Fault diagnosis method and device, equipment and storage medium
By obtaining real-time technical and business indicators in the outgoing call system and entering a fault diagnosis model, the limitations of fault diagnosis in the existing technology are solved, and accurate fault diagnosis and real-time status monitoring of various platforms of the outgoing call system are realized.
Patent Information
- Application Number
- CN202411901301.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-23
- Publication Date
- 2025-04-18
AI Technical Summary
The prior art is difficult to effectively utilize multiple indicators in the fault diagnosis of outbound call systems, making it difficult to capture deep-level faults and has high limitations in fault diagnosis.
By obtaining real-time technical indicators and real-time business indicators of the outgoing call system and inputting them into pre-trained fault diagnosis models, we can determine the fault diagnosis results of the voice processing platform, natural language processing platform and outgoing call scheduling platform.
It realizes accurate fault diagnosis of the outbound call system, can monitor the fault status of each platform in real time, and improves the accuracy and comprehensiveness of fault diagnosis.
Smart Images
Figure CN119854408A_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present invention relate to the field of artificial intelligence technology, and in particular, to a fault diagnosis method, apparatus, device and storage medium. Background Art
[0002] During the operation of the outbound call system, failures may occur due to various reasons, such as server downtime, database connection abnormality, business overload, etc. The outbound call system is a large distributed system including multiple platforms, with many nodes and complex upstream and downstream links. Timely detection of outbound call system failures is crucial to ensure the normal operation of the outbound call system.
[0003] In the prior art, thresholds are usually set manually for key performance indicators of the outbound call system, and these key performance indicators are monitored. When the performance indicator value exceeds the corresponding threshold, a failure of the outbound call system can be determined. The key performance indicators may include response time, number of concurrent users, container central processing unit, network throughput, etc.
[0004] However, monitoring a single indicator to determine whether an outbound call system has a fault cannot effectively utilize multiple indicators at the same time, making it difficult to capture deep-seated faults in the system, resulting in high limitations in fault diagnosis. Summary of the invention
[0005] The present invention provides a fault diagnosis method, device, equipment and storage medium, which can realize accurate fault diagnosis of an outbound call system according to indicator data of the outbound call system.
[0006] In a first aspect, an embodiment of the present invention provides a fault diagnosis method, comprising:
[0007] Acquire real-time technical indicators and real-time business indicators of an outbound call system, wherein the outbound call system includes a voice processing platform, a natural language processing platform, and an outbound call dispatching platform;
[0008] The real-time technical indicators and the real-time business indicators are input into a pre-trained fault diagnosis model so that the fault diagnosis model determines the fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call scheduling platform according to the real-time technical indicators and the real-time business indicators.
[0009] The technical solution of the embodiment of the present invention provides a fault diagnosis method, including: obtaining real-time technical indicators and real-time business indicators of an outbound call system, wherein the outbound call system includes a voice processing platform, a natural language processing platform and an outbound call dispatching platform; inputting the real-time technical indicators and the real-time business indicators into a pre-trained fault diagnosis model, so that the fault diagnosis model determines the fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call dispatching platform according to the real-time technical indicators and the real-time business indicators. In the above technical solution, the real-time technical indicators of the outbound call system are obtained in the memory of the server where the outbound call system is located, the real-time business indicators of the outbound call system are obtained in the high-efficiency lake table of the outbound call system, and the real-time technical indicators and the real-time business indicators of the outbound call system are input into the pre-trained fault diagnosis model. The fault diagnosis model can determine the real-time fault diagnosis results of the voice processing platform, the language processing platform and the dispatching platform in the outbound call system according to the real-time technical indicators and the real-time business indicators of the outbound call system, so as to realize the real-time fault diagnosis of the voice processing platform, the language processing platform and the dispatching platform in the outbound call system. The above technical solution obtains the real-time technical indicators of the outbound call system in the memory of the server where the outbound call system is located, obtains the real-time business indicators of the outbound call system in the high-efficiency lake table of the outbound call system, and inputs the real-time technical indicators and real-time business indicators of the outbound call system into a pre-trained fault diagnosis model. The fault diagnosis model can determine the real-time fault diagnosis results of the voice processing platform, language processing platform and scheduling platform in the outbound call system according to the real-time technical indicators and real-time business indicators of the outbound call system, realize real-time fault diagnosis of the voice processing platform, language processing platform and scheduling platform in the outbound call system, and then realize accurate fault diagnosis of the outbound call system.
[0010] Furthermore, the real-time technical indicators include at least CPU usage, memory occupancy, disk read and write speed, and network transmission speed; the real-time business indicators include at least outbound call volume, connection volume, connection rate, scenario type, average call duration, high intention rate, natural language processing rejection number, complaint rate, interactive backup trigger number, interactive backup trigger rate, call silence number, call silence rate, interactive failure rate, outbound call result pushback number, and outbound call result pushback rate; the fault diagnosis result is a normal diagnosis or an abnormal diagnosis. When the fault diagnosis result is an abnormal diagnosis, the fault diagnosis result also includes an abnormality type, which is a scenario abnormality, an interactive abnormality, a bot abnormality, or a pushback abnormality.
[0011] Furthermore, real-time business indicators of the outbound call system are obtained, including:
[0012] Acquire real-time business data of the outbound call system based on the outbound call record table, call details table and call intention table of the outbound call system;
[0013] The real-time business indicators of the outbound call system are determined by extracting features and processing the real-time business data.
[0014] Furthermore, the training process of the fault diagnosis model includes:
[0015] Obtaining historical technical indicators, historical business indicators of the outbound call system, and historical fault diagnosis results of the voice processing platform, the natural language processing platform, and the outbound call dispatching platform in the outbound call system;
[0016] The historical technical indicators, the historical business indicators, and the historical fault diagnosis results of the voice processing platform, the natural language processing platform, and the outbound call dispatching platform in the outbound call system are used as training sets to fit a decision tree model to obtain the fault diagnosis model.
[0017] Furthermore, after determining the fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call dispatching platform, it also includes:
[0018] If the fault diagnosis result of at least one of the voice processing platform, the natural language processing platform and the outbound call dispatching platform is a diagnosis abnormality, the real-time technical indicators, the real-time business indicators, the platform whose fault diagnosis result is a diagnosis abnormality and its abnormality type, and a pre-set prompt word are input into the big model, so that the big model determines the fault cause and solution of the platform whose fault diagnosis result is a diagnosis abnormality based on the prompt word.
[0019] Further, after determining that the fault diagnosis result is the fault cause and solution of the platform with abnormal diagnosis, it also includes:
[0020] The fault diagnosis result is that the fault cause and solution of the platform with the diagnosis abnormality are sent to the operation and maintenance terminal corresponding to the operation and maintenance personnel.
[0021] In a second aspect, an embodiment of the present invention further provides a fault diagnosis device, comprising:
[0022] An acquisition module, used to acquire real-time technical indicators and real-time business indicators of an outbound call system, wherein the outbound call system includes a voice processing platform, a natural language processing platform, and an outbound call dispatching platform;
[0023] The diagnostic module is used to input the real-time technical indicators and the real-time business indicators into a pre-trained fault diagnosis model so that the fault diagnosis model determines the fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call scheduling platform according to the real-time technical indicators and the real-time business indicators.
[0024] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:
[0025] at least one processor; and a memory communicatively coupled to the at least one processor;
[0026] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the fault diagnosis method as described in any one of the first aspects.
[0027] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, are used to perform the fault diagnosis method as described in any one of the first inventions.
[0028] In a fifth aspect, the present application provides a computer program product, which includes computer instructions. When the computer instructions are executed on a computer, the computer executes the fault diagnosis method provided in the first aspect.
[0029] It should be noted that the above computer instructions may be stored in whole or in part on a computer-readable storage medium, wherein the computer-readable storage medium may be packaged together with the processor of the fault diagnosis device, or may be packaged separately from the processor of the fault diagnosis device, which is not limited in this application.
[0030] The description of the second, third, fourth and fifth aspects in this application can refer to the detailed description of the first aspect; and the beneficial effects of the description of the second, third, fourth and fifth aspects can refer to the beneficial effect analysis of the first aspect, which will not be repeated here.
[0031] In this application, the name of the above-mentioned fault diagnosis device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear with other names. As long as the functions of each device or functional module are similar to those of this application, they fall within the scope of the claims of this application and their equivalent technologies.
[0032] These and other aspects of the present application will become more apparent from the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0034] Figure 1 A flowchart of a fault diagnosis method provided by an embodiment of the present invention;
[0035] Figure 2 A flowchart of another fault diagnosis method provided by an embodiment of the present invention;
[0036] Figure 3 A schematic diagram of the structure of a fault diagnosis device provided by an embodiment of the present invention;
[0037] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0038] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.
[0039] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.
[0040] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.
[0041] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.
[0042] It should be mentioned before discussing exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe various operations (or steps) as sequential processes, many operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of various operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to methods, functions, procedures, subroutines, subprograms, etc. In addition, the embodiments in the present invention and the features in the embodiments can be combined with each other without conflict.
[0043] It should be noted that, 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 specific way.
[0044] In the description of the present application, unless otherwise specified, “plurality” means two or more.
[0045] There is a mutual calling relationship between the platforms of the outbound call system, but the traditional fault diagnosis method only focuses on whether the platform itself is normal, and it is difficult to perceive the abnormalities of other platforms. For example, the natural language processing platform normally completes semantic understanding and provides interactive content with customers, but due to a failure of the intelligent voice processing station, the actual speech is not read to the customer. The outbound call dispatching platform is difficult to perceive the failure of the intelligent voice processing station because the calling link is normal. Therefore, it is impossible to complete product marketing to customers, affecting the efficiency of outbound calls.
[0046] Therefore, the present application proposes a fault diagnosis method to achieve accurate fault diagnosis of each platform in the outbound call system.
[0047] The fault diagnosis method proposed in the present application will be described in detail below with reference to the diagrams and embodiments.
[0048] Figure 1 A flowchart of a fault diagnosis method provided by an embodiment of the present invention is provided. This embodiment is applicable to situations where timely and effective fault diagnosis of an outbound call system is required. The method can be executed by a fault diagnosis device, such as Figure 1 As shown, the specific steps include:
[0049] Step 110: Obtain real-time technical indicators and real-time business indicators of the outbound call system.
[0050] Among them, the outbound call system includes a voice processing platform, a natural language processing platform and an outbound call dispatching platform. The voice processing platform has the functions of telephone voice, outbound calls and recording for contacting users. The natural language processing platform has the functions of speech recognition, speech synthesis and speech analysis. The outbound call dispatching platform has the function of outbound call task dispatching, which is mainly responsible for the start and stop, issuance, voice interaction and settlement of outbound call tasks.
[0051] Technical indicators can be understood as indicator information of the environment in which the outbound call system is located, such as CPU utilization, memory usage, disk read and write speed, and network transmission speed. Business indicators can be understood as indicator information generated by the outbound call system processing outbound call business, such as outbound call volume, connection volume, connection rate, scenario type, average call duration, high intention rate, etc.
[0052] Specifically, the technical indicators of the outbound call system can be obtained based on the storage module of the server equipped with the outbound call system, and then the real-time technical indicators of the outbound call system can be determined according to the current time, for example, the real-time CPU usage rate, real-time memory occupancy, real-time disk read and write speed, and real-time network transmission speed of the outbound call system can be determined. The business records of the outbound call system are stored in the high-efficiency lake table, which includes the outbound call record table, call detail table, and call intention table. Therefore, the business records of the outbound call system can be obtained based on the high-efficiency lake table, and then the real-time business indicators of the outbound call system can be determined according to the current time.
[0053] Real-time business indicators may include real-time outbound call volume, real-time connection volume, real-time connection rate, real-time average call duration, real-time high intention rate, etc. Therefore, the real-time outbound call volume can be determined in the outbound call record table, the real-time connection volume, the total number of real-time calls and the call duration of each connected call can be determined in the call details table, the real-time connection rate can be determined based on the real-time connection volume and the total number of real-time calls, the real-time average call duration can be determined based on the call duration of each connected call and the real-time connection volume, the call intention of each connected call can be determined in the call intention table, and the real-time high intention rate can be determined based on the number of high-intention calls and the total number of real-time calls.
[0054] In an embodiment of the present invention, real-time technical indicators of the outbound call system are obtained in the memory of the server where the outbound call system is located, and real-time business indicators of the outbound call system are obtained in a high-efficiency lake table of the outbound call system, thereby realizing real-time acquisition of real-time technical indicators and real-time business indicators of the outbound call system.
[0055] Step 120: input the real-time technical indicators and the real-time business indicators into a pre-trained fault diagnosis model, so that the fault diagnosis model determines the fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call scheduling platform according to the real-time technical indicators and the real-time business indicators.
[0056] Among them, the fault diagnosis model is obtained by training a decision tree model, which can be used to determine the fault diagnosis results of each platform in the outbound call system according to the real-time technical indicators and real-time business indicators of the outbound call system. The fault diagnosis result is a normal diagnosis or an abnormal diagnosis. When the fault diagnosis result is an abnormal diagnosis, the fault diagnosis result also includes an abnormality type, which is a scene abnormality, an interaction abnormality, a bot abnormality, or a pushback abnormality.
[0057] Specifically, the real-time technical indicators and real-time business indicators of the outbound call system are input into the fault diagnosis model. The fault diagnosis model can analyze the operation status of each platform in the outbound call system and the calling relationship between each platform through the real-time technical indicators and real-time business indicators of the outbound call system to determine the fault diagnosis results of each platform.
[0058] In an embodiment of the present invention, by inputting the real-time technical indicators and real-time business indicators of the outbound call system into a pre-trained fault diagnosis model, the fault diagnosis model can determine the real-time fault diagnosis results of the voice processing platform, language processing platform and scheduling platform in the outbound call system according to the real-time technical indicators and real-time business indicators of the outbound call system, thereby realizing real-time fault diagnosis of the voice processing platform, language processing platform and scheduling platform in the outbound call system.
[0059] The fault diagnosis method provided by the embodiment of the present invention includes: obtaining real-time technical indicators and real-time business indicators of an outbound call system, wherein the outbound call system includes a voice processing platform, a natural language processing platform and an outbound call dispatching platform; inputting the real-time technical indicators and the real-time business indicators into a pre-trained fault diagnosis model, so that the fault diagnosis model determines the fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call dispatching platform according to the real-time technical indicators and the real-time business indicators. In the above technical scheme, the real-time technical indicators of the outbound call system are obtained in the memory of the server where the outbound call system is located, the real-time business indicators of the outbound call system are obtained in the high-efficiency lake table of the outbound call system, and the real-time technical indicators and the real-time business indicators of the outbound call system are input into the pre-trained fault diagnosis model. The fault diagnosis model can determine the real-time fault diagnosis results of the voice processing platform, the language processing platform and the dispatching platform in the outbound call system according to the real-time technical indicators and the real-time business indicators of the outbound call system, so as to realize the real-time fault diagnosis of the voice processing platform, the language processing platform and the dispatching platform in the outbound call system, and then realize the accurate fault diagnosis of the outbound call system.
[0060] Figure 2 This is a flow chart of another fault diagnosis method provided by an embodiment of the present invention. This embodiment is specific based on the above embodiment. Figure 2 As shown, in this embodiment, the method may further include:
[0061] Step 210: Obtain historical technical indicators, historical business indicators of the outbound call system, and historical fault diagnosis results of the voice processing platform, the natural language processing platform, and the outbound call dispatching platform in the outbound call system.
[0062] Specifically, historical technical indicators, historical business indicators, and historical fault diagnosis results of the voice processing platform, natural language processing platform, and outbound call dispatching platform of the outbound call system can be obtained within the historical time period. Specifically, the historical technical indicators of the outbound call system can be obtained from the storage module of the server equipped with the outbound call system according to the historical time period, that is, the historical CPU usage rate, historical memory occupancy, historical disk read and write speed, and historical network transmission speed of the outbound call system can be obtained.
[0063] The business indicators include outbound call volume, connection volume, connection rate, average call duration, high intention rate, natural language processing rejection number, complaint rate, interactive bottom-up trigger number, interactive bottom-up trigger rate, call silence number, call silence rate, interactive failure rate, outbound call result pushback number and outbound call result pushback rate. The outbound call volume, connection volume, connection rate, average call duration and high intention rate can be determined by referring to the determination method of the above-mentioned embodiment, that is, the outbound call volume in the historical time period can be determined in the outbound call record table according to the historical time period, the connection volume, the total number of calls and the call duration of each connected call in the historical time period can be determined in the call details table according to the historical time period, the connection rate can be determined according to the connection volume and the total number of calls, the average call duration can be determined according to the call duration of each connected call and the connection volume, the call intention of each connected call in the historical time period can be determined in the call intention table according to the historical time period, and the high intention rate can be determined according to the number of high-intention calls and the total number of calls.
[0064] The high-efficiency lake table also includes a natural language processing platform identification table, an interactive backup record table, and a complaint record table. Therefore, the number of natural language processing rejections in the historical time period can be determined in the natural language processing platform identification table according to the historical time period. The number of complaints in the historical time period can also be determined in the complaint record table according to the historical time period, and the complaint rate can be determined based on the total number of calls and the number of complaints in the historical time period. The number of silent calls in the historical time period can also be determined in the call details table according to the historical time period, and the silent call rate can be determined based on the number of silent calls and the total number of calls. The number of interactive backup triggers and the number of interactive failures in the historical time period can also be determined in the interactive backup record table according to the historical time period, and the interactive backup trigger rate can be determined based on the number of interactive backup triggers and the total number of calls, and the interactive failure rate can be determined based on the number of interactive failures and the number of interactive backup triggers. The number of outbound call result pushbacks in the historical time period can also be determined in the outbound call record table according to the historical time period, and the outbound call result pushback rate can be determined based on the number of outbound call result pushbacks and the total number of outbound calls.
[0065] In addition, the high-efficiency lake table also includes fault record tables for the voice processing platform, natural language processing platform, and outbound call dispatching platform. Therefore, the historical fault diagnosis results of the voice processing platform, natural language processing platform, and outbound call dispatching platform in the outbound call system within the historical time period can also be obtained in the high-efficiency lake table according to the historical time period.
[0066] In the embodiment of the present invention, it is possible to obtain historical technical indicators and historical business indicators of the outbound call system in a historical period of time and historical fault diagnosis results of the voice processing platform, natural language processing platform and outbound call dispatching platform in the outbound call system.
[0067] Step 220: Use the historical technical indicators, the historical business indicators, and the historical fault diagnosis results of the voice processing platform, the natural language processing platform, and the outbound call dispatching platform in the outbound call system as training sets to fit a decision tree model to obtain the fault diagnosis model.
[0068] Among them, the decision tree model can be a LightGBM model.
[0069] Specifically, first, a training set and a test set can be constructed based on the historical technical indicators, historical business indicators, and historical fault diagnosis results of the voice processing platform, natural language processing platform, and outbound dispatching platform of the outbound call system. Specifically, a training set can be constructed based on 70% of the data in the historical technical indicators, historical business indicators, and historical fault diagnosis results of the voice processing platform, the natural language processing platform, and the outbound dispatching platform of the outbound call system, and a test set can be constructed based on the remaining data. Secondly, the business characteristics can be determined based on the historical technical indicators and historical business indicators of the outbound call system, and then the target features corresponding to each node in the LightGBM model are determined in turn based on the business characteristics and the historical fault diagnosis results of the voice processing platform, natural language processing platform, and outbound dispatching platform in the outbound call system. The initial diagnosis model is constructed based on the target features corresponding to each node in the LightGBM model and the feature thresholds corresponding to the target features.
[0070] Of course, the initial diagnostic model can also be verified on the test set. Specifically, the diagnostic accuracy of the initial diagnostic model can be determined. When the diagnostic accuracy is determined to be greater than the accuracy threshold, it is determined that the initial diagnostic model is fitted successfully, and then the initial diagnostic model can be determined as a fault diagnosis model. Otherwise, the training set can continue to be obtained for model training until the diagnostic accuracy is greater than the accuracy threshold to obtain a fault diagnosis model.
[0071] In an embodiment of the present invention, a decision tree model is fitted using a training set consisting of historical technical indicators, historical business indicators, and historical fault diagnosis results of a voice processing platform, a natural language processing platform, and an outbound call scheduling platform in an outbound call system to obtain a fault diagnosis model that can be used to diagnose faults in an outbound call system.
[0072] Step 230: Obtain real-time technical indicators and real-time business indicators of the outbound call system.
[0073] In one implementation, step 230 may specifically include:
[0074] The real-time business data of the outbound call system is obtained based on the outbound call record table, call detail table and call intention table of the outbound call system; the real-time business indicators of the outbound call system are determined by extracting features and processing the real-time business data.
[0075] Specifically, for the outbound call volume, connection volume, connection rate, average call duration, and high intention rate, the real-time business data of the outbound call system can be first obtained based on the outbound call record table, call details table, and call intention table of the outbound call system, that is, the real-time outbound call volume, real-time connection volume, total number of real-time calls, call duration of each connected call, and call intention of each connected call can be obtained. By performing feature extraction and data processing on the real-time business data, the real-time business indicators of the outbound call system can be determined, that is, the real-time outbound call volume can be determined in the outbound call record table, the real-time connection volume, the total number of real-time calls, and the call duration of each connected call can be determined in the call details table, the real-time connection rate can be determined based on the real-time connection volume and the total number of real-time calls, the real-time average call duration can be determined based on the call duration of each connected call and the real-time connection volume, the call intention of each connected call can be determined in the call intention table, and the real-time high intention rate can be determined based on the number of high-intention calls and the total number of real-time calls.
[0076] The number of natural language processing rejections, complaint rate, number of interactive bottom-line triggers, interactive bottom-line trigger rate, number of silent calls, silent call rate, interactive failure rate, number of outbound call result pushbacks, and outbound call result pushback rate can be determined based on the aforementioned steps, that is, the number of real-time natural language processing rejections can be determined in the natural language processing platform recognition table, the real-time complaint volume can be determined in the complaint record table, and the real-time complaint rate can be determined based on the total number of real-time calls and the real-time complaint volume. The number of real-time silent calls can be determined in the call details table, and the real-time call silent rate can be determined based on the number of real-time silent calls and the total number of real-time calls. The number of real-time interactive bottom-line triggers and the number of real-time interactive failures can be determined in the interactive bottom-line record table, and the real-time interactive bottom-line trigger rate can be determined based on the number of real-time interactive bottom-line triggers and the total number of real-time calls. The real-time interactive failure rate can be determined based on the number of real-time interactive failures and the number of real-time interactive bottom-line triggers. The number of real-time outbound call result pushbacks can be determined in the outbound call record table, and the real-time outbound call result pushback rate can be determined based on the number of real-time outbound call pushbacks and the total number of real-time outbound calls.
[0077] In the embodiment of the present invention, real-time acquisition of real-time technical indicators and real-time business indicators of an outbound call system is achieved.
[0078] Step 240: input the real-time technical indicators and the real-time business indicators into a pre-trained fault diagnosis model, so that the fault diagnosis model determines the fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call scheduling platform according to the real-time technical indicators and the real-time business indicators.
[0079] As mentioned above, the real-time technical indicators and real-time business indicators of the outbound call system are input into the fault diagnosis model. The fault diagnosis model can analyze the operation status of the server where the outbound call system is located, the operation status of each platform in the outbound call system, and the call relationship between each platform through the real-time technical indicators and real-time business indicators of the outbound call system, and determine the fault diagnosis results of each platform. The fault diagnosis model determines the real-time fault diagnosis results of each platform in the outbound call system by deeply analyzing the operation status of each platform and the call relationship between each platform, and realizes real-time status monitoring of each platform in the outbound call system.
[0080] In an embodiment of the present invention, by inputting the real-time technical indicators and real-time business indicators of the outbound call system into a pre-trained fault diagnosis model, the fault diagnosis model can determine the real-time fault diagnosis results of the voice processing platform, language processing platform and scheduling platform in the outbound call system according to the real-time technical indicators and real-time business indicators of the outbound call system, thereby realizing real-time fault diagnosis of the voice processing platform, language processing platform and scheduling platform in the outbound call system, and further realizing real-time status monitoring of each platform in the outbound call system.
[0081] Step 250: If the fault diagnosis result of at least one of the voice processing platform, the natural language processing platform and the outbound call dispatching platform is a diagnosis abnormality, the real-time technical indicators, the real-time business indicators, the platform whose fault diagnosis result is a diagnosis abnormality and its abnormality type, and a pre-set prompt word are input into the big model, so that the big model determines the fault cause and solution of the platform whose fault diagnosis result is a diagnosis abnormality based on the prompt word.
[0082] Among them, the prompt words can be: the real-time technical indicators of the outbound call system are XX, the real-time business indicators are XX, the fault diagnosis result of the XX platform (at least one of the voice processing platform, natural language processing platform and outbound call scheduling platform) in the outbound call system is a diagnostic exception, and the exception type is XX (scene exception, interaction exception, bot exception or pushback exception), analyze the fault cause and solution of the XX platform's XX exception type fault.
[0083] Specifically, after determining that the fault diagnosis result of at least one of the voice processing platform, the natural language processing platform and the outbound call scheduling platform is a diagnostic abnormality, the input information can be determined based on the pre-set prompt words and the real-time technical indicators, real-time business indicators, the platform whose fault diagnosis result is a diagnostic abnormality and its abnormality type of the outbound call system, and the input information is input into the big model. The big model can output the fault cause and solution of the platform whose fault diagnosis result is a diagnostic abnormality.
[0084] In the embodiment of the present invention, prompt words are pre-set for the large model, so that the large model can quickly determine the cause of the fault and the solution of the platform with the diagnosis abnormality.
[0085] Step 260: Send the fault diagnosis result of the platform with abnormal diagnosis as the cause of the fault and the solution to the operation and maintenance terminal corresponding to the operation and maintenance personnel.
[0086] Specifically, after determining that the big model determines the cause of the fault and the solution of the platform with the fault diagnosis result being the diagnosis abnormality, the cause of the fault and the solution of the platform with the fault diagnosis result being the diagnosis abnormality can be sent to the operation and maintenance terminal corresponding to the operation and maintenance personnel, so that the operation and maintenance personnel can promptly know the cause of the fault of the platform with the fault diagnosis result being the diagnosis abnormality, and can refer to the solution to perform fault maintenance.
[0087] In the embodiment of the present invention, the cause of the fault and the solution of the platform with the diagnosis abnormality are sent to the operation and maintenance terminal, and the operation and maintenance personnel are promptly notified of the cause of the fault and the solution of the platform, so that the operation and maintenance personnel can perform timely and effective fault maintenance on the outbound call system.
[0088] The fault diagnosis method provided by the embodiment of the present invention comprises: obtaining the historical technical indicators, historical business indicators of the outbound call system and the historical fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call dispatching platform in the outbound call system; fitting the decision tree model with the historical technical indicators, the historical business indicators and the historical fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call dispatching platform in the outbound call system as training sets, obtaining the fault diagnosis model; obtaining the real-time technical indicators and real-time business indicators of the outbound call system; inputting the real-time technical indicators and the real-time business indicators into a pre-trained fault diagnosis model, so that the fault diagnosis model The fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call dispatching platform are determined according to the real-time technical indicators and the real-time business indicators; if the fault diagnosis result of the voice processing platform, the natural language processing platform or the outbound call dispatching platform is a diagnosis abnormality, the real-time technical indicators, the real-time business indicators, the platform whose fault diagnosis result is a diagnosis abnormality and its abnormality type, and a pre-set prompt word are input into the big model, so that the big model determines the fault cause and solution of the platform whose fault diagnosis result is a diagnosis abnormality based on the prompt word; the fault cause and solution of the platform whose fault diagnosis result is a diagnosis abnormality are sent to the operation and maintenance terminal corresponding to the operation and maintenance personnel. The above technical scheme obtains historical technical indicators and historical business indicators of the outbound call system in a historical period of time, as well as historical fault diagnosis results of the voice processing platform, natural language processing platform and outbound call dispatching platform in the outbound call system, and fits the decision tree model through a training set composed of historical technical indicators, historical business indicators and historical fault diagnosis results of the voice processing platform, natural language processing platform and outbound call dispatching platform in the outbound call system to obtain a fault diagnosis model that can be used for fault diagnosis of the outbound call system, obtains real-time technical indicators of the outbound call system in the memory of the server where the outbound call system is located, obtains real-time business indicators of the outbound call system in the high-efficiency lake table of the outbound call system, and inputs the real-time technical indicators and real-time business indicators of the outbound call system into the pre-trained fault diagnosis model. The fault diagnosis model can determine the real-time fault diagnosis results of the voice processing platform, language processing platform and dispatching platform in the outbound call system according to the real-time technical indicators and real-time business indicators of the outbound call system, realize real-time fault diagnosis of the voice processing platform, language processing platform and dispatching platform in the outbound call system, and then realize accurate fault diagnosis of the outbound call system, and further realize real-time status monitoring of each platform in the outbound call system.
[0089] Furthermore, when it is determined that the fault diagnosis result of at least one of the voice processing platform, the natural language processing platform, and the outbound call dispatching platform is a diagnostic abnormality, the real-time technical indicators, the real-time business indicators, the platform whose fault diagnosis result is a diagnostic abnormality and its abnormality type, and the pre-set prompt words are input into the big model. The big model can quickly determine the fault cause and solution of the platform whose fault diagnosis result is a diagnostic abnormality based on the prompt words.
[0090] Of course, after determining that the fault diagnosis result of the large model is the fault cause and solution of the platform with the diagnosis abnormality, the fault cause and solution of the platform with the diagnosis abnormality are sent to the operation and maintenance terminal, the operation and maintenance personnel can be notified of the fault cause and solution of the platform in a timely manner, which is convenient for the operation and maintenance personnel to perform timely and effective fault maintenance on the outbound call system.
[0091] Figure 3 The present invention provides a schematic diagram of a fault diagnosis device according to an embodiment of the present invention, which can be applied to situations where timely and effective fault diagnosis of an outbound call system is required. The device can be implemented by software and / or hardware and is generally integrated in an electronic device, such as a computer device.
[0092] like Figure 3 As shown, the device comprises:
[0093] An acquisition module 310 is used to acquire real-time technical indicators and real-time business indicators of an outbound call system, wherein the outbound call system includes a voice processing platform, a natural language processing platform, and an outbound call dispatching platform;
[0094] The diagnostic module 320 is used to input the real-time technical indicators and the real-time business indicators into a pre-trained fault diagnosis model so that the fault diagnosis model determines the fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call scheduling platform according to the real-time technical indicators and the real-time business indicators.
[0095] The fault diagnosis device provided in this embodiment obtains the real-time technical indicators and real-time business indicators of the outbound call system, wherein the outbound call system includes a voice processing platform, a natural language processing platform and an outbound call dispatching platform; the real-time technical indicators and the real-time business indicators are input into a pre-trained fault diagnosis model, so that the fault diagnosis model determines the fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call dispatching platform according to the real-time technical indicators and the real-time business indicators. The above technical scheme obtains the real-time technical indicators of the outbound call system in the memory of the server where the outbound call system is located, obtains the real-time business indicators of the outbound call system in the high-efficiency lake table of the outbound call system, and inputs the real-time technical indicators and real-time business indicators of the outbound call system into the pre-trained fault diagnosis model. The fault diagnosis model can determine the real-time fault diagnosis results of the voice processing platform, the language processing platform and the dispatching platform in the outbound call system according to the real-time technical indicators and the real-time business indicators of the outbound call system, thereby realizing real-time fault diagnosis of the voice processing platform, the language processing platform and the dispatching platform in the outbound call system, and further realizing accurate fault diagnosis of the outbound call system.
[0096] In one embodiment, the real-time technical indicators include at least central processing unit utilization rate, memory occupancy, disk read and write speed, and network transmission speed; the real-time business indicators include at least outbound call volume, connection volume, connection rate, scenario type, average call duration, high intention rate, natural language processing rejection number, complaint rate, interactive bottom-line trigger number, interactive bottom-line trigger rate, call silence number, call silence rate, interactive failure rate, outbound call result pushback number, and outbound call result pushback rate; the fault diagnosis result is a normal diagnosis or an abnormal diagnosis. When the fault diagnosis result is an abnormal diagnosis, the fault diagnosis result also includes an abnormality type, which is a scenario abnormality, an interactive abnormality, a bot abnormality, or a pushback abnormality.
[0097] Based on the above embodiment, the acquisition module 310 is specifically used for:
[0098] The real-time business data of the outbound call system is obtained based on the outbound call record table, call detail table and call intention table of the outbound call system; the real-time business indicators of the outbound call system are determined by extracting features and processing the real-time business data.
[0099] Based on the above embodiment, the device further includes:
[0100] A training module is used to obtain historical technical indicators, historical business indicators of the outbound call system, and historical fault diagnosis results of the voice processing platform, the natural language processing platform, and the outbound call scheduling platform in the outbound call system; the historical technical indicators, the historical business indicators, and the historical fault diagnosis results of the voice processing platform, the natural language processing platform, and the outbound call scheduling platform in the outbound call system are used as training sets to fit a decision tree model to obtain the fault diagnosis model.
[0101] Based on the above embodiment, the device further includes:
[0102] An execution module is used to input the real-time technical indicators, the real-time business indicators, the platform whose fault diagnosis result is a diagnosis abnormality and its abnormality type, and a pre-set prompt word into a large model after determining the fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call dispatching platform, if the fault diagnosis result of at least one of the voice processing platform, the natural language processing platform and the outbound call dispatching platform is a diagnosis abnormality, so that the large model determines the fault cause and solution of the platform whose fault diagnosis result is a diagnosis abnormality based on the prompt word.
[0103] Based on the above embodiment, the device further includes:
[0104] The sending module is used to send the fault cause and solution of the platform with the fault diagnosis result as the diagnosis abnormality to the operation and maintenance terminal corresponding to the operation and maintenance personnel after determining that the fault diagnosis result is the fault cause and solution of the platform with the diagnosis abnormality.
[0105] The fault diagnosis device provided in the embodiment of the present invention can execute the fault diagnosis method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the fault diagnosis method.
[0106] It is worth noting that in the embodiment of the above-mentioned fault diagnosis device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.
[0107] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 4 A block diagram of an exemplary electronic device 4 suitable for implementing embodiments of the present invention is shown. Figure 4 The electronic device 4 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.
[0108] like Figure 4 As shown, the electronic device 4 is in the form of a general purpose computing electronic device. The components of the electronic device 4 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).
[0109] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.
[0110] The electronic device 4 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 4, including volatile and non-volatile media, removable and non-removable media.
[0111] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 4 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.
[0112] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.
[0113] The electronic device 4 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the electronic device 4, and / or any device that enables the electronic device 4 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 4 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. Figure 4 As shown, the network adapter 20 communicates with other modules of the electronic device 4 via the bus 18. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 4, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0114] The processing unit 16 executes various functional applications and page displays by running the program stored in the system memory 28, for example, implementing the fault diagnosis method provided by the embodiment of the present invention, the method comprising:
[0115] Acquire real-time technical indicators and real-time business indicators of an outbound call system, wherein the outbound call system includes a voice processing platform, a natural language processing platform, and an outbound call dispatching platform;
[0116] The real-time technical indicators and the real-time business indicators are input into a pre-trained fault diagnosis model so that the fault diagnosis model determines the fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call scheduling platform according to the real-time technical indicators and the real-time business indicators.
[0117] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the fault diagnosis method provided by any embodiment of the present invention.
[0118] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, for example, a fault diagnosis method provided by an embodiment of the present invention is implemented. The method includes:
[0119] Acquire real-time technical indicators and real-time business indicators of an outbound call system, wherein the outbound call system includes a voice processing platform, a natural language processing platform, and an outbound call dispatching platform;
[0120] The real-time technical indicators and the real-time business indicators are input into a pre-trained fault diagnosis model so that the fault diagnosis model determines the fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call scheduling platform according to the real-time technical indicators and the real-time business indicators.
[0121] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.
[0122] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0123] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
[0124] Computer program code for performing the operations of the present invention may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0125] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.
[0126] In addition, the acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with the relevant provisions of national laws and regulations.
[0127] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims
1. A fault diagnosis method, characterized in that: include: Acquire real-time technical indicators and real-time business indicators of an outbound call system, wherein the outbound call system includes a voice processing platform, a natural language processing platform, and an outbound call dispatching platform; The real-time technical indicators and the real-time business indicators are input into a pre-trained fault diagnosis model so that the fault diagnosis model determines the fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call scheduling platform according to the real-time technical indicators and the real-time business indicators.
2. The fault diagnosis method according to claim 1, characterized in that: The real-time technical indicators include at least the CPU usage rate, memory occupancy, disk read and write speed, and network transmission speed; the real-time business indicators include at least the outbound call volume, the connection volume, the connection rate, the scenario type, the average call duration, the high intention rate, the natural language processing rejection number, the complaint rate, the interactive bottom-line trigger number, the interactive bottom-line trigger rate, the number of silent calls, the silent call rate, the interactive failure rate, the number of outbound call result pushbacks, and the outbound call result pushback rate; the fault diagnosis result is a normal diagnosis or an abnormal diagnosis. When the fault diagnosis result is an abnormal diagnosis, the fault diagnosis result also includes an abnormality type, which is a scenario abnormality, an interactive abnormality, a bot abnormality, or a pushback abnormality.
3. The fault diagnosis method according to claim 2, characterized in that: Get real-time business indicators of the outbound call system, including: Acquire real-time business data of the outbound call system based on the outbound call record table, call details table and call intention table of the outbound call system; The real-time business index of the outbound call system is determined by extracting features and processing the real-time business data.
4. The fault diagnosis method according to claim 1, characterized in that: The training process of the fault diagnosis model includes: Obtaining historical technical indicators, historical business indicators of the outbound call system, and historical fault diagnosis results of the voice processing platform, the natural language processing platform, and the outbound call dispatching platform in the outbound call system; The historical technical indicators, the historical business indicators, and the historical fault diagnosis results of the voice processing platform, the natural language processing platform, and the outbound call dispatching platform in the outbound call system are used as training sets to fit a decision tree model to obtain the fault diagnosis model.
5. The fault diagnosis method according to claim 1, characterized in that: After determining the fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call dispatching platform, the method further includes: If the fault diagnosis result of at least one of the voice processing platform, the natural language processing platform and the outbound call dispatching platform is a diagnosis abnormality, the real-time technical indicators, the real-time business indicators, the platform whose fault diagnosis result is a diagnosis abnormality and its abnormality type, and a pre-set prompt word are input into the big model, so that the big model determines the fault cause and solution of the platform whose fault diagnosis result is a diagnosis abnormality based on the prompt word.
6. The fault diagnosis method according to claim 5, characterized in that: After determining that the fault diagnosis result is the fault cause and solution of the platform with abnormal diagnosis, the method further includes: The fault diagnosis result is that the fault cause and solution of the platform with the diagnosis abnormality are sent to the operation and maintenance terminal corresponding to the operation and maintenance personnel.
7. A fault diagnosis device, characterized in that: include: An acquisition module, used to acquire real-time technical indicators and real-time business indicators of an outbound call system, wherein the outbound call system includes a voice processing platform, a natural language processing platform, and an outbound call dispatching platform; The diagnostic module is used to input the real-time technical indicators and the real-time business indicators into a pre-trained fault diagnosis model so that the fault diagnosis model determines the fault diagnosis results of the voice processing platform, the natural language processing platform and the outbound call scheduling platform according to the real-time technical indicators and the real-time business indicators.
8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the fault diagnosis method as described in any one of claims 1-6.
9. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to perform the fault diagnosis method as described in any one of claims 1 to 6 when executed by a computer processor.
10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program implements the fault diagnosis method according to any one of claims 1 to 6.