Fault knowledge generation method and equipment

Abstract

The invention provides a fault knowledge generation method and equipment, and relates to the field of communication. The method is used for generating fault knowledge which is high in readability and normative in mathematical logic, and is friendly to both people and machines. The method comprises the following steps: acquiring original fault information; determining phenomenon description information and root cause reasoning information according to the original fault information; determining corresponding fault path information according to the phenomenon description information, wherein the fault path information indicates a relation path of the fault phenomenon; determining corresponding inference rule information according to the root cause inference information, wherein the inference rule information indicates a logic rule relationship of the fault; and generating fault knowledge information, wherein the fault knowledge information comprises fault path information and corresponding inference rule information.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of communication technology, and in particular to a method and device for generating fault knowledge. Background Art

[0002] In order to quickly resolve communication failure incidents in the network telecommunications field, troubleshooting applications built based on fault knowledge through big data technology and artificial intelligence technology can provide corresponding solutions, thereby achieving accurate and rapid troubleshooting.

[0003] At present, the construction of troubleshooting applications can be achieved by building a fault knowledge base. For example, taking the industry-wide knowledge graph as an example, a triple fault knowledge base can be built through knowledge graph technology. The triple fault knowledge includes the information of two device entities and the relationship information between the two device entities. The directed graph constructed by the knowledge graph establishes the graph edge association relationship, which provides the basis for the implementation of algorithms such as running search, random walk and network flow.

[0004] The current troubleshooting applications are built based on mathematical algorithms, which provide engineers with mathematical logic expressions. However, engineers need clear and explainable fault paths and fault logic reasoning chains. The current troubleshooting applications can only show users the associated event nodes in the graph network, lacking the business logic explainability of domain knowledge. Summary of the invention

[0005] The embodiments of the present application provide a method and device for generating fault knowledge, which are used to generate fault knowledge with strong readability and standardized mathematical logic, and are friendly to both humans and machines.

[0006] In a first aspect, an embodiment of the present application provides a method for generating fault knowledge, the method comprising: obtaining original fault information; determining phenomenon description information and root cause reasoning information based on the original fault information; determining corresponding fault path information based on the phenomenon description information, the fault path information indicating a relationship path of the fault phenomenon; determining corresponding reasoning rule information based on the root cause reasoning information, the reasoning rule information indicating a logical rule relationship between parameters of the fault; generating fault knowledge information, the fault knowledge information comprising fault path information and corresponding reasoning rule information.

[0007] In this possible implementation, an original fault information is cut into two parts: phenomenon description information and root cause reasoning information, and then fault path information with strong readability and human-friendly is generated; and mathematical logic specifications and machine-friendly reasoning rule information are generated. Finally, the generated fault knowledge information includes the above-mentioned fault path information and reasoning rule information, thereby realizing the generation of fault knowledge information that is friendly to both humans and machines.

[0008] In a possible implementation manner of the first aspect, the determining corresponding fault path information according to the phenomenon description information includes: extracting fault keywords from the phenomenon description information; and determining the fault path information according to the fault keywords.

[0009] In this possible implementation, network devices can extract keywords through semantic recognition technology, and then generate fault path information that is readable and explainable, which is friendly to engineers.

[0010] In a possible implementation manner of the first aspect, determining the fault path information according to the fault keyword includes: matching the fault path information in a fault path corpus according to the fault keyword.

[0011] In a possible implementation manner of the first aspect, the determining fault path information according to the fault keyword includes: generating a new fault path according to the fault keyword, the new fault path not belonging to a fault path corpus; and adding the new fault path to the fault path corpus.

[0012] In a possible implementation manner of the first aspect, the above-mentioned fault path information includes a fault phenomenon path, a root cause, a solution, and a corresponding case.

[0013] In a possible implementation manner of the first aspect, the determining corresponding reasoning rule information according to the root cause reasoning information includes: determining fault parameters and corresponding logical relationships according to the root cause reasoning information; and determining reasoning rule information according to the fault parameters and the corresponding logical relationships.

[0014] In this possible implementation, the network device can determine the fault parameters and the corresponding logical relationships to generate inference rule information, thereby achieving logic standardization and regular expression, and achieving structured and standardized generation of a fault knowledge base.

[0015] In a possible implementation manner of the first aspect, the above-mentioned inference rule information includes a first fault parameter, a second fault parameter and a relation symbol, and the relation symbol indicates a logical relationship between the first fault parameter and the second fault parameter.

[0016] In a possible implementation of the first aspect, the above-mentioned inference rule information includes a first expression, a second expression and a first relationship symbol, the first relationship symbol indicates the logical relationship between the first relationship symbol and the second relationship symbol; the first expression includes a first fault parameter, a second fault parameter and a second relationship symbol, the second relationship symbol indicates the logical relationship between the first fault parameter and the second fault parameter; the second expression includes a third fault parameter, a fourth fault parameter and a third relationship symbol, the third relationship symbol indicates the logical relationship between the first fault parameter and the second fault parameter.

[0017] In a second aspect, an embodiment of the present application provides a network device, including: a processor and a memory. The processor is coupled to the memory; the memory is used to store computer instructions, and the computer instructions are loaded and executed by the processor to enable the network device to implement any one of the methods provided in the first aspect.

[0018] In a third aspect, an embodiment of the present application provides a chip, comprising: a processor and an interface circuit; the interface circuit is used to receive code instructions and transmit them to the processor; the processor is used to run the code instructions to execute any one of the methods provided in the first aspect.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which at least one computer program instruction is stored, and the computer program instruction is loaded and executed by a processor to implement any one of the methods provided in the first aspect above.

[0020] In a fifth aspect, an embodiment of the present application provides a computer program product, including computer execution instructions, which, when executed on a computer, enable the computer to execute any one of the methods provided in the first aspect.

[0021] The technical effects brought about by any implementation method in the second to fifth aspects can refer to the technical effects brought about by the corresponding implementation methods in the first and second aspects, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A flowchart of a method for generating fault knowledge provided in an embodiment of the present application;

[0023] Figure 2 A schematic diagram of a format of a fault path provided in an embodiment of the present application;

[0024] Figure 3 A flowchart of another fault knowledge generation method provided in an embodiment of the present application;

[0025] Figure 4 A schematic diagram of the structure of a network device provided in an embodiment of the present application;

[0026] Figure 5 A schematic diagram of the structure of another network device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In the description of this application, unless otherwise specified, " / " indicates that the objects associated with each other are in an "or" relationship, for example, A / B can represent A or B; "and / or" in this application is merely a description of the association relationship between associated objects, indicating that three relationships may exist, for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural.

[0028] In the description of this application, unless otherwise specified, "plurality" means two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0029] In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference.

[0030] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0031] It is understood that the "embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the various embodiments in the entire specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It is understood that in various embodiments of the present application, the size of the sequence number of each process does not mean the order of execution, and 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 application.

[0032] It can be understood that some optional features in the embodiments of the present application may be implemented independently in certain scenarios without relying on other features, such as the solution on which they are currently based, to solve corresponding technical problems and achieve corresponding effects, or may be combined with other features according to needs in certain scenarios. Accordingly, the devices provided in the embodiments of the present application may also realize these features or functions accordingly, which will not be elaborated here.

[0033] In this application, unless otherwise specified, the same or similar parts between the various embodiments can refer to each other. In this application, if there is no special description or logical conflict between the various embodiments, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and different embodiments can be combined to form new embodiments according to their inherent logical relationships. The following implementation methods of this application do not constitute a limitation on the scope of protection of this application.

[0034] In order to quickly resolve communication failure incidents in the network telecommunications field, troubleshooting applications built based on fault knowledge through big data technology and artificial intelligence technology can provide corresponding solutions, thereby achieving accurate and rapid troubleshooting.

[0035] At present, the construction of troubleshooting applications can be achieved by building a fault knowledge base. For example, taking the industry-wide knowledge graph as an example, a triple fault knowledge base can be built through knowledge graph technology. The triple fault knowledge includes the information of two device entities and the relationship information between the two device entities. The directed graph constructed by the knowledge graph establishes the graph edge association relationship, which provides the basis for the implementation of algorithms such as running search, random walk and network flow.

[0036] A knowledge graph is a graph-based data structure consisting of nodes (points) and edges (edges). Each node represents an "entity" and each edge is a "relationship" between entities. A knowledge graph is essentially a semantic network.

[0037] The current troubleshooting applications are built based on mathematical algorithms, which provide engineers with mathematical logic expressions. However, engineers need clear and explainable fault paths and fault logic reasoning chains. The current troubleshooting applications can only show users the associated event nodes in the graph network, lacking the business logic explainability of domain knowledge.

[0038] Based on this, an embodiment of the present application provides a fault knowledge generation method, which includes: obtaining original fault information; determining phenomenon description information and root cause reasoning information based on the original fault information; determining corresponding fault path information based on the phenomenon description information, the fault path information indicates the relationship path of the fault phenomenon; determining corresponding reasoning rule information based on the root cause reasoning information, the reasoning rule information indicates the logical rule relationship of the fault; generating fault knowledge information, the fault knowledge information includes fault path information and corresponding reasoning rule information.

[0039] In the embodiments of the present application, the structured and standardized generation of fault knowledge can construct an independent fault knowledge database, which can assist field engineers in fault handling; can be called and presented by the telecommunications field fault handling automation platform or system for problem handling diagnosis; can form API knowledge components, open interfaces, and achieve docking with other telecommunications network elements or systems to achieve self-discovery, self-diagnosis and other functions. In addition, the structured and standardized generation of fault knowledge can also be used as an independent fault knowledge database or fault data base, which can be called by current artificial intelligence algorithm technology, and can greatly help intelligent operation and maintenance work from the two aspects of domain knowledge and data drive, and help realize automated operation and maintenance.

[0040] The fault knowledge generation method in the embodiment of the present application can be applied to various devices, such as terminal devices, network devices and servers, such as wireless base stations, controllers, switches, routers, storage servers, gateways and switches, and other devices. It can also be other methods that can apply the fault knowledge generation method in the embodiment of the present application, which is not limited here.

[0041] The terminal device can be referred to as a terminal, also known as user equipment (UE), which is a device with wireless transceiver function. The terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on the water (such as ships, etc.); it can also be deployed in the air (for example, on airplanes, drones, balloons and satellites, etc.). The terminal device can be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality terminal device, an augmented reality terminal device, a wireless terminal device in industrial control, a wireless terminal device in unmanned driving, a wireless terminal device in telemedicine, a wireless terminal device in smart grids, a wireless terminal device in transportation safety, a wireless terminal device in smart cities, and a wireless terminal device in smart homes. The terminal device can also be fixed or mobile. The embodiments of the present application are not limited to this.

[0042] In the embodiment of the present application, the device for realizing the function of the terminal may be a terminal device; or it may be a device capable of supporting the terminal device to realize the function, such as a chip system, which may be installed in the terminal device. In the embodiment of the present application, the chip system may be composed of a chip, or may include a chip and other discrete devices. In the technical solution provided in the embodiment of the present application, the technical solution provided in the embodiment of the present application is described by taking the device for realizing the function of the terminal device as an example that the terminal device is an example.

[0043] The network device may be an access network device, which may also be referred to as a radio access network (RAN) device, and is a device that provides wireless communication functions for terminal devices. Access network devices include, for example, but are not limited to: next generation base stations (generation nodeB, gNB) in 5G, evolved node B (evolved node B, eNB), baseband units (baseband units, BBU), transmitting and receiving points (transmitting and receiving points, TRP), transmitting points (transmitting points, TP), base stations in future mobile communication systems or access points in WiFi systems, etc. The access network device may also be a wireless controller, a centralized unit (CU), and / or a distributed unit (DU) in a cloud radio access network (CRAN) scenario, or the network device may be a relay station, an on-board device, and a network device in a future evolved PLMN network, etc.

[0044] The terminal device can communicate with multiple access network devices of different technologies. For example, the terminal device can communicate with an access network device supporting long term evolution (LTE), can communicate with an access network device supporting 5G, and can also communicate with an access network device supporting LTE and an access network device supporting 5G at the same time. The embodiments of the present application are not limited.

[0045] The technical solutions of the embodiments of the present application can be applied to various communication systems, for example: global system of mobile communication (GSM) system, code division multiple access (CDMA) system, wideband code division multiple access (WCDMA) system, general packet radio service (GPRS), long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), universal mobile telecommunication system (UMTS), worldwide interoperability for microwave access (WiMAX) communication system, fifth generation (5G) system or new radio (NR), etc.

[0046] Generally speaking, traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communications, but will also support, for example, internet of things (IoT) communications, device to device (D2D) communications, machine to machine (M2M) communications, machine type communications (MTC), vehicle to everything (V2X) communications, vehicle to vehicle (V2V) communications, vehicle to pedestrian (V2P) communications, vehicle to infrastructure (vehicle to infrastructure) communications, etc., without limitation.

[0047] It is understandable that in the embodiments of the present application, the execution subject may execute some or all of the steps in the embodiments of the present application, and these steps or operations are only examples. The embodiments of the present application may also execute other operations or variations of various operations. In addition, the various steps may be executed in different orders presented in the embodiments of the present application, and it is possible that not all operations in the embodiments of the present application need to be executed.

[0048] It should be noted that the message names between the devices or the names of the parameters in the messages in the following embodiments of the present application are only examples, and other names may be used in the specific implementation, and the embodiments of the present application do not specifically limit this.

[0049] like Figure 1 As shown, the embodiment of the present application provides a method for generating fault knowledge, which is described by taking application on a network device as an example. The method includes the following steps:

[0050] Step 101: The network device obtains original fault information.

[0051] The network device obtains original fault information, which may be information such as a fault problem case, a fault root cause report, and a fault handling guide.

[0052] like Figure 2 As shown, for example, the original fault information may be "By checking that the alarm ID is 33 and the value of the base station call system C is 0, it can be proved that the terminal user access failure is caused by transmission interruption, and transmission recovery is required to solve it." Among them, the manifestation of the fault is that the terminal user fails to connect due to transmission interruption, and the solution to be taken is transmission recovery.

[0053] Step 102: The network device determines phenomenon description information and root cause reasoning information.

[0054] After obtaining the original fault information, the network equipment can extract phenomenon description information and root cause reasoning information through natural language processing (NLP) technology.

[0055] In the embodiment of the present application, the phenomenon description information is a description of the fault phenomenon, indicating the phenomenon of the fault. For example, when the original fault information is "by checking that the alarm ID is 33 and the value of the base station call system C is 0, it can be proved that the terminal user access failure is caused by transmission interruption, and transmission recovery is required to solve it", the network device can extract the phenomenon description information "the terminal user access failure is caused by transmission interruption, and transmission recovery is required to solve it" through NLP technology.

[0056] like Figure 2As shown, in an embodiment of the present application, the root cause reasoning information is the reasoning logic information for the root cause of the fault. For example, when the original fault information is "by checking that the alarm ID is 33, and the value of the base station call system C is 0, it can be proved that the terminal user's access failure is caused by transmission interruption, and transmission recovery is required to solve it", the network device can extract the root cause reasoning information "checking that the alarm ID is 33, and the value of the base station call system C is 0" through NLP technology.

[0057] In the embodiment of the present application, the original fault information is divided into two parts: phenomenon description and root cause reasoning, which are processed separately, thereby avoiding mutual influence between the two parts.

[0058] 103. The network device determines corresponding fault path information according to the phenomenon description information.

[0059] The network device can determine corresponding fault path information according to the phenomenon description information, and the fault path information is fault relationship path information that already exists in the fault path library.

[0060] The network device can first extract the fault keywords in the phenomenon description information, such as call, failure, interruption, recovery, etc., and then determine the corresponding fault path information in the fault path library of the network device according to these fault keywords. The fault path information is easy for engineers to understand.

[0061] Specifically, in the embodiment of the present application, when the network device extracts fault keywords from the phenomenon description information, it essentially matches the fault keywords in the problem domain, mainly relying on a supervised or semi-supervised approach, and the fault keywords in the problem domain that match it can come from a manually maintained keyword thesaurus, that is, the phenomenon description information is matched with the fault keywords in the keyword thesaurus. In addition, other methods can also be used, for example, the network device can construct a problem description corpus (i.e., a keyword thesaurus) by combining a naive Bayes (NB) model or a support vector machine algorithm to support keyword extraction and matching of the phenomenon description information.

[0062] Specifically, in the embodiment of the present application, when the network device determines the fault path information, it can match the fault keywords with the prior fault information in the fault path corpus to determine the fault path information.

[0063] like Figure 3 As shown, the fault path corpus in the embodiment of the present application can be a tree-like directory branch structure, which is decomposed layer by layer from the overall phenomenon to the sub-phenomenon. The relationship between each level can be a general-specific relationship, a causal relationship, and a parallel relationship, etc. For example Figure 3As shown in the figure, under the phenomenon of "cell failure", there may be parallel reasons such as "cell unavailable", "cell service capability declines" and "cell outages", and under the phenomenon of "cell outages", there may be a reason of "transmission failure". It can be understood that "cell failure" and "cell unavailable", "cell service capability declines" and "cell outages" may be in a total-specific relationship, that is, cell failure includes these situations. "Cell outages" may be in a causal relationship with "transmission failure", that is, transmission failures cause cell outages.

[0064] like Figure 2 As shown, in an embodiment of the present application, for example, when the phenomenon description information is "the terminal user access failure is caused by transmission interruption, and transmission recovery is required to solve it", the corresponding fault path information is determined, and the fault path information is "access failure, the root cause is transmission interruption, and the solution is transmission recovery".

[0065] In the embodiment of the present application, the network device can determine the corresponding fault path information according to the phenomenon description information, and the fault path can be automatically generated by the network device; or it can be a manually formulated fault path template, and the network device matches it. Specific details are not limited here.

[0066] In one possible implementation, when the network device does not obtain fault path information based on the fault keyword and the fault path corpus, the network device can generate a new fault path based on the fault keyword, and the new fault path does not belong to the fault path corpus, and then the network device adds the new fault path to the fault path corpus.

[0067] In the embodiment of the present application, the fault path information may include information on three aspects: phenomenon path, root cause and solution. In addition, it may also include other information, such as information on "corresponding cases", which is not limited here.

[0068] In the embodiment of the present application, fault scenario path matching and keyword matching are performed on the phenomenon description information to generate a structured knowledge path, thereby achieving the representation of the complex cause and effect of network faults and having the interpretability and explainability of the domain knowledge process.

[0069] 104. The network device determines inference rule information according to the root cause inference information.

[0070] The network device determines the fault parameters and the corresponding logical relationship according to the reasoning information, and then determines the logical reasoning expression according to the fault parameters and the corresponding logical relationship.

[0071] It is understandable that the network device determines the inference rule information based on the root cause reasoning information, and can use the semantic interpretation algorithm based on NLP to assist manual work, extract the fault parameters and corresponding logical relationships in the root cause reasoning information, and convert it into a logical reasoning expression that can be recognized or easily understood by the machine.

[0072] Specifically, the network device determines the fault parameter based on the root cause reasoning information, which can be based on the matching of the root cause reasoning information with the log type keywords, such as "alarm ID", "error code" and "traffic statistics KPI" and other keywords. At the same time, the fault parameter can be a data structure of a key-value pair array. For example<name,value> It can be a key-value pair, where name indicates the parameter name of the fault parameter and value indicates the value of the fault parameter.

[0073] Specifically, the network device determines the logical relationship corresponding to the fault parameter according to the root cause reasoning information. The network device may normalize the logical relationship between the fault parameters in the root cause reasoning information according to the NLP algorithm, and convert the expression of the logical relationship into symbols that can be understood by the machine, for example, it is necessary to convert "equal" in the logical relationship into "==", and convert "not" in the logical relationship into "!=". For example, the network device may extract the judgment condition into an independent triple expression expr(a, r, b) or expr. The meaning of an independent triple expression expr(a, r, b) is shown in Table 1.

[0074] Table 1

[0075] Relational operation / r illustrate Example rule ＜ Less than a<b If a is less than b, the result is true. ＞ Greater than a>b If a is greater than b, the result is true. ＝＝ equal a==b If a is equal to b, the result is true. ！＝ Not equal to a!=b If a is not equal to b, the result is true. ＜＝ Less than or equal to a<=b If a is less than or equal to b, the result is true. ＞＝ Greater than or equal to a>=b If a is greater than or equal to b, the result is true.

[0076] In addition, multiple independent expressions expr can also be logically combined, as shown in Table 2.

[0077] Table 2

[0078]

[0079] like Figure 2As shown, for example, when the root cause reasoning information is "check that the alarm ID is 33, and the value of the base station conversation system C is 0", the fault parameter alarm ID and the base station conversation system C can be determined, the alarm ID value is 33, and the base station conversation system C value is 0; then the logical relationship is normalized and converted, and there are two reasoning rules, one is "the alarm ID value is 33", and the corresponding logical relationship symbol is "==", and the other is "the base station conversation system C value is 0", and the corresponding logical relationship symbol is "==". At the same time, according to the keywords "and" and "and", the logical relationship symbol between "the alarm ID value is 33" and "the base station conversation system C value is 0" is determined to be "&&", so that the final reasoning rule information is obtained as follows:

[0080] “

[0081] "Alarm ID == 33"

[0082] &&

[0083] "Base station call statistics C==0"

[0084] ”.

[0085] It can be understood that the inference rule information is machine-oriented fault knowledge information, so the inference rule information can be understood as the conditions for the network device to judge the occurrence of the fault event, that is, when the network device determines that the expression of the inference rule information is satisfied, the network device can determine that the fault event corresponding to the inference rule information has occurred.

[0086] In the embodiment of the present application, for the root cause reasoning information, the network device realizes the standardization and regular expression of mathematical logic through the logic paradigm transformation method. It is highly structured and can be used as a data base by the machine algorithm.

[0087] 105. The network device generates fault knowledge information.

[0088] The network device generates fault knowledge information, which includes fault path information and inference rule information.

[0089] In the embodiment of the present application, a corresponding relationship is established between the fault path information and the inference rule information to generate a complete fault knowledge information. The inference rule information forms a causal chain judgment support relationship with the fault path information, where the inference rule information is the cause and the fault path information is the effect.

[0090] Network equipment can build a fault knowledge base by generating multiple fault knowledge information. In the fault knowledge base, one fault path information can correspond to multiple reasoning rule information, but one reasoning rule information can only correspond to one fault path information. The fault knowledge base has both readable and interpretable expressions in the knowledge field and digital structures in the algorithm field. It can serve as a general data base in the fault field, pre-embed data structures and basic data for the application of artificial intelligence technology, and quickly realize product engineering and digital applications.

[0091] In the embodiment of the present application, the fault knowledge generation system based on semantic and mathematical rules, the network equipment extracts and divides the original fault information into phenomenon description information extraction and corresponding root cause reasoning information, and then generates the content of the fault knowledge base through scenario-based path matching generation and logical paradigm transformation. It can not only characterize the complex causal relationship of network faults, but also has the readability and interpretability of the domain knowledge process, which not only solves the expressibility and interpretability of industry domain information, but also has data structuring and standardization.

[0092] The embodiment of the present application provides a network device 400. In the embodiment of the present application, the network device 400 can be divided into functional modules according to the above method example. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0093] In the case of dividing each functional module into corresponding functional modules, Figure 4 A possible structural diagram of the network device 400 involved in the above embodiment is shown. Figure 4 As shown, the network device 400 includes:

[0094] The acquisition module 401 is used to acquire original fault information; for example, the step 101 in the above method embodiment is executed: the network device acquires original fault information.

[0095] The first determination module 402 is used to determine the phenomenon description information and the root cause reasoning information according to the original fault information; for example, executing step 102 in the above method embodiment: the network device determines the phenomenon description information and the root cause reasoning information.

[0096] The second determination module 403 is used to determine the corresponding fault path information according to the phenomenon description information, and the fault path information indicates the relationship path of the fault phenomenon; for example, executing step 103 in the above method embodiment: the network device determines the corresponding fault path information according to the phenomenon description information.

[0097] The second determining module 403 includes:

[0098] The extraction unit 404 is used to extract the fault keywords of the phenomenon description information; for example, the step 103 in the above method embodiment is executed: the network device determines the corresponding fault path information according to the phenomenon description information.

[0099] The first determining unit 405 is configured to determine the fault path information according to the fault keyword, for example, by executing step 103 in the above method embodiment: the network device determines the corresponding fault path information according to the phenomenon description information.

[0100] The first determining unit 405 is specifically configured to:

[0101] The fault path information in the fault path corpus is matched according to the fault keyword. For example, step 103 in the above method embodiment is performed: the network device determines the corresponding fault path information according to the phenomenon description information.

[0102] The third determination module 406 is used to determine corresponding reasoning rule information according to the root cause reasoning information, and the reasoning rule information indicates the logical rule relationship between the parameters of the fault; for example, executing step 104 in the above method embodiment: the network device determines the reasoning rule information according to the root cause reasoning information.

[0103] The third determination module 406 includes:

[0104] The second determining unit 407 is used to determine the fault parameters and the corresponding logical relationship according to the root cause reasoning information; for example, executing step 104 in the above method embodiment: the network device determines the reasoning rule information according to the root cause reasoning information.

[0105] The third determining unit 408 is configured to determine the inference rule information according to the fault parameter and the corresponding logical relationship, for example, by executing step 104 in the above method embodiment: the network device determines the inference rule information according to the root cause inference information.

[0106] The generating module 409 is used to generate fault knowledge information, wherein the fault knowledge information includes the fault path information and the corresponding inference rule information. For example, the step 105 in the above method embodiment is performed: the network device generates fault knowledge information.

[0107] The various modules of the above-mentioned network device can also be used to perform other actions in the above-mentioned method embodiment. All relevant contents of each step involved in the above-mentioned method embodiment can be referred to the functional description of the corresponding functional module and will not be repeated here.

[0108] Figure 5It is a schematic diagram of a network device structure provided in an embodiment of the present application. The network device 500 may include one or more central processing units (CPU) 501 and a memory 505. The memory 505 stores one or more application programs or data.

[0109] The memory 505 may be a volatile storage or a persistent storage. The program stored in the memory 505 may include one or more modules, each of which may include a series of instruction operations in the network device. Furthermore, the central processor 501 may be configured to communicate with the memory 505 and execute a series of instruction operations in the memory 505 on the network device 500.

[0110] The central processor 501 is used to execute the computer program in the memory 505, so that the network device 500 is used to perform: obtaining original fault information; determining phenomenon description information and root cause reasoning information according to the original fault information; determining corresponding fault path information according to the phenomenon description information, the fault path information indicates the relationship path of the fault phenomenon; determining corresponding reasoning rule information according to the root cause reasoning information, the reasoning rule information indicates the logical rule relationship of the fault; generating fault knowledge information, the fault knowledge information includes fault path information and corresponding reasoning rule information. For specific implementation methods, please refer to Figure 1 Steps 101-105 in the illustrated embodiment are not described in detail here.

[0111] The network device 500 may also include one or more power supplies 502, one or more wired or wireless network interfaces 503, one or more input and output interfaces 504, and / or one or more operating systems, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0112] The network device 500 can execute the aforementioned Figure 1 The operations performed by the network device in the illustrated embodiment will not be described in detail here.

[0113] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loading and executing computer program instructions on a computer, all or part of the processes (or functions) described in the embodiments of the present application are implemented. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or may contain one or more servers, data centers and other data storage devices that can be integrated with the medium. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)), etc. In the embodiment of the present application, the computer may include the aforementioned device.

[0114] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in a claim. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

Claims

1. A method for generating fault knowledge, characterized in that: The method comprises: Get original fault information; Determine phenomenon description information and corresponding root cause reasoning information according to the original fault information; Determine corresponding fault path information according to the phenomenon description information, wherein the fault path information indicates a relationship path of the fault phenomenon; Determine corresponding reasoning rule information according to the root cause reasoning information, wherein the reasoning rule information indicates a logical rule relationship between parameters of the fault; Fault knowledge information is generated, wherein the fault knowledge information includes the fault path information and the corresponding inference rule information.

2. The method according to claim 1, characterized in that The determining corresponding fault path information according to the phenomenon description information includes: Extracting fault keywords from the phenomenon description information; Fault path information is determined according to the fault keyword.

3. The method according to claim 2, characterized in that The determining of fault path information according to the fault keyword includes: The fault path information in the fault path corpus is matched according to the fault keyword.

4. The method according to claim 3, characterized in that: The fault path information includes the fault phenomenon path, root cause, solution and corresponding case.

5. The method according to any one of claims 1 to 4, characterized in that: The determining corresponding inference rule information according to the root cause inference information includes: Determine fault parameters and corresponding logical relationships according to the root cause reasoning information; Inference rule information is determined according to the fault parameters and corresponding logical relationships.

6. The method according to claim 5, characterized in that The inference rule information includes a first fault parameter, a second fault parameter, and a relation symbol, wherein the relation symbol indicates a logical relationship between the first fault parameter and the second fault parameter.

7. The method according to claim 5, characterized in that The inference rule information includes a first expression, a second expression and a first relation symbol, wherein the first relation symbol indicates a logical relationship between the first relation symbol and the second relation symbol; the first expression includes a first fault parameter, a second fault parameter and a second relation symbol, wherein the second relation symbol indicates a logical relationship between the first fault parameter and the second fault parameter; the second expression includes a third fault parameter, a fourth fault parameter and a third relation symbol, wherein the third relation symbol indicates a logical relationship between the first fault parameter and the second fault parameter.

8. A network device, characterized in that: The network equipment includes: An acquisition module is used to obtain original fault information; A first determination module, configured to determine phenomenon description information and root cause reasoning information according to the original fault information; A second determination module, configured to determine corresponding fault path information according to the phenomenon description information, wherein the fault path information indicates a relationship path of the fault phenomenon; A third determination module, configured to determine corresponding reasoning rule information according to the root cause reasoning information, wherein the reasoning rule information indicates a logical rule relationship between parameters of the fault; A generation module is used to generate fault knowledge information, wherein the fault knowledge information includes the fault path information and the corresponding inference rule information.

9. The network device according to claim 8, characterized in that: The second determining module comprises: An extraction unit, used to extract fault keywords from the phenomenon description information; The first determining unit is used to determine the fault path information according to the fault keyword.

10. The network device according to claim 9, characterized in that: The first determining unit is specifically configured to: The fault path information in the fault path corpus is matched according to the fault keyword.

11. The network device according to any one of claims 8 to 10, characterized in that: The third determination module comprises: A second determining unit, configured to determine fault parameters and corresponding logical relationships according to the root cause reasoning information; The third determining unit is used to determine the inference rule information according to the fault parameters and the corresponding logical relationship.

12. A network device, characterized in that: The network device comprises a processor and a memory; the processor is coupled to the memory; the memory is used to store computer instructions, and the computer instructions are loaded and executed by the processor to enable the network device to implement the method according to any one of claims 1-7.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one computer program instruction, and the computer program instruction is loaded and executed by a processor to implement the method according to any one of claims 1 to 7.

Images