Network fault diagnosis method, equipment and device

Abstract

The embodiment of the invention provides a network fault diagnosis method, equipment and device. The method comprises the steps of obtaining a target fault description corresponding to a target base station under the condition of determining that the target base station is in an abnormal working state; based on the target fault description, determining a target fault reason when the target base station is in an abnormal working state in a network fault knowledge graph; wherein the network fault knowledge graph comprises a corresponding relationship between a plurality of fault descriptions and a plurality of fault causes. The network fault diagnosis method, equipment and device provided by the invention are used for improving the fault diagnosis efficiency of the base station.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a network fault diagnosis method, equipment and device. Background Art

[0002] Network failure usually refers to network abnormalities caused by various reasons such as interference, channel fading, air interface failure or improper base station parameter settings.

[0003] At present, the diagnosis process of network faults includes the following three stages: fault detection stage, fault diagnosis stage and network recovery stage. In the fault detection stage, the key performance indicators (KPI) of the base station are obtained, and the KPI is used to determine whether the base station has a network fault. In the fault diagnosis stage, the operation and maintenance personnel locate the cause of the network fault based on the KPI and the log information of the base station. In the network recovery stage, based on the above reasons, a reasonable plan is formulated to implement the recovery task for the network fault.

[0004] In the above-mentioned related technologies, during the fault diagnosis stage, operation and maintenance personnel locate the cause of the network fault based on KPI and log information of the base station, resulting in low efficiency in fault diagnosis of the base station. Summary of the invention

[0005] The embodiments of the present application provide a network fault diagnosis method, device and apparatus to solve the defect of low efficiency of fault diagnosis of base stations in the prior art and achieve the purpose of improving the efficiency of fault diagnosis of base stations.

[0006] In a first aspect, an embodiment of the present application provides a network fault diagnosis method, including:

[0007] When it is determined that the target base station is in an abnormal working state, obtaining a target fault description corresponding to the target base station;

[0008] Based on the target fault description, a target fault cause of the target base station being in an abnormal working state is determined in a network fault knowledge graph, wherein the network fault knowledge graph includes a correspondence between multiple fault descriptions and multiple fault causes.

[0009] Optionally, according to a network fault diagnosis method according to an embodiment of the present application, the determining that the target base station is in an abnormal working state includes:

[0010] Obtaining actual operating values ​​of each of a plurality of network indicators of the target base station;

[0011] For each network indicator, determining whether an actual operating value of the network indicator satisfies a fault detection rule corresponding to the network indicator;

[0012] When the fault detection rule is met, it is determined that the target base station is in an abnormal working state.

[0013] Optionally, according to a network fault diagnosis method according to an embodiment of the present application, the obtaining a target fault description corresponding to the target base station includes:

[0014] Determine the fault description corresponding to the network indicator in a preset mapping relationship; wherein the preset mapping relationship includes a correspondence relationship between multiple network indicators and multiple fault descriptions;

[0015] The fault description corresponding to the network indicator is determined as the target fault description.

[0016] Optionally, according to a network fault diagnosis method of an embodiment of the present application, determining the target fault cause of the target base station being in an abnormal working state in the network fault knowledge graph based on the target fault description includes:

[0017] Searching for a fault name corresponding to the target fault description in the network fault knowledge graph;

[0018] In the case where a fault name corresponding to the target fault description is found, the fault name is determined as the target fault name;

[0019] Based on the target fault name, a target fault cause of the target base station being in an abnormal working state is determined in the network fault knowledge graph.

[0020] Optionally, according to a network fault diagnosis method of an embodiment of the present application, determining, based on the target fault name, in the network fault knowledge graph, a target fault cause of the target base station being in an abnormal working state, includes:

[0021] Acquire multiple fault causes corresponding to the target fault name from the network fault knowledge graph;

[0022] For each of the multiple fault causes, based on historical fault information of the target base station, determine the number of occurrences of the fault cause;

[0023] The fault cause with the largest number of occurrences is determined as the target fault cause.

[0024] Optionally, according to a network fault diagnosis method of an embodiment of the present application, determining, based on the target fault name, in the network fault knowledge graph, a target fault cause of the target base station being in an abnormal working state, includes:

[0025] Determine whether the target fault corresponding to the target fault name is a hot fault;

[0026] When the target fault is a hot fault, for each of the multiple fault causes corresponding to the target fault name in the network fault knowledge graph, The fault cause is processed to obtain a predicted score of the fault cause; wherein u represents the target fault, i represents the fault cause, and P(u,i) represents the predicted score of the fault cause i. represents the average score of the target fault u, P u represents the word vector of the target fault name, v represents the associated fault of the target fault, P v The word vector representing the associated fault name of the associated fault v, sim(P u ,P v ) indicates P u and P v The word vector similarity between them, V represents the set of all associated faults of the target fault, r vi represents the score of the fault cause i that causes the associated fault v, represents the average score of the associated fault v, r ui A second preset score indicating that the fault cause u leads to the target fault i;

[0027] In the case where the target fault is a non-hot fault, for each fault cause, determine whether the fault cause is a hot cause; in the case where the fault cause is a hot cause, Determine the predicted score of the fault cause; where r b represents a first preset score; when the fault cause is a non-popular cause, the first preset score is determined as the predicted score of the fault cause;

[0028] The fault cause with the largest predicted score among the multiple fault causes is determined as the target fault cause.

[0029] Optionally, according to a network fault diagnosis method of an embodiment of the present application, the network fault knowledge graph includes multiple fault descriptions; the method further includes:

[0030] In the case where the target fault cause is determined to be an error cause, determining, for each fault description in the multiple fault descriptions, a text similarity between the target fault description and the fault description;

[0031] Determine the fault description with the greatest text similarity as the intermediate fault description;

[0032] Determine a new fault name based on the intermediate fault name corresponding to the intermediate fault description in the network fault knowledge graph;

[0033] Based on the new fault name, a new fault cause for the target base station to be in an abnormal working state is determined in the network fault knowledge graph.

[0034] Optionally, according to a network fault diagnosis method of an embodiment of the present application, determining a new fault name based on an intermediate fault name corresponding to the intermediate fault description in the network fault knowledge graph includes:

[0035] The associated fault name of the intermediate fault name is determined as the new fault name.

[0036] In a second aspect, an embodiment of the present application further provides a network fault diagnosis device, including: a memory, a transceiver, and a processor, wherein:

[0037] Memory for storing computer programs;

[0038] a transceiver, for transmitting and receiving data under the control of the processor;

[0039] A processor is configured to read the computer program in the memory and perform the following operations:

[0040] When it is determined that the target base station is in an abnormal working state, obtaining a target fault description corresponding to the target base station;

[0041] Based on the target fault description, a target fault cause of the target base station being in an abnormal working state is determined in a network fault knowledge graph, wherein the network fault knowledge graph includes a correspondence between multiple fault descriptions and multiple fault causes.

[0042] Optionally, according to a network fault diagnosis device according to an embodiment of the present application, the determining that the target base station is in an abnormal working state includes:

[0043] Obtaining actual operating values ​​of each of a plurality of network indicators of the target base station;

[0044] For each network indicator, determining whether an actual operating value of the network indicator satisfies a fault detection rule corresponding to the network indicator;

[0045] When the fault detection rule is met, it is determined that the target base station is in an abnormal working state.

[0046] Optionally, according to a network fault diagnosis device of an embodiment of the present application, the acquiring a target fault description corresponding to the target base station includes:

[0047] Determine the fault description corresponding to the network indicator in a preset mapping relationship; wherein the preset mapping relationship includes a correspondence relationship between multiple network indicators and multiple fault descriptions;

[0048] The fault description corresponding to the network indicator is determined as the target fault description.

[0049] Optionally, according to a network fault diagnosis device of an embodiment of the present application, determining, based on the target fault description, a target fault cause of the target base station being in an abnormal working state in a network fault knowledge graph includes:

[0050] Searching for a fault name corresponding to the target fault description in the network fault knowledge graph;

[0051] In the case where a fault name corresponding to the target fault description is found, the fault name is determined as the target fault name;

[0052] Based on the target fault name, a target fault cause of the target base station being in an abnormal working state is determined in the network fault knowledge graph.

[0053] Optionally, according to a network fault diagnosis device of an embodiment of the present application, determining, based on the target fault name, in the network fault knowledge graph, a target fault cause of the target base station being in an abnormal working state, includes:

[0054] Acquire multiple fault causes corresponding to the target fault name from the network fault knowledge graph;

[0055] For each of the multiple fault causes, based on historical fault information of the target base station, determine the number of occurrences of the fault cause;

[0056] The fault cause with the largest number of occurrences is determined as the target fault cause.

[0057] Optionally, according to a network fault diagnosis device of an embodiment of the present application, determining, based on the target fault name, in the network fault knowledge graph, a target fault cause of the target base station being in an abnormal working state, includes:

[0058] Determine whether the target fault corresponding to the target fault name is a hot fault;

[0059] When the target fault is a hot fault, for each of the multiple fault causes corresponding to the target fault name in the network fault knowledge graph, The fault cause is processed to obtain a predicted score of the fault cause; wherein u represents the target fault, i represents the fault cause, and P(u,i) represents the predicted score of the fault cause i. represents the average score of the target fault u, P u represents the word vector of the target fault name, v represents the associated fault of the target fault, P v The word vector representing the associated fault name of the associated fault v, sim(P u ,P v ) indicates P u and P v The word vector similarity between them, V represents the set of all associated faults of the target fault, r vi represents the score of the fault cause i that causes the associated fault v, represents the average score of the associated fault v, r ui A second preset score indicating that the fault cause u leads to the target fault i;

[0060] In the case where the target fault is a non-hot fault, for each fault cause, determine whether the fault cause is a hot cause; in the case where the fault cause is a hot cause, Determine the predicted score of the fault cause; where r b represents a first preset score; when the fault cause is a non-popular cause, the first preset score is determined as the predicted score of the fault cause;

[0061] The fault cause with the largest predicted score among the multiple fault causes is determined as the target fault cause.

[0062] Optionally, according to a network fault diagnosis device of an embodiment of the present application, the network fault knowledge graph includes multiple fault descriptions; and the processor is further configured to perform the following operations:

[0063] In the case where the target fault cause is determined to be an error cause, determining, for each fault description in the multiple fault descriptions, a text similarity between the target fault description and the fault description;

[0064] Determine the fault description with the greatest text similarity as the intermediate fault description;

[0065] Determine a new fault name based on the intermediate fault name corresponding to the intermediate fault description in the network fault knowledge graph;

[0066] Based on the new fault name, a new fault cause for the target base station to be in an abnormal working state is determined in the network fault knowledge graph.

[0067] Optionally, according to a network fault diagnosis device of an embodiment of the present application, the determining a new fault name based on the intermediate fault name corresponding to the intermediate fault description in the network fault knowledge graph includes:

[0068] The associated fault name of the intermediate fault name is determined as the new fault name.

[0069] In a third aspect, an embodiment of the present application further provides a network fault diagnosis device, including:

[0070] An acquisition module, configured to acquire a target fault description corresponding to the target base station when it is determined that the target base station is in an abnormal working state;

[0071] A determination module is used to determine a target fault cause of the target base station being in an abnormal working state in a network fault knowledge graph based on the target fault description, wherein the network fault knowledge graph includes a correspondence between multiple fault descriptions and multiple fault causes.

[0072] In a fourth aspect, an embodiment of the present application further provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the network fault diagnosis method as described in the first aspect above.

[0073] A network fault diagnosis method, device and apparatus provided in the embodiments of the present application obtain a target fault description corresponding to a target base station when it is determined that the target base station is in an abnormal working state; based on the target fault description, the target fault cause of the target base station being in an abnormal working state is determined in a network fault knowledge graph, thereby solving the problem of low efficiency of fault diagnosis of base stations caused by operation and maintenance personnel locating the cause of network faults based on KPIs and base station log information, thereby improving the efficiency of fault diagnosis of base stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0075] Figure 1 It is a flowchart of a network fault diagnosis method provided by an embodiment of the present application;

[0076] Figure 2 It is one of the structural schematic diagrams of the network fault knowledge graph provided in the embodiment of the present application;

[0077] Figure 3 It is a flowchart of a method for determining that a target base station is in an abnormal working state provided by an embodiment of the present application;

[0078] Figure 4 It is a flowchart of a method for determining a target fault name provided in an embodiment of the present application;

[0079] Figure 5 This is the second structural diagram of the network fault knowledge graph provided in the embodiment of the present application;

[0080] Figure 6 is a schematic flow chart of a method for determining a new fault cause provided by an embodiment of the present invention;

[0081] Figure 7 This is the second flow chart of the method for determining the cause of a target failure provided in an embodiment of the present application;

[0082] Figure 8 It is a structural diagram of a network fault diagnosis device provided in an embodiment of the present application;

[0083] Fig. 9 It is a structural diagram of a network fault diagnosis device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0084] In the present application, the term "include" and its variations may refer to non-restrictive inclusion; the term "or" and its variations may refer to "and / or". The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. In the present application, "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previously associated objects are in an "or" relationship.

[0085] In the embodiments of the present application, the term "plurality" refers to two or more than two, and other quantifiers are similar.

[0086] The technical solution provided in the embodiment of the present application can be applied to a variety of systems, such as non-terrestrial networks (NTN) and 5G systems. For example, the applicable system can also be a global system of mobile communication (GSM) system, a code division multiple access (CDMA) system, a wideband code division multiple access (WCDMA) general packet radio service (GPRS) system, a long term evolution (LTE) system, a LTE frequency division duplex (FDD) system, a LTE time division duplex (TDD) system, an advanced long term evolution (LTE-A) system, a universal mobile telecommunication system (UMTS), a world-wide interoperability for microwave access (WiMAX) system, a 5G new radio (NR) system, etc. These various systems include terminals and network equipment. The system may also include a core network part, such as an evolved packet system (EPS), a 5G system (5GS), etc.

[0087] With the continuous development and progress of mobile communication technology, the emergence of heterogeneous networks meets more different business needs. At the same time, with the popularization of 5G networks, communication networks have become more complex and heterogeneous, which has increased the complexity of operating and maintaining communication networks. The diagnosis of network faults is a key link to enable communication networks to operate sustainably and healthily. However, the existing methods for diagnosing network faults mostly rely on manual testing and time accumulation, and there are problems such as long optimization cycles and high resource consumption. Therefore, in the process of diagnosing network faults, operators need to find new strategies to maintain their competitiveness.

[0088] In the related art, during the fault diagnosis stage of the network fault diagnosis process, operation and maintenance personnel locate the cause of the network fault based on KPI and base station log information, resulting in low efficiency in base station fault diagnosis.

[0089] In the embodiments of the present application, a network fault diagnosis method, device and apparatus are provided to improve the efficiency of fault diagnosis of base stations. In the embodiments of the present application, the network fault diagnosis method and the network fault diagnosis apparatus are based on the same application concept. Since the network fault diagnosis method and the network fault diagnosis apparatus solve the problem in a similar way, the implementation of the network fault diagnosis apparatus and the network fault diagnosis method can refer to each other, and the repeated parts will not be repeated.

[0090] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0091] Figure 1 FIG. 1 is a flow chart of a network fault diagnosis method provided in an embodiment of the present application. Figure 1 As shown, the method includes:

[0092] Step 101: When it is determined that a target base station is in an abnormal working state, a target fault description corresponding to the target base station is obtained.

[0093] Optionally, the network fault diagnosis method provided by the present application may be executed by a network fault diagnosis device or a network fault diagnosis apparatus provided in the network fault diagnosis device. The network fault diagnosis apparatus may be implemented by a combination of software and / or hardware.

[0094] The target base station can be a 4G base station or a 5G base station.

[0095] The situation where the target base station is in an abnormal working state may be, for example, an abnormal reference signal receiving power (RSRP) (RSRP is less than or equal to -85dBm), an abnormal wireless connection rate (wireless connection rate is less than or equal to 99%), or an abnormal wireless resource control (RRC) connection establishment success rate (RRC connection establishment success rate is less than or equal to 99%), etc.

[0096] The target fault description is a description of a phenomenon corresponding to when the target base station is in an abnormal working state.

[0097] For example, in the case where the RSRP of the target base station is abnormal, the target fault description is "low indoor / outdoor service connection success rate".

[0098] For example, in the case where the wireless connection rate of the target base station is abnormal, the target fault description is "slow Internet speed and poor signal for making and receiving calls."

[0099] For example, when the success rate of establishing the RRC connection of the target base station is abnormal, the target fault description is "the cell cannot establish the service normally and there is no response after sending the RRC connection request".

[0100] Step 102: Based on the target fault description, determine the target fault cause of the target base station being in an abnormal working state in the network fault knowledge graph, wherein the network fault knowledge graph includes a correspondence between multiple fault descriptions and multiple fault causes.

[0101] Optionally, when the network fault knowledge graph includes multiple fault descriptions and multiple fault causes, the fault cause corresponding to the target fault description is determined as the target fault cause of the target base station being in an abnormal working state.

[0102] Optionally, a network fault knowledge graph can be constructed based on expert knowledge through preset tools.

[0103] The expert knowledge is the experiential knowledge acquired by experts in the field of communication technology in long-term work practice, and the expert knowledge includes network fault information data.

[0104] The preset tool may be, for example, Apache Spark GraphFrames.

[0105] Optionally, a network fault knowledge graph may be constructed through the following first step to second step.

[0106] The first step is to extract knowledge from network fault information data to obtain entity information and attribute information.

[0107] In the second step, the entity information and attribute information are filled into the pattern layer ontology of the attribute graph to obtain the network fault knowledge graph.

[0108] The network fault knowledge graph may be a property graph.

[0109] A property graph is a graph structure that contains nodes, edges, and attributes. Nodes represent entities, edges connect a pair of nodes, and edges are the relationship between nodes. Nodes and edges have labels and attributes.

[0110] For example, the attributes of an entity may be fault description, fault name, fault cause, fault solution, solution type, possible accidents caused by the fault, fault location, and associated fault names.

[0111] For example, the attributes of an edge can be "cause", "cause", "location", "description", "scheme type", "solution", or "association".

[0112] For example, the relationship between the fault description and the fault name is "description", the relationship between the fault location and the fault name is "location", the relationship between the fault solution and the fault name is "solution", the relationship between the fault solution and the solution type is "solution type", the relationship between the possible accident caused by the fault and the fault name is "trigger", the relationship between the fault cause and the fault name is "cause", and the relationship between the associated fault name and the fault name is "association".

[0113] For example, when the attribute of the entity is a fault description, the entity may be "low indoor / outdoor service connection success rate"; when the attribute of the entity is a fault name, the entity may be "RSRP abnormality".

[0114] Combine the following Figure 2 , the network fault knowledge graph is explained exemplarily.

[0115] Figure 2 This is one of the structural diagrams of the network fault knowledge graph provided in the embodiment of the present application. Figure 2 As shown, the network fault knowledge graph includes entities 1 to 7; among them, the attribute of entity 1 is fault description, the attribute of entity 2 is fault name, the attribute of entity 3 is fault cause, the attribute of entity 4 is fault solution, the attribute of entity 5 is solution type, the attribute of entity 6 is possible accident caused by the fault, the attribute of entity 7 is fault location, and the attribute of entity 8 is the associated fault name.

[0116] It should be noted that the same fault name may correspond to one or more fault descriptions, fault causes, fault solutions, solution types, possible accidents caused by the faults, and fault locations.

[0117] For example, when the fault name is "abnormal RRC connection establishment success rate", the fault description corresponding to the fault name is "the cell cannot establish services normally, and there is no response after sending the RRC connection request", the fault cause corresponding to the fault name is "timer timeout", the fault solution corresponding to the fault name is "optimize the timer waiting for RRC establishment completion from 2 seconds to 5 seconds", the fault solution corresponding to the fault name is "parameter adjustment", the fault corresponding to the fault name may cause an accident of "network paralysis", and the fault location corresponding to the fault name is "timer".

[0118] In an embodiment of the present application, when it is determined that the target base station is in an abnormal working state, a target fault description corresponding to the target base station is obtained; based on the target fault description, the target fault cause of the target base station being in an abnormal working state is determined in the network fault knowledge graph, and there is no need for operation and maintenance personnel to locate the cause of the network fault based on KPIs and base station log information, etc. Instead, through the network fault knowledge graph, based on the target fault description of the target base station, the target fault cause can be automatically determined without manual participation, thereby reducing labor costs and improving fault diagnosis efficiency for the target base station.

[0119] Figure 3 1 is a flow chart of a method for determining that a target base station is in an abnormal working state provided by an embodiment of the present application. Figure 3 As shown, the method includes:

[0120] Step 301: Obtain actual operating values ​​of multiple network indicators of a target base station.

[0121] Optionally, the multiple network indicators include at least two of the following:

[0122] RSRP;

[0123] Reference Signal Receiving Quality (RSRQ);

[0124] Coverage rate;

[0125] RRC connection establishment success rate;

[0126] Evolved Radio Access Bearer (E-RAB) establishment success rate;

[0127] Wireless connection rate;

[0128] Abnormal call drop rate of RRC connection;

[0129] E-RAB call drop rate;

[0130] Call Setup Success Rate (CSSR);

[0131] Call establishment delay for Voice over New Radio (VoNR).

[0132] For example, when the target base station is a 5G base station, the actual operating value of RSRP can be in the range of -31 to 153 decibel milliwatts (dBm), and the actual operating value of RSRQ can be in the range of -43 to 20.

[0133] For example, when the target base station is a 4G base station, the actual operating value of RSRP may be in the range of -44 to 140 dBm, and the actual operating value of RSRQ may be in the range of -3 to -19.5.

[0134] For example, the actual running value of coverage may be 99%, etc.

[0135] For example, the actual operating value of the RRC connection establishment success rate may be 98%, etc.

[0136] For example, the actual operating value of the wireless connection rate may be 82%.

[0137] Step 302: for each network indicator, determine whether the actual operating value of the network indicator satisfies the fault detection rule corresponding to the network indicator.

[0138] Step 303: When the fault detection rule is met, determine that the target base station is in an abnormal working state.

[0139] In the following, in conjunction with Table 1, the process of determining whether the target base station is in an abnormal working state is exemplarily described.

[0140] Table 1

[0141] Network Metrics Fault detection rules RSRP RSRP≤-85dBm Wireless connection rate Wireless connection rate ≤ 99% Coverage Coverage rate <98% RRC connection establishment success rate RRC connection establishment success rate <90%

[0142] As shown in Table 1, "RSRP ≤ -85dBm" means that when RSRP is less than or equal to -85dBm, the target base station is in an abnormal working state. For example, when the actual operating value of RSRP is -90dBm, since -90dBm < -85dBm, the actual operating value of RSRP does not meet the fault detection rule corresponding to RSRP, so the target base station is in an abnormal working state.

[0143] As shown in Table 1, "coverage rate < 98%" means that when the coverage rate is less than 98%, the target base station is in an abnormal working state. For example, when the actual operating value of the coverage rate is 97%, since 97% < 98%, the actual operating value of the coverage rate does not meet the fault detection rule corresponding to the coverage rate, and therefore the target base station is in an abnormal working state.

[0144] In an embodiment of the present application, actual operating values ​​of multiple network indicators of the target base station are obtained, and for each network indicator, it is determined whether the actual operating value of the network indicator satisfies the fault detection rule corresponding to the network indicator. When the fault detection rule is satisfied, it is determined that the target base station is in an abnormal working state. There is no need for operation and maintenance personnel to judge whether the target base station is in an abnormal working state based on their own experience, thereby improving the accuracy of fault diagnosis for the target base station.

[0145] In some embodiments, the acquiring a target fault description corresponding to the target base station includes:

[0146] Determine the fault description corresponding to the network indicator in the preset mapping relationship; wherein the preset mapping relationship includes a correspondence relationship between multiple network indicators and multiple fault descriptions;

[0147] The fault description corresponding to the network indicator is determined as the target fault description.

[0148] Below, based on Table 1 and in combination with Table 2, the process of determining the target fault description is exemplarily described.

[0149] Table 2

[0150]

[0151] As shown in Table 2, when the network indicator is RSRP, the fault description corresponding to RSRP is "low indoor / outdoor service connection success rate", and "low indoor / outdoor service connection success rate" is determined as the target fault description.

[0152] As shown in Table 2, when the network indicator is the RRC connection establishment success rate, the fault description corresponding to the RRC connection establishment success rate is "the cell cannot establish the service normally, and there is no response after sending the RRC connection request", and "the cell cannot establish the service normally, and there is no response after sending the RRC connection request" is determined as the target fault description.

[0153] Figure 4 Schematic diagram of the method for determining the target fault name provided by the embodiment of the present application. Figure 4 As shown, the method includes:

[0154] Step 401: Search the network fault knowledge graph for the fault name corresponding to the target fault description.

[0155] Step 402: When a fault name corresponding to the target fault description is found, the fault name is determined as the target fault name.

[0156] Optionally, when the network fault knowledge graph includes multiple fault descriptions and multiple fault names, the fault name corresponding to the target fault description is determined as the target fault name.

[0157] Below, in Figure 2 Based on Figure 5 , taking the target fault description of "the cell cannot establish services normally and there is no response after sending the RRC connection request" as an example, the process of finding the fault name is explained.

[0158] Figure 5This is the second structural diagram of the network fault knowledge graph provided in the embodiment of the present application. Figure 5 As shown, the network fault knowledge graph includes "the cell cannot establish services normally, and there is no response after sending the RRC connection request" (fault description 1), "RRC connection establishment success rate is abnormal" (fault name 1), "indoor / outdoor service connection success rate is low" (fault description 2) and "RSRP abnormality" (fault description 2); among them, fault name 1 corresponds to fault description 1, and fault name 2 corresponds to fault description 2.

[0159] When the target fault description is "the cell cannot establish services normally and there is no response after sending the RRC connection request", based on the network fault knowledge graph, the fault name corresponding to the target fault description is determined to be "abnormal RRC connection establishment success rate".

[0160] Step 403: Based on the target fault name, determine the target fault cause of the target base station being in an abnormal working state in the network fault knowledge graph.

[0161] In an embodiment of the present application, a fault name corresponding to the target fault description is searched in the network fault knowledge graph. When the fault name corresponding to the target fault description is found, the fault name is determined as the target fault name. Based on the target fault name, the target fault cause of the target base station being in an abnormal working state is determined in the network fault knowledge graph. There is no need for operation and maintenance personnel to analyze the target base station based on personal experience to determine the target fault cause of the target base station being in an abnormal working state, thereby improving the fault diagnosis efficiency of the base station.

[0162] Furthermore, in the related art, operation and maintenance personnel diagnose base station faults based on personal experience, which may lead to inaccurate fault location. In the embodiment of the present application, the target fault cause is found in the network fault knowledge graph, which improves the accuracy of base station fault diagnosis, thereby further improving the efficiency of base station fault diagnosis.

[0163] In some embodiments, based on the target fault name, determining the target fault cause of the target base station being in an abnormal working state in the network fault knowledge graph includes:

[0164] Obtain multiple fault causes corresponding to the target fault name from the network fault knowledge graph;

[0165] For each of the multiple fault causes, based on historical fault information of the target base station, determining the number of occurrences of the fault cause;

[0166] The fault cause with the largest number of occurrences is determined as the target fault cause.

[0167] The fault cause is the cause of the target fault corresponding to the target fault name.

[0168] For example, when the target fault name is "abnormal wireless connection rate", the multiple fault causes corresponding to the target fault name may be "insufficient wireless resources", "UE response timeout" and "error in the master / slave setting of the transmission convergence layer device".

[0169] In the following, in conjunction with Table 3, the process of determining the number of occurrences of the fault cause is exemplarily described.

[0170] As shown in Table 3, the historical fault information includes multiple fault causes and the occurrence time of each fault cause.

[0171] Table 3

[0172]

[0173] Optionally, determining the number of occurrences of the fault cause based on historical fault information of the target base station includes:

[0174] For each fault cause, count the number of occurrences of the fault cause in historical fault information.

[0175] As shown in Table 3, "Insufficient unlimited resources" occurs 3 times, "UE response timeout" occurs 1 time, and "Transmission convergence layer device master / slave setting error" occurs 1 time.

[0176] As shown in Table 3, the occurrence number of “Insufficient infinite resources” is 3 times, so “Insufficient infinite resources” is determined as the target fault cause.

[0177] In an embodiment of the present application, multiple fault causes corresponding to the target fault name are obtained from the network fault knowledge graph, and for each of the multiple fault causes, the number of occurrences of the fault cause is determined based on the historical fault information of the target base station, and the fault cause with the largest number of occurrences is determined as the target fault cause. Based on the characteristics of the target base station itself, that is, the fault cause that has appeared more times in historical time has a higher probability of causing the target base station to be in an abnormal state, the target fault cause determined in this way is more accurate, thereby improving the accuracy of fault diagnosis of the base station.

[0178] Figure 6 FIG. 1 is a flow chart of a method for determining the cause of a new fault provided by an embodiment of the present invention. Figure 6 As shown, the network fault knowledge graph includes multiple fault descriptions, and the method for determining the cause of a new fault includes:

[0179] Step 601: When it is determined that the target fault cause is an error cause, determine the text similarity between the target fault description and the fault description for each fault description in a plurality of fault descriptions.

[0180] Optionally, the operation and maintenance personnel debug the target base station based on the target fault cause, and if the debugging fails, it is determined that the target fault cause is an error cause.

[0181] Optionally, determining text similarity between the target fault description and the fault description includes:

[0182] Obtain a first word vector of the target fault description and a second word vector of the fault description;

[0183] Based on the target algorithm, calculate the similarity between the first word vector and the second word vector;

[0184] The similarity between the first word vector and the second word vector is determined as the text similarity between the target fault description and the fault description.

[0185] The target algorithm may be, for example, calculating cosine similarity, edit distance, or Euclidean distance.

[0186] Optionally, the target fault description and the fault description may be processed based on the first preset model to obtain a first word vector of the target fault description and a second word vector of the fault description.

[0187] The first preset model may be, for example, word2vec, Glove, or FastText.

[0188] Step 602: Determine the fault description with the greatest text similarity as the intermediate fault description.

[0189] For example, in the case where multiple fault descriptions are A, B, and C, if the text similarity between the target fault description and fault description A is the greatest, fault description A is determined as the intermediate fault description.

[0190] Step 603: Determine a new fault name based on the fault name corresponding to the intermediate fault description in the network fault knowledge graph.

[0191] Optionally, the new fault name may be determined in the following two ways.

[0192] Method 11: determine the fault name corresponding to the intermediate fault description as the new fault name.

[0193] Mode 12, based on the fault name corresponding to the intermediate fault description in the network fault knowledge graph, determines a new fault name, including:

[0194] The associated fault name of the intermediate fault name is determined as the new fault name.

[0195] Optionally, when the network fault knowledge graph includes multiple fault names and multiple associated fault names, the associated fault name of the intermediate fault name in the network fault knowledge graph is determined as the new fault name.

[0196] Step 604: Determine a new fault cause of the target base station being in an abnormal working state in the network fault knowledge graph based on the new fault name.

[0197] Optionally, the execution process of step 604 is similar to the execution process of step 603, and the execution method of step 604 is not repeated here.

[0198] In the present application, when it is determined that the target fault cause is an error cause, the text similarity between the target fault description and the fault description is determined for each fault description in multiple fault descriptions, and the fault description with the largest text similarity is determined as the intermediate fault description. Based on the intermediate fault name corresponding to the intermediate fault description in the network fault knowledge graph, a new fault name is determined, and based on the new fault name, a new fault cause for the target base station to be in an abnormal working state is determined in the network fault knowledge graph, which can further improve the accuracy of fault diagnosis for the base station.

[0199] Figure 7 This is the second flow chart of the method for determining the cause of a target failure provided in the embodiment of the present application. Figure 7 As shown, the method includes:

[0200] Step 701, determine the target fault name.

[0201] For details on how to determine the target fault name, see Figure 4 The embodiments are not described in detail here.

[0202] Step 702: Determine whether the target fault corresponding to the target fault name is a hot fault.

[0203] If yes, execute step 703; otherwise, execute step 704.

[0204] Optionally, based on historical fault information of the target base station, the number of occurrences of the target fault name is determined, and when the number of occurrences of the target fault name is greater than or equal to a preset number, the target fault corresponding to the target fault name is determined to be a hot fault.

[0205] Below, based on Table 3 and in combination with Table 4, the process of determining hot faults is exemplarily described.

[0206] Table 4

[0207]

[0208] As shown in Table 4, the historical fault information includes multiple fault causes, the fault name corresponding to each fault cause, and the occurrence time of each fault cause.

[0209] When the target fault name is "abnormal wireless connection rate" and the preset number of times is 3, statistics are taken on the "abnormal wireless connection rate" at different occurrence times, and the number of occurrences of "abnormal wireless connection rate" is 3. Therefore, the target fault corresponding to "abnormal wireless connection rate" is determined as a hot fault.

[0210] Step 703: When the target fault is a hot fault, for each of the multiple fault causes corresponding to the target fault name in the network fault knowledge graph, the fault cause is processed by a second preset model to obtain a predicted score for the fault cause.

[0211] The second preset model is

[0212] Where u represents the target fault, i represents the fault cause, and P(u,i) represents the predicted score of the target fault u caused by the fault cause i. represents the average score of the target fault u, P u The word vector representing the target fault name, v represents the associated fault of the target fault, and P v The word vector representing the associated fault name of the associated fault v, sim(P u ,P v ) indicates P u and P v The word vector similarity between them, V represents the set of all associated faults of the target fault, r vi represents the score of the fault cause i that causes the associated fault v, represents the average score of the associated fault v, r ui Indicates the second preset score.

[0213] Optionally, the historical fault information of the target base station further includes scores of multiple faults and multiple fault causes causing the faults, and the multiple faults include associated faults v and target faults u; The methods for obtaining include:

[0214] From the historical fault information, obtain the scores of multiple fault causes that lead to the target fault u;

[0215] The average of the scores of multiple fault causes is determined as the average score of the target fault.

[0216] How to obtain The method of obtaining is similar and will not be repeated here.

[0217] r uiIndicates that if the fault cause i of the target fault u is an error cause and the score of the fault cause i that causes the target fault u is the highest, Subtract the second preset score.

[0218] Step 704: When the target fault is a non-hot fault, determine whether the fault cause is a hot cause for each fault cause; when the fault cause is a hot cause, determine the predicted score of the fault cause through the third preset model; when the fault cause is a non-hot cause, determine the first preset score as the predicted score of the fault cause.

[0219] The third preset model is

[0220] Among them, r b Indicates the first preset score.

[0221] Optionally, based on historical fault information of the target base station, statistics are collected on fault causes at different occurrence times to obtain the number of occurrences of the fault cause, and when the number of occurrences of the fault cause is greater than or equal to a second preset number, the fault cause is determined to be a hot cause.

[0222] As shown in Table 3, the occurrence number of "Insufficient unlimited resources" is 2 times. When the second preset number is 2, it is determined that "Insufficient unlimited resources" is a hot reason.

[0223] Step 705: Determine the fault cause with the largest predicted score among the multiple fault causes as the target fault cause.

[0224] For example, if the fault causes include A, B, and C, and the predicted score of A is 90 points, the predicted score of B is 80 points, and the predicted score of C is 85 points, then A is determined as the target fault cause.

[0225] In an embodiment of the present application, it is determined whether the target fault corresponding to the target fault name is a hot fault. When the target fault is a hot fault, a predicted score of the fault cause is obtained based on each fault cause among the multiple fault causes corresponding to the target fault name in the network fault knowledge graph; when the target fault is a non-hot fault, for each fault cause, it is determined whether the fault cause is a hot cause; when the fault cause is a hot cause, the predicted score of the fault cause is determined based on the fault cause, and the fault cause with the largest predicted score among the multiple fault causes is determined as the target fault cause. In the process of obtaining the target fault cause, the characteristics of the target base station itself can be taken into consideration, and the weight of the target base station itself can be introduced into the second preset model and the third preset model, so that the obtained target fault cause is more accurate, thereby further improving the fault diagnosis efficiency of the base station.

[0226] In some embodiments, if the target fault cause is confirmed to be an error by the operation and maintenance personnel, a certain penalty (i.e., r b and r ui ) to ensure that the next network fault diagnosis is more accurate.

[0227] Figure 8 Schematic diagram of the structure of a network fault diagnosis device provided in an embodiment of the present application. Figure 8 As shown, the network fault diagnosis device includes: a memory 820, a transceiver 800 and a processor 810; wherein,

[0228] The memory 820 is used to store computer programs; the transceiver 800 is used to send and receive data under the control of the processor 810; the processor 810 is used to read the computer program in the memory 820 and perform the following operations:

[0229] When the target base station is in an abnormal working state, obtaining a target fault description corresponding to the target base station;

[0230] When it is determined that the target base station is in an abnormal working state, obtaining a target fault description corresponding to the target base station;

[0231] Based on the target fault description, a target fault cause of the target base station being in an abnormal working state is determined in a network fault knowledge graph, wherein the network fault knowledge graph includes a correspondence between multiple fault descriptions and multiple fault causes.

[0232] Specifically, the transceiver 800 is used to receive and send data under the control of the processor 810.

[0233] Among them, Figure 8 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 810 and memory represented by memory 820. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 800 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, which may include a wireless channel, a wired channel, an optical cable, and other transmission media.

[0234] The processor 810 is responsible for managing the bus architecture and general processing, and the memory 820 can store data used by the processor 810 when performing operations.

[0235] The processor 810 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD). The processor may also adopt a multi-core architecture.

[0236] The processor calls the computer program stored in the memory to execute any of the methods provided in the embodiments of the present application according to the obtained executable instructions. The processor and the memory can also be arranged physically separately.

[0237] In an optional embodiment, determining that the target base station is in an abnormal working state includes:

[0238] Obtaining actual operating values ​​of each of a plurality of network indicators of the target base station;

[0239] For each network indicator, determining whether an actual operating value of the network indicator satisfies a fault detection rule corresponding to the network indicator;

[0240] When the fault detection rule is met, it is determined that the target base station is in an abnormal working state.

[0241] In an optional embodiment, the acquiring a target fault description corresponding to the target base station includes:

[0242] Determine the fault description corresponding to the network indicator in a preset mapping relationship; wherein the preset mapping relationship includes a correspondence relationship between multiple network indicators and multiple fault descriptions;

[0243] The fault description corresponding to the network indicator is determined as the target fault description.

[0244] In an optional embodiment, determining the target fault cause of the target base station being in an abnormal working state in a network fault knowledge graph based on the target fault description includes:

[0245] Searching for a fault name corresponding to the target fault description in the network fault knowledge graph;

[0246] In the case where a fault name corresponding to the target fault description is found, the fault name is determined as the target fault name;

[0247] Based on the target fault name, a target fault cause of the target base station being in an abnormal working state is determined in the network fault knowledge graph.

[0248] In an optional embodiment, determining, based on the target fault name, in the network fault knowledge graph, a target fault cause of the target base station being in an abnormal working state includes:

[0249] Acquire multiple fault causes corresponding to the target fault name from the network fault knowledge graph;

[0250] For each of the multiple fault causes, based on historical fault information of the target base station, determine the number of occurrences of the fault cause;

[0251] The fault cause with the largest number of occurrences is determined as the target fault cause.

[0252] In an optional embodiment, determining, based on the target fault name, in the network fault knowledge graph, a target fault cause of the target base station being in an abnormal working state includes:

[0253] Determine whether the target fault corresponding to the target fault name is a hot fault;

[0254] When the target fault is a hot fault, for each of the multiple fault causes corresponding to the target fault name in the network fault knowledge graph, The fault cause is processed to obtain a predicted score of the fault cause; wherein u represents the target fault, i represents the fault cause, and P(u,i) represents the predicted score of the fault cause i. represents the average score of the target fault u, P u represents the word vector of the target fault name, v represents the associated fault of the target fault, P v The word vector representing the associated fault name of the associated fault v, sim(P u ,P v ) indicates P u and P v The word vector similarity between them, V represents the set of all associated faults of the target fault, r vi represents the score of the fault cause i that causes the associated fault v, represents the average score of the associated fault v, r ui A second preset score indicating that the fault cause u leads to the target fault i;

[0255] In the case where the target fault is a non-hot fault, for each fault cause, determine whether the fault cause is a hot cause; in the case where the fault cause is a hot cause, Determine the predicted score of the fault cause; where r b represents a first preset score; when the fault cause is a non-popular cause, the first preset score is determined as the predicted score of the fault cause;

[0256] The fault cause with the largest predicted score among the multiple fault causes is determined as the target fault cause.

[0257] In an optional embodiment, the network fault knowledge graph includes multiple fault descriptions; and the processor is further configured to perform the following operations:

[0258] In the case where the target fault cause is determined to be an error cause, determining, for each fault description in the multiple fault descriptions, a text similarity between the target fault description and the fault description;

[0259] Determine the fault description with the greatest text similarity as the intermediate fault description;

[0260] Determine a new fault name based on the intermediate fault name corresponding to the intermediate fault description in the network fault knowledge graph;

[0261] Based on the new fault name, a new fault cause for the target base station to be in an abnormal working state is determined in the network fault knowledge graph.

[0262] In an optional embodiment, the determining a new fault name based on the intermediate fault name corresponding to the intermediate fault description in the network fault knowledge graph includes:

[0263] The associated fault name of the intermediate fault name is determined as the new fault name.

[0264] It should be noted here that the above-mentioned network fault diagnosis device provided in the embodiment of the present application can implement all the method steps implemented by the method embodiment in which the execution subject is the network fault diagnosis device, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0265] Fig. 9 Schematic diagram of the structure of a network fault diagnosis device provided by an embodiment of the present application. Fig. 9 As shown, the network fault diagnosis device includes:

[0266] An acquisition module 910 is used to acquire a target fault description corresponding to the target base station when it is determined that the target base station is in an abnormal working state;

[0267] The determination module 920 is used to determine the target fault cause of the target base station being in an abnormal working state in the network fault knowledge graph based on the target fault description, wherein the network fault knowledge graph includes a correspondence between multiple fault descriptions and multiple fault causes.

[0268] In an optional embodiment, the acquisition module 910 is specifically used to:

[0269] Obtaining actual operating values ​​of each of a plurality of network indicators of the target base station;

[0270] For each network indicator, determining whether an actual operating value of the network indicator satisfies a fault detection rule corresponding to the network indicator;

[0271] When the fault detection rule is met, it is determined that the target base station is in an abnormal working state.

[0272] In an optional embodiment, the acquisition module 910 is specifically used to:

[0273] Determine the fault description corresponding to the network indicator in a preset mapping relationship; wherein the preset mapping relationship includes a correspondence relationship between multiple network indicators and multiple fault descriptions;

[0274] The fault description corresponding to the network indicator is determined as the target fault description.

[0275] In an optional embodiment, the determining module 920 is specifically configured to:

[0276] Searching for a fault name corresponding to the target fault description in the network fault knowledge graph;

[0277] In the case where a fault name corresponding to the target fault description is found, the fault name is determined as the target fault name;

[0278] Based on the target fault name, a target fault cause of the target base station being in an abnormal working state is determined in the network fault knowledge graph.

[0279] In an optional embodiment, the determining module 920 is specifically configured to:

[0280] Acquire multiple fault causes corresponding to the target fault name from the network fault knowledge graph;

[0281] For each of the multiple fault causes, based on historical fault information of the target base station, determine the number of occurrences of the fault cause;

[0282] The fault cause with the largest number of occurrences is determined as the target fault cause.

[0283] In an optional embodiment, the determining module 920 is specifically configured to:

[0284] Determine whether the target fault corresponding to the target fault name is a hot fault;

[0285] When the target fault is a hot fault, for each of the multiple fault causes corresponding to the target fault name in the network fault knowledge graph, The fault cause is processed to obtain a predicted score of the fault cause; wherein u represents the target fault, i represents the fault cause, and P(u,i) represents the predicted score of the fault cause i. represents the average score of the target fault u, P u represents the word vector of the target fault name, v represents the associated fault of the target fault, P v The word vector representing the associated fault name of the associated fault v, sim(P u ,P v ) indicates P u and P v The word vector similarity between them, V represents the set of all associated faults of the target fault, r vi represents the score of the fault cause i that causes the associated fault v, represents the average score of the associated fault v, r ui A second preset score indicating that the fault cause u leads to the target fault i;

[0286] In the case where the target fault is a non-hot fault, for each fault cause, determine whether the fault cause is a hot cause; in the case where the fault cause is a hot cause, Determine the predicted score of the fault cause; where r b represents a first preset score; when the fault cause is a non-popular cause, the first preset score is determined as the predicted score of the fault cause;

[0287] The fault cause with the largest predicted score among the multiple fault causes is determined as the target fault cause.

[0288] In an optional embodiment, the network fault knowledge graph includes multiple fault descriptions; the determination module 920 is further used to:

[0289] In the case where the target fault cause is determined to be an error cause, determining, for each fault description in the multiple fault descriptions, a text similarity between the target fault description and the fault description;

[0290] Determine the fault description with the greatest text similarity as the intermediate fault description;

[0291] Determine a new fault name based on the intermediate fault name corresponding to the intermediate fault description in the network fault knowledge graph;

[0292] Based on the new fault name, a new fault cause for the target base station to be in an abnormal working state is determined in the network fault knowledge graph.

[0293] In an optional embodiment, the determination module 920 is further specifically configured to: determine the associated fault name of the intermediate fault name as the new fault name.

[0294] It should be noted that the division of units in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present application may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0295] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0296] It should be noted here that the above-mentioned device provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0297] On the other hand, an embodiment of the present application further provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the network fault diagnosis method provided in the above embodiments.

[0298] The processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0299] As can be seen from the above embodiments, the processor-readable storage medium stores a computer program, and the computer program is used to cause the processor to execute the above network fault diagnosis method. Therefore, the embodiment of the present application solves the problem that the operation and maintenance personnel locate the cause of the network fault based on the KPI and the log information of the base station, resulting in low efficiency in fault diagnosis of the base station, and improves the efficiency of fault diagnosis of the base station.

[0300] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0301] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer executable instructions. These computer executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0302] These processor executable instructions may also be stored in a processor readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0303] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0304] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A network fault diagnosis method, characterized in that: include: When it is determined that the target base station is in an abnormal working state, obtaining a target fault description corresponding to the target base station; Based on the target fault description, a target fault cause of the target base station being in an abnormal working state is determined in a network fault knowledge graph, wherein the network fault knowledge graph includes a correspondence between multiple fault descriptions and multiple fault causes.

2. The network fault diagnosis method according to claim 1, characterized in that: The determining that the target base station is in an abnormal working state includes: Obtaining actual operating values ​​of multiple network indicators of the target base station; For each network indicator, determining whether the actual operating value of the network indicator satisfies the fault detection rule corresponding to the network indicator; When the fault detection rule is met, it is determined that the target base station is in an abnormal working state.

3. The network fault diagnosis method according to claim 1 or 2, characterized in that: The obtaining a target fault description corresponding to the target base station includes: Determining the fault description corresponding to the network indicator in a preset mapping relationship; wherein the preset mapping relationship includes a correspondence between multiple network indicators and multiple fault descriptions; The fault description corresponding to the network indicator is determined as the target fault description.

4. The network fault diagnosis method according to any one of claims 1 to 3, characterized in that: The determining, based on the target fault description, in the network fault knowledge graph, a target fault cause of the target base station being in an abnormal working state includes: Searching for a fault name corresponding to the target fault description in the network fault knowledge graph; When a fault name corresponding to the target fault description is found, determining the fault name as the target fault name; Based on the target fault name, a target fault cause of the target base station being in an abnormal working state is determined in the network fault knowledge graph.

5. The network fault diagnosis method according to claim 4, characterized in that: The determining, based on the target fault name, in the network fault knowledge graph, a target fault cause of the target base station being in an abnormal working state includes: Acquire multiple fault causes corresponding to the target fault name from the network fault knowledge graph; For each of the multiple fault causes, determining a number of occurrences of the fault cause based on historical fault information of the target base station; The fault cause with the largest number of occurrences is determined as the target fault cause.

6. The network fault diagnosis method according to claim 4, characterized in that: The determining, based on the target fault name, in the network fault knowledge graph, a target fault cause of the target base station being in an abnormal working state includes: Determine whether the target fault corresponding to the target fault name is a hot fault; In the case where the target fault is a hot fault, for each of the multiple fault causes corresponding to the target fault name in the network fault knowledge graph, Process the fault cause to obtain a predicted score for the fault cause; where u represents the target fault, i represents the fault cause, and P(u,i) represents the predicted score for the fault cause i. represents the average score of the target fault u, P u The word vector representing the target fault name, v represents the associated fault of the target fault, P v The word vector representing the associated fault name of the associated fault v, sim(P u ,P v ) indicates P u and P v The word vector similarity between them, V represents the set of all associated faults of the target fault, r vi represents the score of the fault cause i that causes the associated fault v, represents the average score of the associated fault v, r ui Indicates the second preset score; In the case that the target fault is a non-hot fault, for each fault cause, determine whether the fault cause is a hot cause; in the case that the fault cause is a hot cause, Determine the predicted score of the fault cause; where r b Indicates a first preset score; if the fault cause is a non-popular cause, the first preset score is determined as the predicted score of the fault cause; The fault cause with the highest predicted score among the multiple fault causes is determined as the target fault cause.

7. The network fault diagnosis method according to any one of claims 1 to 3, characterized in that: The network fault knowledge graph includes multiple fault descriptions; the method further includes: When it is determined that the target fault cause is an error cause, determining, for each fault description in the multiple fault descriptions, a text similarity between the target fault description and the fault description; Determine the fault description with the greatest text similarity as the intermediate fault description; Determine a new fault name based on the intermediate fault name corresponding to the intermediate fault description in the network fault knowledge graph; Based on the new fault name, a new fault cause of the target base station being in an abnormal working state is determined in the network fault knowledge graph.

8. The network fault diagnosis method according to claim 7, characterized in that: The determining of a new fault name based on the intermediate fault name corresponding to the intermediate fault description in the network fault knowledge graph includes: The associated fault name of the intermediate fault name is determined as the new fault name.

9. A network fault diagnosis device, characterized in that: include: memory, transceivers, and processors; The memory is used to store computer programs; The transceiver is used to send and receive data under the control of the processor; The processor is configured to read the computer program in the memory and perform the following operations: When it is determined that the target base station is in an abnormal working state, obtaining a target fault description corresponding to the target base station; Based on the target fault description, a target fault cause of the target base station being in an abnormal working state is determined in a network fault knowledge graph, wherein the network fault knowledge graph includes a correspondence between multiple fault descriptions and multiple fault causes.

10. The network fault diagnosis device according to claim 9, characterized in that: The determining that the target base station is in an abnormal working state includes: Obtaining actual operating values ​​of multiple network indicators of the target base station; For each network indicator, determining whether the actual operating value of the network indicator satisfies the fault detection rule corresponding to the network indicator; When the fault detection rule is met, it is determined that the target base station is in an abnormal working state.

11. The network fault diagnosis device according to claim 9 or 10, characterized in that: The obtaining a target fault description corresponding to the target base station includes: Determining the fault description corresponding to the network indicator in a preset mapping relationship; wherein the preset mapping relationship includes a correspondence between multiple network indicators and multiple fault descriptions; The fault description corresponding to the network indicator is determined as the target fault description.

12. The network fault diagnosis device according to any one of claims 9 to 11, characterized in that: The determining, based on the target fault description, in the network fault knowledge graph, a target fault cause of the target base station being in an abnormal working state includes: Searching for a fault name corresponding to the target fault description in the network fault knowledge graph; When a fault name corresponding to the target fault description is found, determining the fault name as the target fault name; Based on the target fault name, a target fault cause of the target base station being in an abnormal working state is determined in the network fault knowledge graph.

13. The network fault diagnosis device according to claim 12, characterized in that: The determining, based on the target fault name, in the network fault knowledge graph, a target fault cause of the target base station being in an abnormal working state includes: Acquire multiple fault causes corresponding to the target fault name from the network fault knowledge graph; For each of the multiple fault causes, determining a number of occurrences of the fault cause based on historical fault information of the target base station; The fault cause with the largest number of occurrences is determined as the target fault cause.

14. The network fault diagnosis device according to claim 12, characterized in that: The determining, based on the target fault name, in the network fault knowledge graph, a target fault cause of the target base station being in an abnormal working state includes: Determine whether the target fault corresponding to the target fault name is a hot fault; In the case where the target fault is a hot fault, for each of the multiple fault causes corresponding to the target fault name in the network fault knowledge graph, Process the fault cause to obtain a predicted score for the fault cause; where u represents the target fault, i represents the fault cause, and P(u,i) represents the predicted score for the fault cause i. represents the average score of the target fault u, P u The word vector representing the target fault name, v represents the associated fault of the target fault, P v The word vector representing the associated fault name of the associated fault v, sim(P u ,P v ) indicates P u and P v The word vector similarity between them, V represents the set of all associated faults of the target fault, r vi represents the score of the fault cause i that causes the associated fault v, represents the average score of the associated fault v, r ui A second preset score indicating that the fault cause u causes the target fault i; In the case that the target fault is a non-hot fault, for each fault cause, determine whether the fault cause is a hot cause; in the case that the fault cause is a hot cause, Determine the predicted score of the fault cause; where r b Indicates a first preset score; if the fault cause is a non-popular cause, the first preset score is determined as the predicted score of the fault cause; The fault cause with the highest predicted score among the multiple fault causes is determined as the target fault cause.

15. The network fault diagnosis device according to any one of claims 9 to 11, characterized in that: The network fault knowledge graph includes multiple fault descriptions; the processor is further configured to perform the following operations: When it is determined that the target fault cause is an error cause, determining, for each fault description in the multiple fault descriptions, a text similarity between the target fault description and the fault description; Determine the fault description with the greatest text similarity as the intermediate fault description; Determine a new fault name based on the intermediate fault name corresponding to the intermediate fault description in the network fault knowledge graph; Based on the new fault name, a new fault cause of the target base station being in an abnormal working state is determined in the network fault knowledge graph.

16. The network fault diagnosis device according to claim 15, characterized in that: The determining of a new fault name based on the intermediate fault name corresponding to the intermediate fault description in the network fault knowledge graph includes: The associated fault name of the intermediate fault name is determined as the new fault name.

17. A network fault diagnosis device, characterized in that: include: an acquisition module, configured to acquire a target fault description corresponding to the target base station when it is determined that the target base station is in an abnormal working state; A determination module is used to determine a target fault cause of the target base station being in an abnormal working state in a network fault knowledge graph based on the target fault description, wherein the network fault knowledge graph includes a correspondence between multiple fault descriptions and multiple fault causes.

18. A processor-readable storage medium, characterized in that: The processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the network fault diagnosis method according to any one of claims 1 to 8.

Images