CN115328689A

CN115328689A - Fault diagnosis method, device, equipment and program product

Info

Publication number: CN115328689A
Application number: CN202211249173.8A
Authority: CN
Inventors: 唐钟; 徐大伟
Original assignee: Jidu Technology Co ltd
Current assignee: Beijing Jidu Technology Co Ltd
Priority date: 2022-10-12
Filing date: 2022-10-12
Publication date: 2022-11-11
Anticipated expiration: 2042-10-12
Also published as: CN115328689B

Abstract

The embodiment of the application provides a fault diagnosis method, a fault diagnosis device, equipment and a program product, relates to the technical field of fault diagnosis, and is used for improving the fault troubleshooting efficiency of a vehicle and further improving the fault maintenance efficiency. In an embodiment of the present application, the method may include: acquiring equipment information and fault information of target equipment to be maintained; determining at least one fault knowledge point matched with the equipment information and the fault information of the target equipment from an equipment fault knowledge base; the equipment fault knowledge base comprises a plurality of fault types, test schemes corresponding to fault reasons and fault repair schemes, wherein one fault type comprises at least one fault knowledge point, and one fault knowledge point corresponds to one or more fault reasons; determining the probability of each fault reason corresponding to the at least one fault knowledge point; and determining the fault reason of the target equipment based on the probability of each fault reason corresponding to the at least one fault knowledge point.

Description

Fault diagnosis method, device, equipment and program product

Technical Field

The present application relates to the field of fault diagnosis technologies, and in particular, to a fault diagnosis method, apparatus, device, and program product.

Background

With the continuous increase of the vehicle intelligent degree and the increase of the complexity of the vehicle electronic and electrical architecture, the updating of the knowledge and technology of the vehicle after-sale technicians is difficult to timely follow the rapid iteration of the vehicle electronic technology and software functions. When a vehicle is relatively faulty, a lot of time and energy are generally consumed for vehicle after-sales technicians to troubleshoot the cause of the fault, which makes the vehicle troubleshooting inefficient. Existing vehicle fault diagnosis schemes typically include two of: one is based on the analysis of the fault tree of the whole vehicle and the subsystem, and the other is based on the large data mining and matching of the maintenance case.

According to the first vehicle fault diagnosis scheme, fault trees of all subsystems of the vehicle need to be built, fault transmission logics among the subsystems are analyzed, and finally the fault trees of all the subsystems are connected to build a fault tree of the whole vehicle. Obviously, the fault diagnosis scheme has the problems of complex system, high development difficulty, poor applicability among different vehicle types and the like, and the fault diagnosis method also needs to be established on the basis of a large number of cases of actual fault vehicles. The fault diagnosis scheme based on the large data of the maintenance cases also needs to accumulate a large number of historical maintenance cases, and obviously, the fault diagnosis mode is not suitable for vehicle maintenance of the vehicle model without the historical maintenance data.

Therefore, how to provide a general fault diagnosis method for various existing vehicles to improve the troubleshooting efficiency of the vehicle and further improve the fault maintenance efficiency still needs to provide a further solution.

Disclosure of Invention

Aspects of the present application provide a fault diagnosis method, apparatus, device, and program product for improving the troubleshooting efficiency of a vehicle and further improving the troubleshooting efficiency.

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

acquiring equipment information and fault information of target equipment to be maintained;

determining at least one fault knowledge point matched with the equipment information and the fault information of the target equipment from an equipment fault knowledge base; the equipment fault knowledge base comprises a plurality of fault types, test schemes corresponding to fault reasons and fault repair schemes, wherein one fault type comprises at least one fault knowledge point, and one fault knowledge point corresponds to one or more fault reasons;

determining the probability of each fault reason corresponding to the at least one fault knowledge point;

and determining the fault reason of the target equipment based on the probability of each fault reason corresponding to the at least one fault knowledge point.

In a second aspect, an embodiment of the present application further provides a computer device, including: a memory and a processor; wherein the memory is used for storing a computer program; the processor is coupled to the memory for executing the computer program for performing the steps of the method of the first aspect.

In a third aspect, embodiments of the present application further provide a computer program product, which includes a computer program/instruction, and when being executed, the computer program/instruction processor implements the steps in the method according to the first aspect.

As can be seen from the technical solutions provided in the embodiments of the present application, the embodiments of the present application have at least one of the following technical effects:

according to one or more embodiments provided by the application, a pre-constructed equipment fault knowledge base can be used as a basis for equipment fault diagnosis, corresponding fault knowledge points are matched from the equipment fault knowledge base according to equipment information and fault information of target equipment, the fault occurrence probability of each fault reason corresponding to the matched fault knowledge points is determined, and finally the fault reason of the target equipment can be diagnosed according to the fault occurrence probability corresponding to each fault reason, so that the troubleshooting efficiency of equipment faults is effectively improved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

fig. 1 is a schematic flow chart illustrating an implementation of a fault diagnosis method according to an exemplary embodiment of the present application;

fig. 2 is a schematic structural diagram of an equipment failure knowledge base in a failure diagnosis method according to an exemplary embodiment of the present application;

fig. 3 (a) is a schematic flow chart of a first part of a fault diagnosis method applied to an actual scenario according to an exemplary embodiment of the present application;

fig. 3 (b) is a second partial schematic flowchart of a fault diagnosis method applied to an actual scenario according to an exemplary embodiment of the present application;

fig. 4 is a schematic structural diagram of a fault diagnosis device according to an exemplary embodiment of the present application;

fig. 5 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described below with reference to specific embodiments of the present application and accompanying drawings.

As described in the background art, the conventional fault diagnosis scheme usually needs to be based on a large amount of historical repair data of faulty vehicles, and the conventional fault diagnosis scheme is complex in system and difficult to develop, and cannot be used for some new vehicles without historical repair data.

To this, for the troubleshooting efficiency that improves the vehicle and then improve the maintenance of failure efficiency, this application embodiment provides a solution, and the basic thinking is: according to the method, a pre-constructed equipment fault knowledge base is used as a basis for equipment fault diagnosis, corresponding fault knowledge points are matched from the equipment fault knowledge base according to equipment information and fault information of target equipment, the fault occurrence probability of each fault reason corresponding to the matched fault knowledge points is determined, and finally the fault reason of the target equipment can be diagnosed according to the fault occurrence probability corresponding to each fault reason, so that the troubleshooting efficiency of equipment faults is effectively improved.

The equipment fault knowledge base can be constructed based on the problem data of the system fault principle, the whole machine (such as a whole vehicle) test and the system integration test of the equipment, and the data based on the construction of the equipment fault knowledge base can be obtained before the equipment is sold on the market, namely in the production process.

The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.

Fig. 1 is a schematic implementation flowchart of a fault diagnosis method according to an embodiment of the present application. The method of fig. 1 may include:

step 110, obtaining the device information and fault information of the target device to be maintained.

Step 120, determining at least one failure knowledge point matching the device information and the failure information of the target device from the device failure knowledge base.

And step 130, determining the probability of each fault reason corresponding to at least one fault knowledge point.

And 140, determining the fault reason of the target equipment based on the probability of each fault reason corresponding to at least one fault knowledge point.

It should be noted that the fault diagnosis method provided in the embodiment of the present application may be applicable to fault diagnosis of vehicles such as automobiles, ships, airplanes, trains, and the like, and in addition, the fault diagnosis method may also be applicable to other electronic devices, for example, electronic devices such as computers, mobile phones, computers, and the like. As an example, the embodiment of the present application takes a vehicle as an example to specifically describe an implementation process of the fault diagnosis method.

The device information of the target device includes a device model and a time-off-line of the target device, or a device model and a software version of the target device. Taking the target device as an example of the target Vehicle, then for step 110, the Vehicle information of the target Vehicle may include a Vehicle Identification Number (VIN) of the target Vehicle, a Vehicle model of the target Vehicle, a offline time, and a full Vehicle software version. Where VIN is composed of 17 digits and capital letters, the first to third digits are an identification code of a vehicle manufacturer, the fourth to ninth digits are a vehicle description part, and the tenth to seventeenth digits are a vehicle indication part. And VIN of different vehicles can not be repeated, and the VIN can be used as a unique identifier of the vehicle, which is equivalent to the identification number of the vehicle. The vehicle model, the offline time, and the full vehicle software version of the target vehicle may be obtained from the vehicle center based on the VIN of the target vehicle.

The fault information of the target vehicle may include a fault Code (DTC), warning prompt information (WTI), an abnormal signal, a fault symptom, and the like of the target vehicle. The DTC is used for locating partial fault positions and partial fault reasons of the vehicle under the condition that the vehicle is not disassembled, and can be used for detecting and diagnosing fault positions of a vehicle engine, a vehicle chassis, a vehicle body and accessories, vehicle exhaust pollutants, noise and the like.

When the target vehicle breaks down, vehicle information such as the vehicle model, the offline time and the whole vehicle software version of the target vehicle can be determined based on the VIN of the target vehicle, and fault information such as DTC, WTI, abnormal signals and fault symptoms displayed when the target vehicle breaks down is acquired.

For example, in step 120, the device failure knowledge base includes a plurality of failure types, test schemes corresponding to failure causes, and failure repair schemes, where one failure type includes at least one failure knowledge point, and one failure knowledge point corresponds to one or more failure causes, and the device failure knowledge base is constructed based on problem data of a device system failure principle, a device test, and a system integration test.

Taking the device as an example, the problem data of the system fault principle, the whole vehicle test and the system integration test of one or more vehicles can be obtained before the one or more vehicles are on the market. Thus, even if the model of the target vehicle is a new model to be marketed, the cause of failure of the target vehicle can be diagnosed based on the equipment failure knowledge base. It should be understood that since the cause of failure of vehicles of different vehicle types will typically also vary, to achieve accurate location of the cause of failure of the target vehicle, the one or more vehicles may include vehicles of the same vehicle type as the target vehicle.

As an embodiment, the fault types contained in the equipment fault knowledge base may include fault types such as DTC, WTI, abnormal signals, and fault symptoms. In addition, the equipment failure knowledge base may also include failure types that match the vehicle model and the down time of the vehicle, and failure types that match the vehicle model and the full vehicle software version of the vehicle.

Fig. 2 is a schematic structural diagram of an equipment fault knowledge base in a fault diagnosis method according to an exemplary embodiment of the present application. The equipment fault knowledge base comprises a fault code base, a fault symptom base, a fault reason base, a test scheme base, a fault repair scheme base, an alarm prompt information base and an abnormal signal base. The fault code library stores fault knowledge points of DTC fault types, the fault symptom library stores fault knowledge points of fault types of fault symptoms, the alarm prompt information library stores fault knowledge points of fault types of alarm prompt information, and the abnormal signal library stores fault knowledge points of fault types of abnormal signals. The fault reason library stores fault knowledge points of fault types except a fault code library, a fault symptom library, an alarm prompt information library and an abnormal signal library. The test scheme library comprises test schemes formulated for all fault reasons in the equipment fault knowledge library, and the fault repair schemes comprise fault repair schemes formulated for all fault reasons in the equipment fault knowledge library. In addition, the fault symptom library comprises a whole vehicle symptom library, a system symptom library and a working condition library. The failure reason library comprises a part library, a failure part library and a failure mode library.

In addition to the basic database, since there may be correlation between different fault types, correlation between a fault cause and each fault type, and correlation between a fault cause and a test scheme, based on which, in order to improve efficiency and accuracy of vehicle fault troubleshooting and avoid repeated troubleshooting, the equipment fault knowledge base may further include a fault cause-fault code relation base, a fault cause-fault symptom relation base, a fault cause-test scheme relation base, a fault cause-fault repair scheme relation base, an alarm prompt information-abnormal signal relation base, a fault cause-alarm prompt information relation base, and a fault cause-abnormal signal relation base. Optionally, in the method shown in fig. 1, after the failure cause of the target device is determined, a failure repair scheme corresponding to the failure cause may also be recommended. The fault remediation scheme may be prompted to maintenance personnel, for example, via an output device such as a display screen or speaker.

It should be understood that the vehicle can be marketed for users through a plurality of system fault principle tests, whole vehicle tests and system integration tests in the production process. During the process of multiple system fault principle tests, finished automobile tests and system integration tests, the automobile may expose some hardware problems, and the hardware problems are recorded in an equipment fault knowledge base in the form of fault knowledge points during the tests, are associated with the automobile model and the offline time (namely the production time) of the automobile, and can be used as a basis for checking the fault reason of the automobile when the automobile goes on the market and is in fault in the using process of a user.

Optionally, after the target vehicle fails, in order to implement an all-around troubleshooting of the failure cause of the target vehicle, a hardware and software problem generated in a production process of the target vehicle may be first troubleshot based on vehicle information of the target vehicle to determine whether the failure cause of the target vehicle is associated with the hardware and software problem in the production process. Specifically, determining at least one failure knowledge point matching the device information and the failure information of the target device from the device failure knowledge base includes:

determining the equipment model and the off-line time of the target equipment or determining the equipment model and the software version of the target equipment based on the equipment information of the target equipment;

determining whether a first failure knowledge point matched with the equipment model and the offline time of the target equipment or a second failure knowledge point matched with the equipment model and the software version of the target equipment exists in an equipment failure knowledge base;

if the first failure knowledge point or the second failure knowledge point exists in the equipment failure knowledge base, determining whether the failure corresponding to the first failure knowledge point or the second failure knowledge point is repaired or not;

and if the fault corresponding to the first fault knowledge point or the second fault knowledge point is repaired, determining at least one fault knowledge point matched with the fault information of the target equipment and the equipment model of the target equipment from the equipment fault knowledge base.

Optionally, after determining whether the first failure knowledge point matching the vehicle model and the offline time of the target vehicle exists in the vehicle failure knowledge base, if the first failure knowledge point matching the vehicle model and the offline time of the target vehicle does not exist in the vehicle failure knowledge base, it indicates that the target vehicle does not have a hardware problem that may cause a failure cause of the target vehicle during a production test.

When a first failure knowledge point which is matched with the vehicle model and the off-line time of the target vehicle exists in the vehicle failure knowledge base, the first failure knowledge point indicates that some hardware problems occur in the test of the target vehicle in the production process, and the problems are usually repaired in the production or after-sale maintenance of the vehicle and then are sold for users to use. In this case, it is determined whether the failure cause corresponding to the first failure knowledge point is repaired, and if the failure cause corresponding to the first failure knowledge point is repaired, the failure cause corresponding to the first failure knowledge point can be eliminated from the failure causes causing the failure of the target vehicle.

It should be understood that the whole vehicle software version is also recorded with the exposed software problems in the development, test and trial process, and such software problems are also recorded in the vehicle failure knowledge base in the form of failure knowledge points and are associated with the vehicle model of the vehicle and the whole vehicle software version so as to be used as a basis for checking the vehicle failure reason when the failure occurs in the use process of the vehicle by a user after the vehicle is on the market. Specifically, when the vehicle fault causes are checked, whether a software problem exists in the whole vehicle software version matched with the vehicle model of the target vehicle in the software development and test process can be determined, and if a second fault knowledge point corresponding to the software problem is recorded in the vehicle fault knowledge base, the fault cause corresponding to the second fault knowledge point can be determined as one of the fault causes causing the target vehicle to have a fault. In this case, a fault repair scheme corresponding to a fault cause caused by the entire vehicle software version matched with the vehicle model of the target vehicle can be determined from the vehicle fault knowledge base, and the target vehicle can be subjected to fault repair according to the fault repair scheme. And if the vehicle fault knowledge base does not record a second fault knowledge point corresponding to the software problem, the fault reason corresponding to the second fault knowledge point can be eliminated from the fault reasons causing the target vehicle fault.

As one embodiment, the above embodiment of checking the first failure knowledge point and the second failure knowledge point may be implemented as two parallel embodiments, or may be used in combination with the two embodiments. When the two embodiments are combined, the sequence of checking the first failure knowledge point and the second failure knowledge point in the embodiment of the present application may not be specifically limited, and the sequence may be selected according to actual needs.

For example, for step 130, one failure knowledge point corresponds to one or more failure causes, and often, failure recovery schemes for different failure causes are different, and in order to determine a failure cause causing the failure of the target vehicle, so as to accurately implement the failure recovery of the target vehicle, the target vehicle may be tested on-line (or remotely) through the test schemes for the failure causes corresponding to at least one failure knowledge point, so as to determine which of the failure causes corresponding to at least one failure knowledge point are related to the test result, and which are unrelated to the test result, thereby achieving the purpose of determining the probability that each failure cause causes the failure of the target vehicle. Specifically, determining the probability of each fault reason corresponding to at least one fault knowledge point includes:

testing the target equipment based on the on-line testing scheme of each fault reason corresponding to at least one fault knowledge point to obtain a testing result of the target equipment;

determining a first related fault reason, a first unrelated fault reason and a first to-be-determined fault reason from all fault reasons corresponding to at least one fault knowledge point based on the test result; the first relevant fault reason is a fault reason with the probability of 1, the first irrelevant fault reason is a fault reason with the probability of 0, and the first to-be-determined fault reason is a fault reason except the first relevant fault reason and the first irrelevant fault reason in the fault reasons corresponding to the at least one fault knowledge point;

and determining the probability of the first to-be-confirmed fault reason based on the number of the fault reasons corresponding to the fault knowledge point to which the first to-be-confirmed fault reason belongs, wherein the first to-be-confirmed fault reason is the fault reason of the offline test scheme in the first to-be-confirmed fault reasons.

The on-line test of the target vehicle can be usually performed in a remote test mode, and for some test schemes which cannot be subjected to the remote test, off-line test of the target vehicle can be performed on the site by off-line maintenance personnel to obtain a test result of the target vehicle.

After determining a first related fault reason which has an association relation with the online test result of the target vehicle from the fault reasons corresponding to the at least one fault knowledge point, the probability that the target vehicle fails at this time due to the first related fault reason is determined to be 100%, and the first related fault reason is marked to be in a "confirmation" state, so as to indicate that the first related fault reason is determined to be the fault reason of the target vehicle which fails at this time. After determining a first irrelevant fault reason which has no association relation with the test result of the target vehicle from all fault reasons corresponding to at least one fault knowledge point, determining that the probability of the first irrelevant fault reason causing the current fault of the target vehicle is 0, and deleting the first irrelevant fault reason from all fault reasons corresponding to at least one fault knowledge point to indicate that the first irrelevant fault reason can be eliminated from the fault reasons of the current fault of the target vehicle.

After the first relevant fault reason and the first irrelevant fault reason are determined based on the test result obtained by testing the target vehicle based on the test scheme corresponding to the at least one fault knowledge point, and the first to-be-determined fault reason except the first relevant fault reason and the first irrelevant fault reason in the fault reasons corresponding to the at least one fault knowledge point can be marked with an 'undetermined' state, namely, the first to-be-determined fault reason is a fault reason which may cause the target vehicle to have a fault at this time. The first to-be-determined fault cause may include a first to-be-determined fault cause of the offline test scheme and a fault cause of the offline test scheme. And for the first to-be-confirmed fault reason of the on-line test scheme, off-line testing can be performed on the target vehicle by off-line maintenance personnel on site to obtain a test result of the target vehicle. If the fault causes of the offline test scheme do not exist, maintenance personnel of the equipment fault knowledge base need to pay important attention to the fault causes so as to research the corresponding offline test scheme as a basis for subsequently perfecting the equipment fault knowledge base. Specifically, the first to-be-determined fault cause further includes a fault cause for which there is no offline test scheme.

For the first to-be-confirmed fault reasons of the off-line test scheme existing in the first to-be-confirmed fault reasons, the probability of the first to-be-confirmed fault reasons can be determined based on the number of the fault reasons corresponding to the fault knowledge point to which the first to-be-confirmed fault reasons belong, then sorting is performed according to the sequence from the largest probability to the smallest probability, the fault reasons with the same probability are sorted according to the standard that the fault reasons with low test cost are ranked, and if the probabilities of the fault reasons are the same and the test costs are also the same, sorting is performed according to the fault identification, and then, the fault reasons are checked one by one according to the test scheme corresponding to each fault reason in the first to-be-confirmed fault reasons until the number of the first to-be-confirmed fault reasons is 0.

The probability of the first to-be-confirmed fault cause RCn may be determined according to a formula Count _ n/Σ Count _ i, where Σ Count _ i is a sum of the number of fault causes corresponding to the fault knowledge point corresponding to the first to-be-confirmed fault cause RCn, and Count _ n is 1 in an initial state. In the initial state, assuming that the sum of the number of the fault reasons corresponding to the fault knowledge point corresponding to the first fault reason RCn to be confirmed is 3, the probability of determining the first fault reason RCn to be confirmed as 1/3 is determined according to the formula Count _ n/Σ Count _ i.

Optionally, if a fault repair scheme that is the same as the confirmed fault cause (i.e., the first related fault cause) exists in the fault repair scheme corresponding to a certain undetermined fault cause in the first undetermined fault causes, the fault repair scheme corresponding to the confirmed fault cause can solve the vehicle fault caused by the undetermined fault cause, so that the undetermined fault cause can be deleted from the first undetermined fault cause, thereby reducing the time and test cost for fault diagnosis and improving the fault repair efficiency. Specifically, the determining the fault cause of the target vehicle based on the probability of each fault cause corresponding to at least one fault knowledge point comprises the following steps:

sorting the first to-be-determined fault reasons based on at least one of the probability of the first to-be-determined fault reasons, fault identification, test cost and test scheme;

for each reason to be determined in the sorted first reasons to be determined, if the fault repair scheme corresponding to the reason to be determined is consistent with the fault repair scheme corresponding to the first relevant fault reason, deleting the reason to be determined to obtain the remaining reasons to be determined;

according to the sequence of the remaining undetermined fault reasons, sequentially executing the offline test schemes corresponding to the remaining undetermined fault reasons on the premise that the remaining undetermined fault reasons exist in the offline test schemes;

and determining the fault reason of the target equipment based on the test result of the residual undetermined fault reason.

In this case, since it is not determined whether the first predetermined cause of failure is the cause of failure causing the failure of the target vehicle, it is usually necessary to determine a more detailed test scheme to further investigate and determine which are the relevant causes of failure with a probability of 100% and which are the irrelevant causes of failure with a probability of 0. If the fault repairing scheme corresponding to some undetermined fault reasons in the undetermined fault reasons is consistent with the fault repairing scheme corresponding to some related fault reasons in the confirmed first related fault reasons, the fault problem caused by the undetermined fault reasons can be repaired by using the fault repairing scheme corresponding to the confirmed related fault reasons regardless of the probability of the undetermined fault reasons and whether the undetermined fault reasons are the related fault reasons.

Based on the method and the device, the undetermined fault reasons consistent with the fault repairing scheme corresponding to some of the confirmed first relevant fault reasons can be deleted before confirming a more detailed testing scheme for the undetermined fault reasons, so that the troubleshooting cost of the undetermined fault reasons can be saved, and the overall troubleshooting efficiency of the target vehicle is improved.

Optionally, when there are multiple test schemes corresponding to one remaining undetermined fault reason, the test schemes corresponding to the remaining undetermined fault reasons are sequentially executed according to the sequence of the remaining undetermined fault reasons, the test scheme with the lower test cost can be preferentially selected to perform field or remote test on the target vehicle, and if the probability that the test scheme with the lower test cost cannot confirm the corresponding remaining undetermined fault reasons is 100% or 0, the test scheme with the second lower test cost is selected to perform test on the target vehicle until the probability that the remaining undetermined fault reasons corresponding to the test scheme are determined to be 100% or 0.

Optionally, after determining the first relevant fault cause, the first pending fault cause, and the probability of the first to-be-confirmed fault cause among the first to-be-confirmed fault causes, the embodiments of the present application may rank the fault causes. Specifically, the first related failure cause may be ranked first, and if there are a plurality of first related failure causes, the first related failure causes are ranked according to the failure flag of the first related failure cause. After the first relevant fault cause, the first to-be-confirmed fault causes are sorted. Specifically, the first to-be-confirmed fault causes may be ranked according to their probabilities, and if two or more first to-be-confirmed fault causes have the same probability, the first to-be-confirmed fault causes may be ranked according to their testing costs. And if the test cost of two or more first to-be-confirmed fault reasons is the same, sequencing according to the fault identification. After the first fault reason to be confirmed, the fault reasons without the offline test scheme are sorted, and the fault reasons can be sorted according to the fault identification. The sequence of the fault causes can be used for the maintenance personnel to carry out the reference of the maintenance sequence. And continuously updating the fault reason after continuously confirming a new related fault reason and an unrelated fault reason in the follow-up process until the number of the undetermined fault reasons cannot be confirmed to be 0.

It should be understood that after the remaining undetermined fault reasons are tested according to the test scheme corresponding to the remaining undetermined fault reasons, the remaining undetermined fault reasons can be further checked according to the test result, that is, a relevant fault reason having an association relationship with the test result and an irrelevant fault reason having no association relationship with the test result are determined, so as to further confirm the fault reason of the target vehicle. Specifically, determining the fault reason of the target vehicle based on the test result of the remaining undetermined fault reasons comprises the following steps:

determining a second related fault reason and a second unrelated fault reason from the remaining undetermined fault reasons based on the test result of the remaining undetermined fault reasons, and deleting the second related fault reason and the second unrelated fault reason from the remaining undetermined fault reasons;

and repeatedly executing the operation until the number of the remaining undetermined fault reasons is 0, and determining the fault reason of the target vehicle based on the first relevant fault reason and the second relevant fault reason. The target failure cause includes a first related failure cause and a second related failure cause.

And if the number of the remaining reasons for the pending fault is not 0, the following steps can be continuously executed: firstly, the undetermined fault reason which has the same fault repair scheme with the first related fault reason and/or the second related fault reason is determined from the remaining undetermined fault reasons, and the undetermined fault reason is deleted from the remaining undetermined fault reasons. And sequencing the remaining undetermined fault reasons according to the probability of the current remaining undetermined fault reasons, the test cost and the fault reason identification. And then, sequentially executing the test schemes corresponding to the remaining undetermined fault reasons according to the sequence of the remaining undetermined fault reasons. And finally, determining a third related fault reason with the probability of 100% and a third related fault reason with the probability of 0 from the remaining undetermined fault reasons based on the test result of the remaining undetermined fault reasons. Until the number of fault causes remaining pending fault causes is 0.

Optionally, the vehicle failure knowledge base is constructed based on problem data of system failure principles, vehicle tests and system integration tests of a plurality of vehicles before the vehicles are on the market in an initial state, and in order to continuously perfect the vehicle failure knowledge base, the constructed vehicle failure knowledge base can comprehensively cover all failure causes corresponding to failure knowledge points of various vehicles and a failure repair scheme corresponding to all the failure causes. Specifically, after determining the failure cause of the target vehicle based on the probability of each corresponding failure cause in the at least one failure knowledge point, the method provided in the embodiment of the present application further includes:

repairing the target equipment based on a fault repairing scheme corresponding to the fault reason of the target equipment;

and updating the equipment failure knowledge base based on the failure reason of the target equipment and the repair result of the target equipment.

Optionally, the embodiment of the application can iteratively update the vehicle failure knowledge base from two layers of knowledge point maturity and knowledge point heat of the failure knowledge point. Specifically, updating the device failure knowledge base based on the failure cause of the target device and the repair result of the target device includes:

determining a target fault knowledge point corresponding to a fault reason of target equipment;

updating the knowledge point maturity of the target fault knowledge point under the target fault type in the equipment fault knowledge base based on the target fault type corresponding to the target fault knowledge point and the repair result of the target equipment;

updating the knowledge point heat of the target fault knowledge point under the target fault type in the equipment fault knowledge base based on the target fault type corresponding to the target fault knowledge point;

the knowledge point maturity of the target fault knowledge point is used for representing the success rate of the target fault knowledge point matching with the equipment fault information, and the knowledge point heat of the target fault knowledge point is used for representing the importance degree of the target fault knowledge point in the equipment fault knowledge base.

The initial value of the knowledge point heat of the target fault knowledge point in the vehicle fault knowledge base is 0, if the fault causes of the target vehicle are checked according to the vehicle fault knowledge base, the heat value of the knowledge point of the target fault knowledge point is +1 once the faults of the types such as DTC (digital time to analog) information, WTI (WTI) information, abnormal signals, fault symptoms and the like of the target vehicle are matched with the target fault knowledge point. Obviously, as the number of faulty vehicles subjected to fault troubleshooting according to the vehicle fault knowledge base increases, the knowledge point heat value of each fault knowledge point in the vehicle fault knowledge base also changes, and the fault knowledge point with the larger knowledge point heat value indicates that the fault knowledge point has higher frequency in the faulty vehicle, so that higher requirements are provided for fault reasons, test schemes and fault repair schemes corresponding to the fault knowledge point. Therefore, the knowledge point heat of the target fault knowledge point can be used as an important basis for a technician to continuously optimize the vehicle fault knowledge base.

Specifically, the knowledge point maturity of the target failure knowledge point may be represented by a ratio of the knowledge point success number of the target failure knowledge point to the sum (S + F) of the knowledge point success number S and the knowledge point failure number F of the target failure knowledge point, i.e., S/(S + F). In the process of continuously troubleshooting vehicles according to the vehicle fault knowledge base, the vehicle fault knowledge base is also continuously updated in an iteration mode. In the process, the knowledge point success times S and the knowledge point failure times F of the target failure knowledge points are also dynamically changed.

Taking a fault vehicle as an example, in the process that the target vehicle carries out fault troubleshooting by using a vehicle fault knowledge base, if the fault corresponding to the target fault knowledge point is successfully repaired according to the test scheme and the fault repairing scheme corresponding to the target fault knowledge point provided by the vehicle fault knowledge base, the success frequency S +1 of the knowledge point corresponding to the target fault knowledge point is obtained. On the contrary, if the fault corresponding to the target fault knowledge point cannot be repaired according to the test scheme and the fault repair scheme corresponding to the target fault knowledge point provided by the vehicle fault knowledge base, the failure frequency of the knowledge point corresponding to the fault knowledge point is F +1. The initial values of S and F are 1 in percentage units, so the knowledge point maturity of the newly created failure knowledge points in the vehicle failure knowledge base is 50%. Specifically, updating the knowledge point maturity of the target failure knowledge point in the device failure knowledge base under the target failure type based on the target failure type corresponding to the target failure knowledge point and the repair result of the target device, includes:

determining whether a fault corresponding to a target fault knowledge point in the target equipment under the target fault type is repaired or not based on the repair result of the target equipment;

if the fault corresponding to the target fault knowledge point in the target fault type in the target equipment is determined to be repaired, updating the success times of the knowledge points of the target fault knowledge point in the target fault type, and updating the maturity of the knowledge points of the target fault knowledge point in the target fault type based on the updated success times of the knowledge points;

if it is determined that the fault corresponding to the target fault knowledge point in the target fault type in the target equipment is not repaired, updating the knowledge point failure times of the target fault knowledge point in the target fault type, and updating the knowledge point maturity of the target fault knowledge point in the target fault type based on the updated knowledge point failure times.

Obviously, as the number of faulty vehicles subjected to troubleshooting according to the vehicle fault knowledge base increases, the knowledge point maturity of each faulty knowledge point in the vehicle fault knowledge base also changes, and the fault knowledge point with the higher knowledge point maturity indicates that the fault knowledge point has higher reliability as a fault cause for troubleshooting and repairing the faulty vehicle. The lower the maturity of the knowledge point is, the lower the reliability of the fault knowledge point as a fault cause for troubleshooting and repairing the faulty vehicle is, so that the fault cause, the test scheme and the fault repair scheme corresponding to the fault knowledge point need to be further optimized. Obviously, the knowledge point maturity provides an effective basis for technicians to continuously optimize the vehicle fault knowledge base, and also provides a reference for evaluating the reliability of each fault knowledge point.

Fig. 3 (a) and 3 (b) are schematic flow charts of a fault diagnosis method applied to an actual scenario according to an exemplary embodiment of the present application, where fig. 3 (a) is a first part and fig. 3 (b) is a second part. In fig. 3, the fault diagnosis method includes:

and S31, acquiring the vehicle information and the vehicle fault information of the target vehicle.

And S32, acquiring vehicle information such as the vehicle model, the offline time, the whole vehicle software version and the like of the target vehicle from the vehicle center based on the VIN of the target vehicle.

And S33, matching the first fault knowledge point according to the vehicle model and the offline time.

And S34, determining whether the first failure knowledge point is matched.

If so, go to S35, otherwise, go to S37.

And S35, determining whether the first fault knowledge point is repaired in the production or after-sale maintenance of the batch of vehicles corresponding to the VIN.

If yes, go to S37, otherwise, go to S36.

And S36, recommending a fault maintenance scheme according to the fault repair scheme corresponding to the first fault knowledge point.

And S37, matching a second fault knowledge point according to the vehicle model and the whole vehicle software version.

And S38, determining whether the second failure knowledge point is matched.

If so, go to S39, otherwise, go to S310.

And S39, recommending a fault maintenance scheme according to the fault repair scheme corresponding to the second fault knowledge point.

And S310, judging whether the characteristics of fault types such as DTC/WTI information, abnormal signals, fault characteristics and the like exist.

If yes, S311 is executed, otherwise, the maintenance is finished.

And S311, matching the fault information of the target vehicle with fault knowledge of several fault types in a vehicle fault knowledge base respectively.

S312, determining whether at least one fault knowledge point is matched.

If so, go to S313, otherwise, contact technical support.

And S313, the knowledge point heat of at least one fault knowledge point is +1.

And S314, remotely testing the target vehicle according to the test scheme of each fault reason corresponding to the at least one fault knowledge point.

S315, based on the test result, relevant fault reasons, irrelevant fault reasons and undetermined fault reasons are determined from all fault reasons corresponding to at least one fault knowledge point.

And S316, determining the probability of the reason of the undetermined fault.

And S317, sequencing the related fault reasons and the reasons of the pending faults.

And S318, determining whether the number of the reasons of the undetermined faults is 0.

If so, go to S319, otherwise, go to S320.

And S319, performing fault repairing on the target vehicle according to the fault repairing scheme corresponding to the relevant fault reason.

And S320, if the fault repair scheme which is the same as the related fault reason exists in the undetermined fault reasons, deleting the undetermined fault reason corresponding to the same fault repair scheme.

After S320 is executed, the updated pending fault cause may be obtained, at this time, the process returns to step S317, the updated pending fault cause and the related fault cause are sorted, and after S317 is executed, S321 is executed.

S321, performing field test on the target vehicle according to the test scheme corresponding to the relevant fault reason.

And S322, updating the related fault reason, the unrelated fault reason and the undetermined fault reason according to the test result.

After the step S322 is executed, the process returns to step S318 to determine whether the number of the pending fault causes is 0, if so, the step S319 is executed, and after the step S319 is executed, the step S323 is executed. If the number of the causes of the pending fault is not 0, the process returns to S320.

And S323, determining the fault type of the fault knowledge point corresponding to the relevant fault reason.

And S3241, if the number is DTC, determining the DTC code of the current fault of the target vehicle.

And S3242, determining whether the DTC code still appears in the repaired target vehicle.

If yes, S328 is executed to update the knowledge point maturity of the failure knowledge point corresponding to the DTC code, where F +1 is the number of times of failure of the knowledge point corresponding to the DTC code.

If not, executing S327, and updating the knowledge point maturity of the failure knowledge point corresponding to the DTC code by using S +1 the knowledge point success times of the failure knowledge point corresponding to the DTC code.

S3251, if the information is WTI information, determining WTI information of the current failure of the target vehicle.

S3252, it is determined whether the WTI information is still present in the repaired target vehicle.

If so, S328 is executed to update the knowledge point maturity of the failure knowledge point corresponding to the WTI information by using the knowledge point failure times F +1 of the failure knowledge point corresponding to the WTI information.

If not, executing S327, and updating the knowledge point maturity of the fault knowledge point corresponding to the WTI information by using the knowledge point success times S +1 of the fault knowledge point corresponding to the WTI information.

And S3261, if the vehicle is a fault symptom, determining the fault symptom of the current fault of the target vehicle.

S3262, it is determined whether the repaired target vehicle still exhibits the failure symptom.

If yes, S328 is executed to update the knowledge point maturity of the failure knowledge point corresponding to the failure symptom by the number F +1 of failure times of the knowledge point corresponding to the failure symptom.

If not, executing S327, and updating the knowledge point maturity of the failure knowledge point corresponding to the failure symptom by the number of success times S +1 of the knowledge point corresponding to the failure symptom.

S3271, if the signal is an abnormal signal, determines an abnormal signal indicating the current failure of the target vehicle.

S3272, determining whether the restored target vehicle still has the abnormal signal.

If yes, S328 is executed to update the knowledge point maturity of the failure knowledge point corresponding to the abnormal signal by the number F +1 of failure times of the failure knowledge point corresponding to the abnormal signal.

If not, executing S327, and updating the knowledge point maturity of the failure knowledge point corresponding to the abnormal signal by using S +1 times of success of the knowledge point of the failure knowledge point corresponding to the abnormal signal.

And S327, the success times S +1 of the knowledge points corresponding to the fault knowledge points.

And S328, determining the failure times F +1 of the knowledge points corresponding to the failure knowledge points.

According to the fault diagnosis method provided by one or more embodiments, a pre-established equipment fault knowledge base can be used as a basis for equipment fault diagnosis, corresponding fault knowledge points are matched from the equipment fault knowledge base according to equipment information and fault information of target equipment, the fault occurrence probability of each fault reason corresponding to the matched fault knowledge points is determined, and finally, the fault reason of the target equipment can be diagnosed according to the fault occurrence probability corresponding to each fault reason, so that the equipment fault troubleshooting efficiency is effectively improved. The basis of the established equipment failure knowledge base is problem data of a system failure principle, a complete machine test and a system integration test of a plurality of pieces of equipment, the data can be obtained before the equipment is on the market, namely in the production process, and the method can be realized without accumulating a large amount of historical maintenance data of the failed equipment, so that the time cost required for establishing the equipment failure knowledge base is saved.

It should be noted that in some of the flows described in the above embodiments and the drawings, a plurality of operations are included in a specific order, but it should be clearly understood that the operations may be executed out of the order presented herein or in parallel, and the sequence numbers of the operations, such as 110, 120, etc., are merely used for distinguishing different operations, and the sequence numbers do not represent any execution order per se. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit the types of "first" and "second".

Fig. 4 is a schematic structural diagram of a fault diagnosis device according to another exemplary embodiment of the present application. The failure diagnosing apparatus is used to execute the failure diagnosing method of the embodiment shown in fig. 1 above. As shown in fig. 4, the failure diagnosis apparatus includes:

an information obtaining module 41, configured to obtain device information and fault information of a target device to be maintained;

a knowledge point determining module 42, configured to determine, from an equipment failure knowledge base, at least one failure knowledge point that matches the equipment information and the failure information of the target equipment; the equipment fault knowledge base comprises a plurality of fault types, test schemes corresponding to fault reasons and fault repair schemes, wherein one fault type comprises at least one fault knowledge point, one fault knowledge point corresponds to one or more fault reasons, and the equipment fault knowledge base is obtained by constructing problem data based on a system fault principle, an equipment test and a system integration test of equipment;

a probability determination module 43, configured to determine a probability of each fault cause corresponding to the at least one fault knowledge point;

and a fault determining module 44, configured to determine a fault cause of the target device based on the probability of each fault cause corresponding to the at least one fault knowledge point.

The fault diagnosis device provided by one or more embodiments of the present application can use a pre-established device fault knowledge base as a basis for device fault diagnosis, match corresponding fault knowledge points from the device fault knowledge base according to device information and fault information of a target device, determine fault occurrence probabilities of fault causes corresponding to the matched fault knowledge points, and finally diagnose fault causes of the target device according to the fault occurrence probabilities corresponding to the fault causes, thereby effectively improving troubleshooting efficiency of device faults. The basis of the established equipment failure knowledge base is problem data of a system failure principle, a complete machine test and a system integration test of a plurality of pieces of equipment, and the data can be obtained before the equipment is sold on the market, namely in the production process, so that the method can be realized without accumulating a large amount of historical maintenance data of the failed equipment, and the time cost required for establishing the equipment failure knowledge base is saved.

The specific implementation of the fault diagnosis apparatus shown in fig. 4 has been described in detail in the embodiment of the fault diagnosis method, and will not be elaborated here.

Fig. 5 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present application. The electronic device is configured to perform the fault diagnosis method of the embodiment shown in fig. 1 above. Referring to fig. 5, the electronic device includes: a memory 51 and a processor 52.

The memory 51 is used to store computer programs and may be configured to store various other data to support operations on the computing platform. Examples of such data include instructions for any application or method operating on the computing platform, contact data, phonebook data, messages, pictures, videos, and so forth.

The memory 51 may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The processor 52 is coupled to the memory 51, and configured to execute the computer program in the memory 51, so as to execute the fault diagnosis method according to the embodiment of the present application, and specific descriptions may refer to relevant descriptions in the above method embodiments, which are not described herein again.

Further, as shown in fig. 5, the electronic device may further include: communication components 53, display 54, power components 55, audio components 56, and the like. Only some of the components are schematically shown in fig. 5, and it is not meant that the electronic device comprises only the components shown in fig. 5. In addition, the components within the dashed line frame in fig. 5 are optional components, not necessary components, and may be determined according to the product form of the electronic device. The terminal device of this embodiment may be implemented as a desktop computer, a notebook computer, a smart phone, an IOT device, or other terminal devices that can be deployed in a vehicle, or may be a conventional server, a cloud server, or a server array, or other server-side devices. If the terminal device of this embodiment is implemented as a desktop computer, a notebook computer, a smart phone, or other terminal devices, the terminal device may include components within a dashed line frame in fig. 5; if the terminal device in this embodiment is implemented as a server device such as a conventional server, a cloud server, or a server array, components within a dashed box in fig. 5 may not be included.

Accordingly, the present application further provides a computer-readable storage medium storing a computer program, where the computer program is capable of implementing the steps that can be executed by the electronic device in the foregoing method embodiments when executed.

The methods in this application may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions is loaded and executed on a computer, the processes or functions described herein are performed in whole or in part. The computer may be a general purpose computer, special purpose computer, computer network, network appliance, user equipment, core network appliance, OAM, or other programmable device.

The computer program or instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer program or instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire or wirelessly. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that integrates one or more available media. The usable medium may be a magnetic medium, such as a floppy disk, a hard disk, a magnetic tape; optical media such as digital video disks; but also semiconductor media such as solid state disks. The computer readable storage medium may be volatile or nonvolatile storage medium, or may include both volatile and nonvolatile types of storage media.

The communication component is configured to facilitate wired or wireless communication between the device in which the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as a WiFi, a 2G, 3G, 4G/LTE, 5G and other mobile communication networks, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

The display includes a screen, which may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

The power supply assembly provides power for various components of the device in which the power supply assembly is located. The power components may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device in which the power component is located.

The audio component may be configured to output and/or input an audio signal. For example, the audio component includes a Microphone (MIC) configured to receive an external audio signal when the device in which the audio component is located is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may further be stored in a memory or transmitted via a communication component. In some embodiments, the audio assembly further comprises a speaker for outputting audio signals.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or apparatus comprising the element.

The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A fault diagnosis method, comprising:

2. The method of claim 1, wherein said determining the probability of each failure cause corresponding to said at least one failure knowledge point comprises:

testing the target equipment based on the on-line testing scheme of each fault reason corresponding to the at least one fault knowledge point to obtain a testing result of the target equipment;

determining a first related fault reason, a first unrelated fault reason and a first to-be-determined fault reason from all fault reasons corresponding to the at least one fault knowledge point based on the test result; the first relevant fault reason is a fault reason with a probability of 1, the first irrelevant fault reason is a fault reason with a probability of 0, and the first to-be-determined fault reason is a fault reason except the first relevant fault reason and the first irrelevant fault reason in the fault reasons corresponding to the at least one fault knowledge point;

determining the probability of a first fault reason to be confirmed based on the number of fault reasons corresponding to the fault knowledge point to which the first fault reason to be confirmed belongs, wherein the first fault reason to be confirmed is a fault reason of an offline test scheme in the first fault reason to be confirmed.

3. The method of claim 2, wherein the first to-be-determined cause of failure further comprises a cause of failure for which there is no offline test scheme.

4. The method according to claim 2 or 3, wherein the determining the fault cause of the target device based on the probability of the corresponding fault causes in the at least one fault knowledge point comprises:

sequencing the first to-be-determined fault reasons based on at least one information of the probability, the fault identification, the test cost and the test scheme of the first to-be-determined fault reasons;

for each undetermined fault reason in the sorted first undetermined fault reasons, if the fault repairing scheme corresponding to the undetermined fault reason is consistent with the fault repairing scheme corresponding to the first related fault reason, deleting the undetermined fault reason to obtain the remaining undetermined fault reasons;

according to the sequence of the remaining reasons for the fault to be determined, sequentially executing the off-line test scheme corresponding to the remaining reasons for the fault to be determined on the premise that the remaining reasons for the fault to be determined exist on-line test scheme;

5. The method of claim 4, wherein said determining a cause of failure for the target device based on the test results for the remaining pending causes of failure comprises:

determining a second related fault reason and a second irrelevant fault reason from the residual undetermined fault reasons based on the test result of the residual undetermined fault reasons, and deleting the second related fault reason and the second irrelevant fault reason from the residual undetermined fault reasons;

and repeatedly executing the above operations until the number of the remaining undetermined fault reasons is 0, and determining the fault reason of the target equipment based on the first relevant fault reason and the second relevant fault reason.

6. The method according to any one of claims 1 to 3, wherein after determining the fault cause of the target device based on the probability of each corresponding fault cause in the at least one fault knowledge point, the method further comprises:

7. The method of claim 6, wherein updating the device failure knowledge base based on the cause of failure of the target device and the repair results of the target device comprises:

determining a target fault knowledge point corresponding to the fault reason of the target equipment;

the knowledge point maturity of the target fault knowledge point is used for representing the success rate of the target fault knowledge point matching equipment fault information, and the knowledge point heat of the target fault knowledge point is used for representing the importance degree of the target fault knowledge point in the equipment fault knowledge base.

8. The method as claimed in claim 7, wherein said updating the knowledge point maturity of the target failure knowledge point under the target failure type in the device failure knowledge base based on the target failure type corresponding to the target failure knowledge point and the repair result of the target device comprises:

determining whether the fault corresponding to the target fault knowledge point in the target equipment under the target fault type is repaired or not based on the repair result of the target equipment;

if it is determined that the fault corresponding to the target fault knowledge point in the target fault type in the target device is repaired, updating the knowledge point success times of the target fault knowledge point in the target fault type, and updating the knowledge point maturity of the target fault knowledge point in the target fault type based on the updated knowledge point success times;

if it is determined that the fault corresponding to the target fault knowledge point in the target fault type in the target device is not repaired, updating the knowledge point failure times of the target fault knowledge point in the target fault type, and updating the knowledge point maturity of the target fault knowledge point in the target fault type based on the updated knowledge point failure times.

9. The method according to any one of claims 1 to 3, wherein the determining at least one fault knowledge point which is matched with the equipment information and the fault information of the target equipment from the equipment fault knowledge base comprises:

determining the device model and the offline time of the target device or determining the device model and the software version of the target device based on the device information of the target device;

determining whether a first failure knowledge point matched with the equipment model and the offline time of the target equipment or a second failure knowledge point matched with the equipment model and the software version of the target equipment exists in the equipment failure knowledge base;

if the first failure knowledge point or the second failure knowledge point exists in the equipment failure knowledge base, determining whether a failure corresponding to the first failure knowledge point or the second failure knowledge point is repaired or not;

10. A computer device, comprising: a memory and a processor; wherein the memory is to store a computer program; the processor is coupled to the memory for executing the computer program for performing the steps in the method of any of claims 1-9.

11. A computer program product comprising computer program/instructions for implementing the steps of the method according to any one of claims 1-9 when said computer program/instructions is executed on a processor.