge base. Background Art

[0002] Equipment operation and maintenance is a task that tests maintenance experience, and this is especially true for the operation and maintenance of a meteorological big data cloud platform. A meteorological big data cloud platform is a platform that integrates computing and storage, built to meet the needs of big data computing. This platform has high reliability requirements. For example, when an anomaly occurs on the cloud platform, it must be able to respond quickly and resolve the issue promptly. However, the specialized features of a meteorological big data cloud platform make its operation and maintenance somewhat different from that of general cloud platforms. The operation and maintenance experience of general cloud platforms is often not directly applicable to a meteorological big data cloud platform. Establishing and improving an operation and maintenance knowledge base for a meteorological big data cloud platform can facilitate the accumulation and sharing of operation and maintenance experience, helping to accelerate the response to anomalies on the meteorological big data cloud platform.

[0003] Typically, a knowledge base includes relevant O&M knowledge items, such as solutions to common faults and platform upgrade processes. This allows O&M personnel to quickly query and resolve issues, improving O&M efficiency. With the introduction of knowledge graph technology, the experience and knowledge gained during O&M can be organized and summarized into a knowledge base, facilitating subsequent automated O&M work.

[0004] At present, the main problem in the use of operation and maintenance knowledge base is that it is inconvenient to find the operation and maintenance knowledge that best suits the current equipment abnormality from the knowledge base. Based on this, it is necessary to develop and design a cloud platform operation and maintenance recommendation method based on the knowledge base. Summary of the Invention

[0005] The embodiments of the present invention provide a cloud platform operation and maintenance recommendation method, apparatus, device and medium based on a knowledge base, which is used to solve the problem in the prior art that it is difficult to find the operation and maintenance knowledge that best matches the current device abnormality from the knowledge base.

[0006] In a first aspect, an embodiment of the present invention provides a cloud platform operation and maintenance recommendation method based on a knowledge base, comprising: Get the exception description statement; Segmenting the abnormality description sentence to obtain multiple entity segmentations; Determining multiple candidate operation and maintenance knowledge texts from the operation and maintenance knowledge base based on the frequencies of occurrence of the multiple entity segmentation words in the operation and maintenance knowledge texts and the reverse document frequencies, wherein the reverse document frequencies represent the ratio of the operation and maintenance knowledge texts containing the entity segmentation words to the total operation and maintenance knowledge texts; The multiple cause reliability probabilities are determined based on the probabilities of multiple abnormal causes, the probability of the occurrence of entity segmentations, and the probability of the occurrence of entity segmentations in the operation and maintenance knowledge text under the abnormal cause conditions, and the target operation and maintenance knowledge text is determined from the multiple alternative operation and maintenance knowledge texts based on the multiple cause reliability probabilities, wherein each alternative operation and maintenance knowledge text corresponds to a cause reliability probability and an abnormal cause.

[0007] In one possible implementation, the segmentation of the abnormal description statement to obtain multiple entity segmentations includes: extracting a first number of multiple characters from predetermined positions of the abnormality description sentence; If the multiple characters are not target parts of speech, entity matching is performed in a knowledge graph based on the multiple characters, wherein the knowledge graph includes multiple entities, and the entities in the knowledge graph are connected by relationships; If no match is found, the value of the first number is increased, and the process jumps to the step of extracting a first number of multiple characters from predetermined positions of the exception description statement; Otherwise, the matched entity and entities having multiple identical relationships with the matched entity are added to multiple entity segmentations; The predetermined position is offset according to the predetermined position and the first number, and the process jumps to the step of extracting a first number of multiple characters from the predetermined position of the exception description statement.

[0008] In one possible implementation, determining multiple candidate operation and maintenance knowledge texts from the operation and maintenance knowledge base based on the frequencies of occurrence of the multiple entity segmentations in the operation and maintenance knowledge text and the reverse file frequencies includes: Determine multiple segmentation frequency queues based on the multiple entity segmentations, wherein each segmentation frequency queue corresponds to an operation and maintenance knowledge text, the segmentation frequency queue includes multiple segmentation frequency values, each segmentation frequency value corresponds to an entity segmentation, and the segmentation frequency value represents the probability of the entity segmentation appearing in the operation and maintenance knowledge text; Constructing a reverse file frequency queue according to the frequencies of occurrence of the plurality of entity participles in the operation and maintenance knowledge base, wherein the reverse file frequency queue includes a plurality of reverse file frequency values, each reverse file frequency value corresponding to an entity participle; Determining a plurality of correlation values ​​according to the plurality of word segmentation frequency queues and the reverse file frequency queue, wherein each correlation value corresponds to an operation and maintenance knowledge text, and the correlation value represents a degree of correlation between the operation and maintenance knowledge text and the abnormality description statement; According to the multiple association values, multiple candidate operation and maintenance knowledge texts are determined from the operation and maintenance knowledge base.

[0009] In one possible implementation, determining multiple word segmentation frequency queues based on the multiple entity word segmentations includes: For each operation and maintenance knowledge text, perform the following steps: Sequentially extracting entity participles from the plurality of entity participles as entity participles to be processed; The word segmentation frequency value is calculated according to the first formula, wherein the first formula is:

[0010] Where, is the frequency value of the entity segmentation to be processed, The number of times the entity segmentation to be processed appears in the operation and maintenance knowledge text, is the number of segmented words in the operation and maintenance knowledge text; Add the word segmentation frequency value to the word segmentation frequency queue; If the traversal of the multiple entity participles is not completed, the process jumps to the step of sequentially extracting entity participles from the multiple entity participles as entity participles to be processed.

[0011] In one possible implementation, the step of constructing a reverse file frequency queue based on the frequencies of occurrence of the multiple entity segmentations in the operation and maintenance knowledge base includes: Sequentially extracting entity participles from the plurality of entity participles as entity participles to be processed; The reverse document frequency value of the entity segmentation to be processed is calculated according to the second formula, wherein the second formula is:

[0012] Where, is the reverse document frequency value of the entity segmentation to be processed, is the number of operation and maintenance knowledge texts with entity segmentation to be processed, is the number of operation and maintenance knowledge texts in the operation and maintenance knowledge base, is the first constant; Adding the reverse file frequency value to a reverse file frequency queue; If the traversal of the multiple entity participles is not completed, the process jumps to the step of sequentially extracting entity participles from the multiple entity participles as entity participles to be processed.

[0013] In one possible implementation, determining multiple association values ​​based on the multiple word segmentation frequency queues and the reverse file frequency queue includes: For each operation and maintenance knowledge text, the associated value is determined according to the third formula, wherein the third formula is:

[0014] Where, is the associated value of the operation and maintenance knowledge text, The first word frequency values, The reverse file frequency queue Inverse file frequency values, The total number of entity segmentations.

[0015] In one possible implementation, determining the reliability probabilities of the multiple causes based on the probabilities of the multiple abnormal causes, the probability of the entity segmentation appearing, and the probability of the entity segmentation appearing in the operation and maintenance knowledge text under the abnormal cause condition includes: The cause reliability probability of each abnormal cause is determined according to the fourth formula, wherein the fourth formula is:

[0016] Where, is the cause reliability probability, The first The probability of entity segmentation, is the safety risk probability, For the The probability of an entity segmentation word appearing in the operation and maintenance knowledge text.

[0017] In a second aspect, an embodiment of the present invention provides a knowledge base-based cloud platform operation and maintenance recommendation device, which is used to implement the knowledge base-based cloud platform operation and maintenance recommendation method described in the first aspect or any possible implementation of the first aspect above, wherein the knowledge base-based cloud platform operation and maintenance recommendation device includes: Description acquisition module, used to obtain exception description statements; A word segmentation module is used to segment the abnormal description sentence to obtain multiple entity segmentations; a preliminary selection module, configured to determine a plurality of candidate operation and maintenance knowledge texts from the operation and maintenance knowledge base based on the frequencies of occurrence of the plurality of entity segmentation words in the operation and maintenance knowledge texts and the reverse document frequencies, wherein the reverse document frequencies represent the ratio of the operation and maintenance knowledge texts containing the entity segmentation words to the total operation and maintenance knowledge texts; as well as, The operation and maintenance recommendation module is used to determine the multiple cause reliability probabilities based on the probabilities of multiple abnormal causes, the probability of the occurrence of entity segmentations, and the probability of the occurrence of entity segmentations in the operation and maintenance knowledge text under the abnormal cause conditions, and determine the target operation and maintenance knowledge text from the multiple alternative operation and maintenance knowledge texts based on the multiple cause reliability probabilities, wherein each alternative operation and maintenance knowledge text corresponds to a cause reliability probability and an abnormal cause.

[0018] In a third aspect, an embodiment of the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it implements the steps of the method described in the first aspect or any possible implementation of the first aspect.

[0019] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the method described in the first aspect or any possible implementation of the first aspect.

[0020] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: An embodiment of the present invention discloses a cloud platform operation and maintenance recommendation method based on a knowledge base, which first obtains an abnormality description sentence; then performs word segmentation on the abnormality description sentence to obtain multiple entity word segmentations; then, according to the frequency of occurrence of the multiple entity word segmentations in the operation and maintenance knowledge text and the reverse file frequency, multiple alternative operation and maintenance knowledge texts are determined from the operation and maintenance knowledge base, wherein the reverse file frequency represents the ratio of the operation and maintenance knowledge text containing the entity word segmentations to all the operation and maintenance knowledge texts; finally, according to the probabilities of multiple abnormal causes, the probability of occurrence of the entity word segmentations and the probability of occurrence of the entity word segmentations in the operation and maintenance knowledge text under the abnormal cause conditions, the multiple cause reliability probabilities are determined, and a target operation and maintenance knowledge text is determined from the multiple alternative operation and maintenance knowledge texts according to the multiple cause reliability probabilities, wherein each alternative operation and maintenance knowledge text corresponds to a cause reliability probability and an abnormal cause. The embodiment of the present invention determines alternative operation and maintenance knowledge texts by analyzing the frequency of occurrence of the word segmentation of the abnormal description sentence in the operation and maintenance knowledge text and the proportion of the operation and maintenance knowledge text containing entity segmentation. Finally, through statistics and probability theory, the operation and maintenance knowledge text most relevant to the abnormal description sentence is selected from the alternative operation and maintenance knowledge texts for push. The method of the present invention improves the speed and accuracy of the operation and maintenance knowledge base query, provides assistance to the operation and maintenance work, and improves the efficiency of the operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. 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 paying any creative labor.

[0022] Figure 1 This is a flow chart of a cloud platform operation and maintenance recommendation method based on a knowledge base provided by an embodiment of the present invention; Figure 2 This is a schematic diagram of a method for determining alternative operation and maintenance knowledge texts provided by an embodiment of the present invention; Figure 3 This is a functional block diagram of a cloud platform operation and maintenance recommendation device based on a knowledge base provided by an embodiment of the present invention; Figure 4 This is a functional block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in alternative embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0024] In order to make the objectives, technical solutions and advantages of the present invention more clear, the following will be described through specific implementation methods in conjunction with the accompanying drawings.

[0025] The following is a detailed description of an embodiment of the present invention. This example is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiment.

[0026] Figure 1 Flowchart of a knowledge base-based cloud platform operation and maintenance recommendation method provided in an embodiment of the present invention.

[0027] like Figure 1 As shown, it shows a flow chart of the implementation of the knowledge base-based cloud platform operation and maintenance recommendation method provided by an embodiment of the present invention, which is detailed as follows: In step 101, an exception description statement is obtained.

[0028] In step 102, the abnormal description sentence is segmented to obtain multiple entity segmentations.

[0029] In some embodiments, step 102 includes: extracting a first number of multiple characters from predetermined positions of the abnormality description sentence; If the multiple characters are not target parts of speech, entity matching is performed in a knowledge graph based on the multiple characters, wherein the knowledge graph includes multiple entities, and the entities in the knowledge graph are connected by relationships; If no match is found, the value of the first number is increased, and the process jumps to the step of extracting a first number of multiple characters from predetermined positions of the exception description statement; Otherwise, the matched entity and entities having multiple identical relationships with the matched entity are added to multiple entity segmentations; The predetermined position is offset according to the predetermined position and the first number, and the process jumps to the step of extracting a first number of multiple characters from the predetermined position of the exception description statement.

[0030] Exemplarily, the embodiment of the present invention accepts operation and maintenance query statements, which are generally description statements of abnormal phenomena. Due to different expressions, when the operation and maintenance knowledge base is searched based only on the operation and maintenance query statements, some operation and maintenance knowledge texts (operation and maintenance knowledge entries) may be ignored. The embodiment of the present invention processes description statements by segmenting abnormal description statements, usually by extracting one or two words from the statement, and performing entity matching on the extracted words in the knowledge graph. It should be noted that the knowledge graph includes multiple entities, and each entity is connected to other entities through relationships to form a network. After the extracted words are matched in the entity, the entities with the same relationship with the entity are added to the multiple entity segmentations, otherwise, the number of words is adjusted. This process is repeated to complete the segmentation of the abnormal description statement.

[0031] The multiple word segments obtained through the above steps can be used to search for words with similar meanings to a large extent, thereby expanding the number of alternative targets and improving the search accuracy.

[0032] In step 103, multiple alternative operation and maintenance knowledge texts are determined from the operation and maintenance knowledge base based on the frequency of occurrence of the multiple entity participles in the operation and maintenance knowledge text and the reverse file frequency, wherein the reverse file frequency represents the ratio of the operation and maintenance knowledge text containing entity participles to the total operation and maintenance knowledge text.

[0033] In some embodiments, step 103 includes: Determine multiple segmentation frequency queues based on the multiple entity segmentations, wherein each segmentation frequency queue corresponds to an operation and maintenance knowledge text, the segmentation frequency queue includes multiple segmentation frequency values, each segmentation frequency value corresponds to an entity segmentation, and the segmentation frequency value represents the probability of the entity segmentation appearing in the operation and maintenance knowledge text; Constructing a reverse file frequency queue according to the frequencies of occurrence of the plurality of entity participles in the operation and maintenance knowledge base, wherein the reverse file frequency queue includes a plurality of reverse file frequency values, each reverse file frequency value corresponding to an entity participle; Determining a plurality of correlation values ​​according to the plurality of word segmentation frequency queues and the reverse file frequency queue, wherein each correlation value corresponds to an operation and maintenance knowledge text, and the correlation value represents a degree of correlation between the operation and maintenance knowledge text and the abnormality description statement; According to the multiple association values, multiple candidate operation and maintenance knowledge texts are determined from the operation and maintenance knowledge base.

[0034] In some implementations, determining multiple word segmentation frequency queues based on the multiple entity word segmentations includes: For each operation and maintenance knowledge text, perform the following steps: Sequentially extracting entity participles from the plurality of entity participles as entity participles to be processed; The word segmentation frequency value is calculated according to the first formula, wherein the first formula is:

[0035] Where, is the frequency value of the entity segmentation to be processed, The number of times the entity segmentation to be processed appears in the operation and maintenance knowledge text, is the number of segmented words in the operation and maintenance knowledge text; Add the word segmentation frequency value to the word segmentation frequency queue; If the traversal of the multiple entity participles is not completed, the process jumps to the step of sequentially extracting entity participles from the multiple entity participles as entity participles to be processed.

[0036] In some implementations, constructing a reverse file frequency queue based on the frequencies of occurrence of the multiple entity segmentations in the operation and maintenance knowledge base includes: Sequentially extracting entity participles from the plurality of entity participles as entity participles to be processed; The reverse document frequency value of the entity segmentation to be processed is calculated according to the second formula, wherein the second formula is:

[0037] Where, is the reverse document frequency value of the entity segmentation to be processed, is the number of operation and maintenance knowledge texts with entity segmentation to be processed, is the number of operation and maintenance knowledge texts in the operation and maintenance knowledge base, is the first constant; Adding the reverse file frequency value to a reverse file frequency queue; If the traversal of the multiple entity participles is not completed, the process jumps to the step of sequentially extracting entity participles from the multiple entity participles as entity participles to be processed.

[0038] In some implementations, determining a plurality of association values ​​based on the plurality of word segmentation frequency queues and the reverse file frequency queue includes: For each operation and maintenance knowledge text, the associated value is determined according to the third formula, wherein the third formula is:

[0039] Where, is the associated value of the operation and maintenance knowledge text, The first word frequency values, The reverse file frequency queue Inverse file frequency values, The total number of entity segmentations.

[0040] For example, Figure 2 As shown, the embodiment of the present invention calculates the frequency of each entity segmentation in the multiple entity segmentations 201 for each operation and maintenance knowledge text in the operation and maintenance knowledge base 202, and constructs the frequencies of these entity segmentations into a segmentation frequency queue 203. In this way, each operation and maintenance knowledge text corresponds to a segmentation frequency queue 203. At the same time, for each entity segmentation in the multiple entity segmentations 201, the frequency of its appearance in the operation and maintenance knowledge text in the operation and maintenance knowledge base 202 (reverse file frequency value) is counted, and these frequency values ​​are constructed into a reverse file frequency queue 204. Through the segmentation frequency queue 203 and the reverse file frequency queue 204, we can analyze the correlation between each operation and maintenance knowledge text and the abnormal description statement.

[0041] In terms of determining the word segmentation frequency value, the embodiment of the present invention applies the first formula:

[0042] Where, is the frequency value of the entity segmentation to be processed, The number of times the entity segmentation to be processed appears in the operation and maintenance knowledge text, is the number of segmented words in the operation and maintenance knowledge text.

[0043] In determining the reverse file frequency value, the embodiment of the present invention applies the second formula:

[0044] Where, is the reverse document frequency value of the entity segmentation to be processed, is the number of operation and maintenance knowledge texts with entity segmentation to be processed, is the number of operation and maintenance knowledge texts in the operation and maintenance knowledge base, is the first constant.

[0045] Finally, the present invention calculates the correlation between each operation and maintenance knowledge text and the abnormal description statement through the third formula, which is:

[0046] Where, is the associated value of the operation and maintenance knowledge text, The first word frequency values, The reverse file frequency queue Inverse file frequency values, The total number of entity segmentations.

[0047] In step 104, the multiple cause reliability probabilities are determined based on the probabilities of multiple abnormal causes, the probability of the occurrence of entity segmentations, and the probability of the occurrence of entity segmentations in the operation and maintenance knowledge text under the abnormal cause conditions, and the target operation and maintenance knowledge text is determined from the multiple alternative operation and maintenance knowledge texts based on the multiple cause reliability probabilities, wherein each alternative operation and maintenance knowledge text corresponds to a cause reliability probability and an abnormal cause.

[0048] In some embodiments, determining the multiple cause reliability probabilities based on the probabilities of the multiple abnormal causes, the probability of the entity segmentation appearing, and the probability of the entity segmentation appearing in the operation and maintenance knowledge text under the abnormal cause condition includes: The cause reliability probability of each abnormal cause is determined according to the fourth formula, wherein the fourth formula is:

[0049] Where, is the cause reliability probability, The first The probability of entity segmentation, is the safety risk probability, For the The probability of an entity segmentation word appearing in the operation and maintenance knowledge text.

[0050] For example, in fact, multiple alternative operation and maintenance knowledge texts can be selected through the above steps. These operation and maintenance knowledge texts usually correspond to multiple abnormal causes. If the abnormal cause corresponding to the abnormal description statement is found from these abnormal causes, then the matching of the operation and maintenance knowledge text can be completed.

[0051] Based on the above concept, the embodiment of the present invention calculates the probability of various abnormal causes when multiple entity segmentations appear based on statistical and probability principles. Obviously, the larger the probability value, the closer the abnormal cause is to the cause corresponding to the abnormal description sentence.

[0052] For example, if the exception description statement includes descriptions of insufficient space, excessive task execution time, and new tasks, we can roughly infer that there is a problem with the task execution, resulting in a large amount of data occupying data space.

[0053] The embodiment of the present invention determines the probability of the abnormal cause when the entity segmentation description appears based on the probability of the entity segmentation appearing when the abnormal cause occurs, the probability of the abnormal cause occurring, and the probability of the entity segmentation. Specifically, the fourth formula is used:

[0054] Where, is the cause reliability probability, The first The probability of entity segmentation, is the safety risk probability, For the The probability of an entity segmentation word appearing in the operation and maintenance knowledge text.

[0055] The abnormal risks are ranked by the fourth formula, and the candidate operation and maintenance knowledge texts corresponding to the largest abnormal risks are selected as target operation and maintenance knowledge texts for push. The cloud platform is maintained using these target operation and maintenance knowledge texts as a reference.

[0056] The present invention provides an implementation method for a cloud platform operation and maintenance recommendation method based on a knowledge base, which first obtains an exception description sentence; then performs word segmentation on the exception description sentence to obtain multiple entity word segmentations; then, based on the frequency of occurrence of the multiple entity word segmentations in the operation and maintenance knowledge text and the reverse file frequency, multiple alternative operation and maintenance knowledge texts are determined from the operation and maintenance knowledge base, wherein the reverse file frequency represents the ratio of the operation and maintenance knowledge text containing the entity word segmentations to all the operation and maintenance knowledge texts; finally, based on the probabilities of multiple abnormal causes, the probability of occurrence of the entity word segmentations, and the probability of occurrence of the entity word segmentations in the operation and maintenance knowledge text under the abnormal cause conditions, the multiple cause reliability probabilities are determined, and a target operation and maintenance knowledge text is determined from the multiple alternative operation and maintenance knowledge texts based on the multiple cause reliability probabilities, wherein each alternative operation and maintenance knowledge text corresponds to a cause reliability probability and an abnormal cause. The embodiment of the present invention determines alternative operation and maintenance knowledge texts by analyzing the frequency of occurrence of the word segmentation of the abnormal description sentence in the operation and maintenance knowledge text and the proportion of the operation and maintenance knowledge text containing entity segmentation. Finally, through statistics and probability theory, the operation and maintenance knowledge text most relevant to the abnormal description sentence is selected from the alternative operation and maintenance knowledge texts for push. The method of the present invention improves the speed and accuracy of the operation and maintenance knowledge base query, provides assistance to the operation and maintenance work, and improves the efficiency of the operation and maintenance.

[0057] It should be understood that the size of the serial numbers of each step in the above embodiment does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0058] The following is an embodiment of the device of the present invention. For details not described in detail, please refer to the corresponding method embodiment described above.

[0059] Figure 3 This is a functional block diagram of a cloud platform operation and maintenance recommendation device based on a knowledge base provided by an embodiment of the present invention, referring to Figure 3 The cloud platform operation and maintenance recommendation device based on the knowledge base includes: a description acquisition module 301, a word segmentation module 302, a preliminary selection module 303 and an operation and maintenance recommendation module 304, wherein: Description acquisition module 301, used to obtain an exception description statement; A word segmentation module 302 is used to segment the abnormality description sentence to obtain multiple entity segmentations; A preliminary selection module 303 is configured to determine a plurality of candidate operation and maintenance knowledge texts from the operation and maintenance knowledge base based on the frequencies of occurrence of the plurality of entity segmentations in the operation and maintenance knowledge texts and the reverse document frequencies, wherein the reverse document frequencies represent the ratio of the operation and maintenance knowledge texts containing the entity segmentations to the total operation and maintenance knowledge texts; The operation and maintenance recommendation module 304 is used to determine the multiple cause reliability probabilities based on the probabilities of multiple abnormal causes, the probability of the occurrence of entity segmentations, and the probability of the occurrence of entity segmentations in the operation and maintenance knowledge text under the abnormal cause conditions, and determine the target operation and maintenance knowledge text from the multiple alternative operation and maintenance knowledge texts based on the multiple cause reliability probabilities, wherein each alternative operation and maintenance knowledge text corresponds to a cause reliability probability and an abnormal cause.

[0060] Figure 4 : is a functional block diagram of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, the electronic device 4 of this embodiment includes: a processor 400 and a memory 401, wherein the memory 401 stores a computer program 402 that can be run on the processor 400. When the processor 400 executes the computer program 402, the steps in the above-mentioned cloud platform operation and maintenance recommendation method and embodiment based on the knowledge base are implemented, such as Figure 1 Steps 101 to 104 are shown.

[0061] Illustratively, the computer program 402 may be divided into one or more modules / units, and the one or more modules / units are stored in the memory 401 and executed by the processor 400 to implement the present invention.

[0062] The electronic device 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 4 may include, but is not limited to, a processor 400 and a memory 401. Those skilled in the art will understand that Figure 4It is only an example of the electronic device 4 and does not constitute a limitation of the electronic device 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 4 may also include input and output devices, network access devices, buses, etc.

[0063] The processor 400 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0064] The memory 401 may be an internal storage unit of the electronic device 4, such as a hard drive or memory of the electronic device 4. The memory 401 may also be an external storage device of the electronic device 4, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped on the electronic device 4. Furthermore, the memory 401 may include both an internal storage unit of the electronic device 4 and an external storage device. The memory 401 is used to store the computer program 402 and other programs and data required by the electronic device 4. The memory 401 may also be used to temporarily store data that has been output or is about to be output.

[0065] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the implementation method can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method implementation method, and will not be repeated here.

[0066] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0067] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0068] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0069] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of this embodiment.

[0070] In addition, the functional units in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0071] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can also implement all or part of the processes in the above-mentioned method embodiments by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of the above-mentioned method and device embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium.

[0072] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A cloud platform operation and maintenance recommendation method based on a knowledge base, characterized in that: include: Get the exception description statement; Segmenting the abnormal description sentence to obtain multiple entity segmentations; Determine a plurality of candidate operation and maintenance knowledge texts from the operation and maintenance knowledge base according to the frequencies of occurrence of the plurality of entity segmentations in the operation and maintenance knowledge texts and the reverse file frequencies, wherein the reverse file frequencies represent the ratio of the operation and maintenance knowledge texts containing the entity segmentations to the total operation and maintenance knowledge texts; The multiple cause reliability probabilities are determined based on the probabilities of multiple abnormal causes, the probability of the occurrence of entity segmentations, and the probability of the occurrence of entity segmentations in the operation and maintenance knowledge text under the abnormal cause conditions, and the target operation and maintenance knowledge text is determined from the multiple alternative operation and maintenance knowledge texts based on the multiple cause reliability probabilities, wherein each alternative operation and maintenance knowledge text corresponds to a cause reliability probability and an abnormal cause.

2. The cloud platform operation and maintenance recommendation method based on the knowledge base according to claim 1, characterized in that: The multiple entity segmentations obtained by segmenting the abnormal description sentence include: Extracting a first number of multiple characters from a predetermined position of the abnormal description statement; If the multiple characters are not the target part of speech, entity matching is performed in the knowledge graph according to the multiple characters, wherein the knowledge graph includes multiple entities, and the entities of the knowledge graph are connected by relationships; If there is no match, the value of the first number is increased, and the process jumps to the step of extracting a first number of multiple characters from a predetermined position of the exception description statement; Otherwise, the matched entity and entities having multiple identical relationships with the matched entity are added to multiple entity segmentations; The predetermined position is offset according to the predetermined position and the first number, and the process jumps to the step of extracting a first number of multiple characters from the predetermined position of the exception description statement.

3. The cloud platform operation and maintenance recommendation method based on the knowledge base according to claim 1 is characterized in that: The determining of multiple candidate operation and maintenance knowledge texts from the operation and maintenance knowledge base according to the frequencies of occurrence of the multiple entity segmentations in the operation and maintenance knowledge text and the reverse file frequencies includes: Determine multiple segmentation frequency queues according to the multiple entity segmentations, wherein each segmentation frequency queue corresponds to an operation and maintenance knowledge text, the segmentation frequency queue includes multiple segmentation frequency values, each segmentation frequency value corresponds to an entity segmentation, and the segmentation frequency value represents the probability of the entity segmentation appearing in the operation and maintenance knowledge text; Constructing a reverse file frequency queue according to the frequencies of occurrence of the multiple entity participles in the operation and maintenance knowledge base, wherein the reverse file frequency queue includes multiple reverse file frequency values, each reverse file frequency value corresponding to an entity participle; Determine a plurality of association values ​​according to the plurality of word segmentation frequency queues and the reverse file frequency queue, wherein each association value corresponds to an operation and maintenance knowledge text, and the association value represents the degree of association between the operation and maintenance knowledge text and the abnormal description statement; According to the multiple association values, multiple candidate operation and maintenance knowledge texts are determined from the operation and maintenance knowledge base.

4. The cloud platform operation and maintenance recommendation method based on the knowledge base according to claim 3 is characterized in that: The step of determining a plurality of word segmentation frequency queues according to the plurality of entity word segmentations includes: For each operation and maintenance knowledge text, perform the following steps respectively: Taking out entity participles from the multiple entity participles in sequence as entity participles to be processed; The word segmentation frequency value is calculated according to the first formula, wherein the first formula is: In the formula, is the word segmentation frequency value of the entity to be processed, is the number of times the entity segmentation to be processed appears in the operation and maintenance knowledge text, is the number of segmented words in the operation and maintenance knowledge text; Add the word segmentation frequency value to the word segmentation frequency queue; If the traversal of the multiple entity participles is not completed, jump to the step of sequentially taking out entity participles from the multiple entity participles as entity participles to be processed.

5. The cloud platform operation and maintenance recommendation method based on the knowledge base according to claim 3 is characterized in that: The step of constructing a reverse file frequency queue according to the frequencies of occurrence of the multiple entity segmentations in the operation and maintenance knowledge base includes: Taking out entity participles from the multiple entity participles in sequence as entity participles to be processed; The reverse document frequency value of the entity segmentation to be processed is calculated according to the second formula, wherein the second formula is: In the formula, is the reverse document frequency value of the entity segmentation to be processed, is the number of operation and maintenance knowledge texts with entity segmentation to be processed, is the number of operation and maintenance knowledge texts in the operation and maintenance knowledge base, is the first constant; Adding the reverse file frequency value to a reverse file frequency queue; If the traversal of the multiple entity participles is not completed, jump to the step of sequentially taking out entity participles from the multiple entity participles as entity participles to be processed.

6. The cloud platform operation and maintenance recommendation method based on the knowledge base according to claim 3 is characterized in that: The determining of a plurality of associated values ​​according to the plurality of word segmentation frequency queues and the reverse file frequency queue comprises: For each operation and maintenance knowledge text, the associated value is determined according to the third formula, wherein the third formula is: In the formula, is the associated value of the operation and maintenance knowledge text, is the first word frequency values, The reverse file frequency queue Inverse file frequency values, The total number of entity segmentations.

7. The cloud platform operation and maintenance recommendation method based on a knowledge base according to any one of claims 1 to 6, characterized in that: Determining the reliability probabilities of the multiple causes according to the probabilities of the multiple abnormal causes, the probability of the entity segmentation appearing, and the probability of the entity segmentation appearing in the operation and maintenance knowledge text under the abnormal cause condition includes: The cause reliability probability of each abnormal cause is determined according to the fourth formula, wherein the fourth formula is: In the formula, is the cause reliability probability, The first The probability of entity segmentation, is the safety risk probability, For the The probability of an entity segmentation word appearing in the operation and maintenance knowledge text.

8. A cloud platform operation and maintenance recommendation device based on a knowledge base, characterized in that: Used to implement the cloud platform operation and maintenance recommendation method based on the knowledge base as described in any one of claims 1 to 7, the cloud platform operation and maintenance recommendation device based on the knowledge base includes: Description acquisition module, used to obtain the exception description statement; A word segmentation module, used to segment the abnormal description sentence to obtain multiple entity segmentations; A preliminary selection module, used to determine a plurality of candidate operation and maintenance knowledge texts from the operation and maintenance knowledge base according to the frequencies of occurrence of the plurality of entity segmentations in the operation and maintenance knowledge texts and the reverse file frequencies, wherein the reverse file frequencies represent the ratio of the operation and maintenance knowledge texts containing the entity segmentations to the total operation and maintenance knowledge texts; as well as, The operation and maintenance recommendation module is used to determine the multiple cause reliability probabilities according to the probabilities of multiple abnormal causes, the probability of the occurrence of entity segmentations, and the probability of the occurrence of entity segmentations in the operation and maintenance knowledge text under the abnormal cause conditions, and determine the target operation and maintenance knowledge text from the multiple alternative operation and maintenance knowledge texts according to the multiple cause reliability probabilities, wherein each alternative operation and maintenance knowledge text corresponds to a cause reliability probability and an abnormal cause.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method as claimed in any one of claims 1 to 7 are implemented.

Images