Fault positioning method and computing device thereof

Abstract

The embodiment of the invention provides a fault positioning method and computing equipment thereof, and belongs to the field of computing, and the fault positioning method comprises the steps: obtaining a target identifier and a target model, the target identifier being a test unit item identifier of to-be-detected equipment, and the target model being a model of the to-be-detected equipment; obtaining target data from a target data set according to the target identifier and the target model, the target data set comprising at least one target data, each target data comprising the target identifier, the target model and the fault component type, the target identifier, the target model and the fault part type of the same target data are obtained based on the same problem description information; determining the fault probability of each fault component type according to the first accumulated value of the target data corresponding to each fault component type and the second accumulated value of all the target data; and determining the fault component type of the to-be-detected equipment according to the fault probability. By implementing the technical scheme of the invention, the efficiency and accuracy of fault positioning can be improved.

Description

Technical Field

[0001] The present application relates to the field of computing, and in particular to a fault location method and computing device thereof. Background Art

[0002] With the rapid development of the information industry, various devices (such as terminals, servers, and network equipment) are playing an increasingly important role in business operations and social infrastructure. These devices are subject to various failures over the long term, and quickly and accurately locating faulty components has become a critical step in ensuring stable system operation.

[0003] At present, the location of equipment faults still relies heavily on the experience of maintenance personnel to analyze and judge. However, due to factors such as the maintenance personnel's experience level and knowledge coverage, manual fault location often has problems such as low accuracy and poor efficiency. Summary of the Invention

[0004] The embodiments of the present application provide a fault location method and computing device thereof to improve the accuracy and efficiency of fault location.

[0005] In a first aspect, an embodiment of the present application provides a fault location method, including:

[0006] Obtain a target identifier and a target model, wherein the target identifier is a test unit item identifier of a device to be detected, and the target model is a model of the device to be detected;

[0007] Acquire target data from a target data set according to the target identifier and the target model, the target data set including at least one target data, each target data including the target identifier, the target model, and the faulty component type, the target identifier, the target model, and the faulty component type of the same target data being obtained based on the same problem description information, each problem description information including description information of the test unit item identifier, the model, and the faulty component type;

[0008] determining a failure probability of each of the faulty component types according to a first cumulative value of the target data corresponding to each of the faulty component types and a second cumulative value of all of the target data;

[0009] The faulty component type of the device to be detected is determined according to the failure probability of each faulty component type.

[0010] The above technical solution uses the target identifier and target model to obtain the target data from the target data set based on the test unit item identifier, model and fault component type description information in the problem description information. It can effectively combine the fault location recorded in the historical problem description information, determine the failure probability of each fault component type, ensure the accuracy of the failure probability, and then accurately locate the fault component type, thereby improving the efficiency and accuracy of fault location.

[0011] In a possible implementation, the target identifier, the target machine model, and the faulty component type of the same target data are obtained based on the same problem description information, including:

[0012] The target identifier in the target data is an identifier extracted from the test unit item identifier library of the target model when there is description information matching the text format of the test unit item identifier in the problem description information, and the identifier has a text similarity with the description information greater than a preset threshold;

[0013] The target machine model and the faulty component type in the target data are obtained according to the description information of the problem description information.

[0014] The above technical solution effectively overcomes the problem of non-standard and confusing descriptions of test unit item identifiers in problem descriptions by identifying description information that matches the text format of the test unit item identifier from the problem description information and extracting identifiers from the target model's test unit item identifier library whose text similarity with the description information exceeds a preset threshold. This solution combines text format matching with text similarity matching to improve the accuracy and matching efficiency of target identifier extraction, thereby enhancing the quality of the target data, further improving the accuracy of the fault probability determined based on this target data, and ultimately enhancing the effectiveness of fault location.

[0015] In one possible implementation, before determining the failure probability of each faulty component type based on the first cumulative value of the target data corresponding to each faulty component type and the second cumulative value of all the target data, the method further includes:

[0016] Obtaining a weight for each target data;

[0017] determining the first cumulative value based on a weighted sum of the target data corresponding to each of the faulty components;

[0018] The weighted sum of all the target data is used as the second cumulative value.

[0019] In the above technical solution, before determining the fault probability based on the first cumulative value of the target data corresponding to each faulty component type and the second cumulative value of all target data, the weight of the target data is further introduced. By obtaining the weight of each target data and determining the first cumulative value based on the sum of the weights of the target data corresponding to each faulty component type, and determining the second cumulative value based on the sum of the weights of all target data, the calculation process of the fault probability can comprehensively consider the importance or credibility of different target data, thereby improving the rationality and accuracy of the fault probability assessment results, and further improving the accuracy and reliability of fault location.

[0020] In a possible implementation, before obtaining the weight of each target data, the method further includes:

[0021] If the target problem quality sheet includes multiple pieces of problem description information including interception test unit item descriptions, the weight of the target data is determined according to the bill of lading time of the problem description information corresponding to the target data, wherein the target problem quality sheet is the problem quality sheet including the problem description information corresponding to the target data;

[0022] Otherwise, the weight of the target data is determined according to a preset weight value.

[0023] In the above technical solution, before obtaining the weight of each target data, the target data's weight is determined based on the bill of lading time of the corresponding problem description information, if the target problem quality sheet contains multiple problem description information containing interception test unit item descriptions. This can reflect the impact of time sequence on the problem expression weight. For situations where there are not multiple such problem description information, the weight is determined by a preset weight value. This solution combines the two weight determination methods of time factor and rule setting, improving the flexibility and rationality of target data weight setting, helping to improve the accuracy of fault probability assessment and further enhance the reliability and judgment effect of fault component location.

[0024] In a possible implementation, determining the weight of the target data according to the bill of lading time of the problem description information corresponding to the target data includes:

[0025] When the bill of lading time of the problem description information corresponding to the target data is in the first time interval, a preset first weight total value is allocated according to the number of problem description information containing the interception test unit item description in the first time interval to obtain the weight of the target data, wherein the first time interval is a time interval less than a set time length from the target time, and the target time is the latest bill of lading time in the problem description information containing the interception test unit item description in the target problem quality order.

[0026] In the above technical solution, the bill of lading time of the problem description information corresponding to the target data is compared with the target time to determine whether it falls within the first time interval. Within this time interval, the preset first weight total value is allocated based on the number of problem description information containing interception test unit item descriptions to determine the weight of each target data. This solution can give greater importance to problem description information with bill of lading times closer to the target time in weight allocation, thereby more effectively reflecting the reference value of recent problem records in fault location, improving the sensitivity and rationality of fault probability assessment to the time dimension, and further enhancing the accuracy and timeliness of faulty component identification.

[0027] In a possible implementation, determining the weight of the target data according to the bill of lading time of the problem description information corresponding to the target data includes:

[0028] When the bill of lading time of the problem description information corresponding to the target data is in the second time interval, if the ranking of the bill of lading time of the problem description information corresponding to the target data in the second time interval is greater than the set ranking threshold, the weight of the corresponding target data is reset to zero, wherein the second time interval is a time interval greater than the set time distance from the target time, and the target time is the latest bill of lading time in the problem description information containing the interception test unit item description in the target problem quality list.

[0029] In the above technical solution, the bill of lading time of the problem description information corresponding to the target data is compared with the target time to determine whether it is in the second time interval, that is, the time interval with a distance from the target time greater than a set time. If it is within this interval, and its time ranking in the second time interval exceeds the set ranking threshold, the weight of the target data is reset to zero. Through the time ranking mechanism, this solution screens out historical problem description information that is older, may have expired, or has low reference value, preventing it from interfering with the fault probability assessment, thereby effectively improving the accuracy of weight allocation and further enhancing the timeliness, reliability, and stability of the results during the fault location process.

[0030] In one possible implementation, determining the failure probability of each faulty component type according to the first cumulative value of the target data corresponding to each faulty component type and the second cumulative value of all the target data includes:

[0031] The ratio of the first cumulative value of the target data corresponding to each of the faulty component types to the second cumulative values ​​of all of the target data is calculated to obtain the failure probability of each of the faulty component types.

[0032] In the above technical solution, the failure probability of each faulty component type is obtained by calculating the ratio of the first cumulative value of the target data corresponding to each faulty component type to the second cumulative value of all target data. This makes the calculation method of the failure probability clear and quantifiable, and can accurately reflect the relative occurrence frequency of various types of faulty components in historical problem description information, thereby improving the scientificity and accuracy of the fault probability assessment, providing a reliable basis for the subsequent determination of the faulty component type, and further improving the accuracy and credibility of the fault location results.

[0033] In one possible implementation, determining the type of the faulty component of the device to be detected according to the failure probability of each type of the faulty component includes:

[0034] According to the failure probability of each of the faulty component types, determining the faulty component type having the failure probability greater than a preset probability threshold as the faulty component type of the device to be detected;

[0035] Alternatively, according to the failure probability of each of the faulty component types, the faulty component type with a preset sorting threshold before the failure probability sorting is determined as the faulty component type of the device to be detected.

[0036] In the above technical solution, by screening out the fault component types with a fault probability greater than a preset probability threshold according to the failure probability of each fault component type, or screening out the fault component types with a fault probability ranking before the preset sorting threshold, as the fault component types of the equipment to be detected, a flexible decision-making strategy based on probability threshold control or sorting priority can be implemented, which can not only ensure the accuracy of the fault judgment results, but also adjust the output range according to actual needs, thereby improving the controllability and adaptability of the fault location results, and further enhancing the practicality and intelligence level of the fault diagnosis system.

[0037] In a possible implementation, when the number of problem description information corresponding to the target model is less than a preset number, a prompt message is generated or a fault location entry process is triggered.

[0038] In the above technical solution, when the number of problem description information corresponding to the target model is less than the preset number, a prompt message is generated or the fault location entry process is triggered, which helps to timely prompt data sparsity risks when historical data is insufficient, or guide the supplementation of relevant problem description information, thereby ensuring the basic data quality for subsequent fault probability calculation and fault location, improving the robustness and adaptability of the method, avoiding judgment bias caused by insufficient samples, and further improving the accuracy of fault location and the stability of the system.

[0039] In a second aspect, an embodiment of the present application provides a fault location device, comprising:

[0040] A first acquisition module is configured to acquire a target identifier and a target model, wherein the target identifier is a test unit item identifier of a device to be detected, and the target model is a model of the device to be detected;

[0041] a second acquisition module, configured to acquire target data from a target data set according to the target identifier and the target model, the target data set including at least one target data, each target data including the target identifier, the target model, and the faulty component type, the target identifier, the target model, and the faulty component type of the same target data being acquired based on the same problem description information, each problem description information including description information of a test unit item identifier, a model, and a faulty component type;

[0042] a failure probability determination module, configured to determine the failure probability of each of the faulty component types based on the first cumulative value of the target data corresponding to each of the faulty component types and the second cumulative value of all of the target data;

[0043] The fault component determination module is used to determine the fault component type of the device to be detected according to the failure probability of each fault component type.

[0044] In a third aspect, an embodiment of the present application provides a computing device comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any of the above methods.

[0045] In a fourth aspect, a computer-readable storage medium stores a computer program / instruction thereon, which implements the steps of any of the above-mentioned methods when executed by a processor.

[0046] In a fifth aspect, a computer program product includes a computer program / instruction, characterized in that the computer program / instruction implements the steps of any of the above-mentioned methods when executed by a processor.

[0047] It is to be understood that both the foregoing general description and the following detailed description are exemplary, and are intended to provide further explanation of the technology as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The above and other purposes, features, and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0049] Figure 1It is a schematic diagram illustrating an implementation environment of an embodiment of the present application.

[0050] Figure 2 FIG. 1 is a flowchart illustrating a fault location method according to an embodiment of the present application.

[0051] Figure 3 is a flowchart illustrating generation of a target data set in a fault location method according to an embodiment of the present application;

[0052] Figure 4 is another flowchart illustrating generating a target data set in a fault location method according to an embodiment of the present application;

[0053] Figure 5 is a flowchart illustrating a method for determining a weight in accordance with an embodiment of the present application;

[0054] Figure 6 is a sub-flowchart illustrating a fault location method according to an embodiment of the present application;

[0055] Figure 7 is a schematic diagram illustrating the fault location probability in the fault location method according to an embodiment of the present application;

[0056] Figure 8 is a block diagram illustrating a fault location device according to an embodiment of the present application;

[0057] Figure 9 is a schematic diagram illustrating a computer program product according to an embodiment of the present application;

[0058] Figure 10 is a hardware block diagram illustrating a computing device according to an embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of this application more apparent, the following exemplary embodiments of this application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this application, rather than all the embodiments of this application, and it should be understood that this application is not limited to the exemplary embodiments described herein.

[0060] See also Figure 1 , Figure 11 is a schematic diagram of an implementation environment provided by an embodiment of the present application. The implementation environment includes a terminal device 101 and a server 102, wherein the terminal device 101 communicates with the server 102 via a network 103, wherein the communication network uses standard communication technology and / or protocol, typically the Internet, but can also be any network, including but not limited to any combination of Bluetooth, local area network (LAN), metropolitan area network (MAN), wide area network (WAN), mobile, private network or virtual private network. The terminal device 101 may include but not limited to mobile phones, tablet computers, desktop computers, laptop computers, PDAs, smart TVs, etc. The server 102 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, and big data and artificial intelligence platforms.

[0061] The terminal device 101 or the server 102 may be installed with a computer program / instruction, which, when executed by a processor, implements the steps of the fault location method in the above-mentioned embodiment of the present application.

[0062] The following describes the relevant terms in the embodiments of this application:

[0063] Text similarity: refers to the comparison of the similarity or degree of similarity between two or more texts using mathematical or computer algorithms.

[0064] Regular expression: A pattern-matching syntax for processing strings. Regular expressions consist of characters and operators that describe complex character sequences that need to be matched when searching text.

[0065] Expert experience library: refers to a system or platform that integrates professional knowledge and experience, which can be used to support business scenarios such as decision-making, problem solving, and training.

[0066] Quality Problem Ticket: A fault reporting management system that reports fault phenomena, repair results, replacement parts and other information for each product.

[0067] Device SN: The unique serial number of a product, used to identify the product identity code.

[0068] TU (Test Unit): A single test unit item in product functional testing, one item is a test unit.

[0069] See also Figure 2, an embodiment of the present application provides a fault location method, including:

[0070] S201 , obtaining a target identifier and a target model, where the target identifier is a test unit item identifier of a device to be tested, and the target model is a model of the device to be tested.

[0071] In this step, the target identifier and target model can be the test unit item identifier and model of the device to be tested for fault location input by the user, or can be generated according to certain rules by a system executing a fault location method in an embodiment of the present application, which is not limited in this embodiment of the present application.

[0072] S202, according to the target identifier and target model, obtain target data from the target data set, the target data set includes at least one target data, each target data includes a target identifier, a target model and a faulty component type, the target identifier, target model and faulty component type of the same target data are obtained based on the same problem description information, and each problem description information includes description information of the test unit item identifier, model and faulty component type.

[0073] In this step, based on the target identifier and target model, the target data corresponding to the target identifier and target model is retrieved from the target dataset. In other words, the target data containing the target identifier and target model is retrieved from the target dataset. This step obtains the target data for all target models and target identifiers.

[0074] S203 , determining the failure probability of each faulty component type according to the first cumulative value of the target data corresponding to each faulty component type and the second cumulative value of all target data.

[0075] In this step, the first cumulative value can be the cumulative value or weighted cumulative value of the number of target data items corresponding to the corresponding faulty component type, and the second cumulative value can be the cumulative value or weighted cumulative value of the number of all target data items. It should be understood that the first cumulative value and the second cumulative value are for the test unit item identifier of the same model and the same identifier.

[0076] S204: Determine the type of the faulty component of the device to be detected according to the failure probability of each faulty component type.

[0077] The embodiment of the present application utilizes the target identifier and target model to obtain target data from the target data set based on the test unit item identifier, model and fault component type description information in the problem description information. This can effectively combine the fault location recorded in the historical problem description information to determine the failure probability of each fault component type, ensure the accuracy of the failure probability, and then accurately locate the fault component type, thereby improving the efficiency and accuracy of fault location.

[0078] In an embodiment of the present application, the target dataset can be pre-constructed based on problem description information, which can be extracted from maintenance record data such as quality problem tickets. For example, problem description information can be obtained from maintenance record data for a preset period of time, and the target dataset can be constructed based on the problem description information.

[0079] In the embodiment of the present application, the problem description information can be presented in various forms. For example, the problem description information can be presented in the form of a quality problem sheet. See Table 1, which is a quality problem sheet that includes a problem sheet number and problem description information.

[0080] Table 1

[0081]

[0082] During the automated testing process of the equipment, such as whole-machine testing and functional testing, when the system is executing each test unit item, if an anomaly or error is detected, the system will automatically record the corresponding test unit item identification. This identification has a standard format and can accurately locate the specific link where the test failed. However, in the subsequent maintenance process, due to the different recording habits of maintenance personnel, the fault phenomena or test information they describe when filling out the quality problem sheet are usually more casual. Although they may involve the content of relevant test unit items, they often do not use the standard test unit item identification format. The problem caused by this is that it is difficult for the system to accurately identify the test unit items mentioned in the maintenance record, which in turn affects the accuracy and consistency of the structured processing of fault data and the subsequent fault location work.

[0083] Specifically, since the test information contained in the quality problem sheet filled out by maintenance personnel may be inconsistent with the standard test unit item identification in terms of expression, such as missing prefixes, abbreviations, spelling differences, etc., it is difficult to directly make a one-to-one correspondence.

[0084] In one embodiment, the target identifier in the target data is an identifier extracted from the test unit item identifier library of the target model when there is description information matching the text format of the test unit item identifier in the problem description information, and the identifier has a text similarity with the description information greater than a preset threshold; the target model and faulty component type in the target data are obtained based on the description information of the problem description information.

[0085] By identifying descriptions from the problem description that match the text format of the test unit item identifiers, and then extracting identifiers from the target model's test unit item identifier library with a text similarity greater than a preset threshold as target identifiers, this effectively overcomes the problem of non-standard and confusing test unit item identifiers in the problem descriptions. This solution combines text format matching with text similarity matching to improve the accuracy and matching efficiency of target identifier extraction, thereby enhancing the quality of the target data and the accuracy of the fault probability determined based on this target data, ultimately strengthening the effectiveness of fault location.

[0086] Accordingly, see Figure 3 , generate the target database, including:

[0087] S301, obtaining description information in the problem description information that matches the text format of the test unit item identifier.

[0088] S302 : extracting an identifier whose similarity to the description information text is greater than a preset threshold from the test unit item identifier library of the target model as a target identifier.

[0089] S303: Obtain the target machine model and the type of the faulty component from the problem description information.

[0090] S304: Generate a target database based on the target identifier, target machine model, and fault component type.

[0091] In the embodiment of the present application, text format matching can adopt regular expression matching and other related text format matching methods. The description information is obtained by using the text format matching method, and then the identifier with a text similarity with the description information greater than a preset threshold is extracted from the test unit item identifier library as the target identifier. Among them, the preset threshold can be set according to demand, for example, 90%. The test unit item identifier library in the embodiment of the present application stores standard test unit item identifiers, which can be generated based on historical test records, or historical test records can be used as the test unit item identifier library.

[0092] In one example, since the problem description information is usually unstructured natural language text, its content forms are diverse, and there are abbreviations, additional notes or inconsistent formats, it is very challenging to directly match or compare them. Therefore, in this example, a set of regular expressions for matching test unit item identifiers is preset. The regular expressions can be constructed according to the structural features of the test unit item identifier in the naming rules (for example, containing specific prefixes "TU", "TST", "ITEM", numbering formats, keywords, etc.), and are used to automatically identify and extract descriptive information that may be related to the test and matches the text format of the test unit item identifier in the problem description information.

[0093] The description information extracted through regular expression matching is then used to calculate similarity with standard test item identifiers. This approach automatically extracts test information from unstructured descriptions without human intervention, improving the accuracy and automation of information processing and providing high-quality input for data association and modeling during fault location.

[0094] The system has pre-set regular expressions or other text format matching rules for identifying test unit item identifiers (for example, matching strings ending in key formats such as _test, Fail, and burn_). These rules automatically extract keywords or fields from the problem description that may correspond to test unit items and use them as description information that matches the text format of the test unit item identifier. For example, the content beginning with "memory" in the problem description of problem ticket number 00002 in Table 1.

[0095] The steps realize the structured extraction of unstructured problem description information, convert the test-related content implicit in the free text into identification information that can be analyzed later, and improve the automation and accuracy of information processing.

[0096] For example, see Figure 4 , get the description information that matches the text format of the test unit item identifier, which can include:

[0097] S401, obtain quality problem list.

[0098] In this step, the system receives or retrieves the quality problem sheet submitted by the maintenance personnel. The quality problem sheet may include equipment identification, problem description information, maintenance time, etc. The problem description information usually records user feedback, test phenomena or maintenance conclusions in the form of natural language text.

[0099] S402, regular expression matching.

[0100] In this step, the system parses and matches the problem description information in the quality issue ticket based on a pre-set regular expression for identifying test unit item identifiers. The automatic recognition of regular expressions can extract structured keywords from unstructured natural language, enabling unified parsing of non-standard repair descriptions and effectively improving the efficiency and accuracy of information extraction.

[0101] S403: Obtain a test unit item identifier matching result, and obtain description information that matches the text format of the test unit item identifier.

[0102] Through this step, the ambiguous or variant information in the original text description can be extracted to provide support for subsequent data matching.

[0103] Based on the device model information, the system searches the historical test database for test failure records for that model. This query includes all standard test unit item identifiers recorded due to historical test failures. In other words, the historical test database is a library of test unit item identifiers. This step limits the query scope to filter data only for the target model, ensuring that the historical test items used in subsequent similarity calculations are highly targeted and comparable, and preventing the introduction of data unrelated to the target model that may interfere with the analysis results.

[0104] For example, see Figure 4 , extract the identification from the target model's test unit item identification library, whose similarity with the description information text is greater than a preset threshold, as the target identification. This includes:

[0105] S404, obtaining the whole device test result.

[0106] In this step, the system obtains the test result data of the target device from the whole machine automated test platform.

[0107] S405: Obtain the test failed TU item.

[0108] In this step, the system traverses the entire device test results and filters out test unit items with a test result of "Fail". Each failed test item corresponds to an abnormal performance of the device in a specific function, module or subsystem.

[0109] S406, remove the version number from the TU item.

[0110] In this step, the system normalizes the failed TU items obtained, mainly including removing the test version number information contained in the test item identifier. The TU item after removing the version number can be used as the TU item in the test unit item identifier library.

[0111] In this step, the system calculates the text similarity between the test unit item identifier and each standard test unit item identifier in the historical test failure record. The similarity calculation can be implemented using algorithms such as edit distance, cosine similarity, and word vector model. If the similarity value between a historical test unit item identifier and a suspected test unit item identifier is greater than or equal to a preset threshold (for example, set to 0.9), the historical identifier is identified as a matching target and used as the target identifier. This step solves the problem that non-standardized identifiers in maintenance description information cannot be directly compared through a similarity matching mechanism. Test items that are semantically or spelled similarly can be identified to improve the matching accuracy between problem descriptions and historical data.

[0112] S407, text familiarity detection.

[0113] In this step, the system compares the textual similarity between the description extracted from the problem description and the standard test unit item identifiers in the test unit item identifier library for the target model. Similarity can be calculated using methods such as edit distance, cosine similarity, or character-level or word-level embedding models.

[0114] S408, determining whether the similarity is greater than 90%, if it is greater than 90%, executing step S409, otherwise executing step 410.

[0115] The system compares the results and makes a judgment. If the similarity value is greater than the set threshold (such as 90%), it is considered that there is a high degree of consistency between the suspected test unit item identifier and the historical standard identifier, and subsequent TU extraction processing is performed; otherwise, the exception handling process is entered.

[0116] S409, TU extraction.

[0117] In this step, the system identifies the corresponding standard test unit items in the matching results with a similarity greater than 90% as the final extracted test unit items (TU), and uses them to construct the target dataset or perform subsequent weight calculations.

[0118] S410, TU extraction is empty.

[0119] In this step, because the text similarity is lower than the threshold, the system fails to extract a valid TU identifier, and the system records the extraction result as empty, or triggers a prompt message for manual confirmation or log annotation.

[0120] Based on the extracted TU, a data base table can be obtained, which is also a type of target data set.

[0121] Based on the matched target identifiers, we further extract records associated with these identifiers from the problem description, including the corresponding target aircraft model and faulty component type, and generate a target dataset. Each target data entry typically contains the following fields: aircraft model, identifier, and faulty component type.

[0122] In one example, before determining the failure probability of each faulty component type based on the first cumulative value of the target data corresponding to each faulty component type and the second cumulative value of all target data, the method further includes: obtaining a weight of each target data;

[0123] A first cumulative value is determined based on the weighted sum of the target data corresponding to each faulty component.

[0124] Before determining the fault probability based on the first cumulative value of the target data corresponding to each faulty component type and the second cumulative value of all target data, the weight of the target data is further introduced. By obtaining the weight of each target data and determining the first cumulative value based on the sum of the weights of the target data corresponding to each faulty component type, and determining the second cumulative value based on the sum of the weights of all target data, the calculation process of the fault probability can comprehensively consider the importance or credibility of different target data, thereby improving the rationality and accuracy of the fault probability assessment results, and further improving the accuracy and reliability of fault location.

[0125] Specifically, each target data item in the target dataset can be weighted. The faulty component, target aircraft model, and target test unit contained in each target data item jointly determine its weight in the overall failure probability calculation. For the same faulty component under the same aircraft model and test unit, the corresponding weights are summed to form the cumulative weight of the component under that aircraft model and test unit.

[0126] Furthermore, based on the target model and target test unit item, the weighted values ​​of all faulty components under the test item are counted respectively, and the component failure probability of each faulty component is calculated accordingly. The probability can be defined as the ratio of the cumulative weight value of the component to the total weight of all faulty components under the test unit item.

[0127] For example:

[0128] If the target dataset contains several data records for faulty component X for model A and test unit item TU1, with weights of 0.3, 0.5, and 0.2, then the total weight of component X is 1.0, meaning the first cumulative value is 1.0. If the sum of the weights of all faulty components under TU1 is 2.0, meaning the second cumulative value is 2.0, then the failure probability of component X is 1.0 / 2.0 = 0.5.

[0129] Through the above method, the system can integrate the frequency and weight information of each component failure in the historical data to achieve more accurate and reliable fault probability modeling, thereby effectively improving the fault location capability at the component level.

[0130] In one example, before obtaining the weight of each target data, the method further includes:

[0131] If the target problem quality sheet contains multiple problem description information containing interception test unit item descriptions, the weight of the target data is determined according to the bill of lading time of the problem description information corresponding to the target data, wherein the target problem quality sheet is the problem quality sheet containing the problem description information corresponding to the target data;

[0132] Otherwise, the weight of the target data is determined according to the preset weight value.

[0133] Before obtaining the weight of each target data point, if the target problem quality sheet contains multiple problem descriptions containing interception test unit item descriptions, the target data's weight is determined based on the billing date of the corresponding problem description information, reflecting the impact of time sequence on the problem expression weight. If the sheet does not contain multiple such problem descriptions, the weight is determined using a preset weight value. This solution combines the two weight determination methods of time factor and rule setting to enhance the flexibility and rationality of target data weight setting, help improve the accuracy of fault probability assessment, and further enhance the reliability and judgment effect of faulty component location.

[0134] In one example, the weight of the target data is determined based on the bill of lading time of the problem description information corresponding to the target data, including:

[0135] When the bill of lading time of the problem description information corresponding to the target data is in the first time interval, a preset first weight total value is allocated according to the number of problem description information containing the interception test unit item description in the first time interval to obtain the weight of the target data, wherein the first time interval is a time interval less than the set time length from the target time, and the target time is the latest bill of lading time in the problem description information containing the interception test unit item description in the target problem quality order.

[0136] In the above technical solution, the bill of lading time of the problem description information corresponding to the target data is compared with the target time to determine whether it falls within the first time interval. Within this time interval, the preset first weight total value is allocated based on the number of problem description information containing interception test unit item descriptions to determine the weight of each target data. This solution can give greater importance to problem description information with bill of lading times closer to the target time in weight allocation, thereby more effectively reflecting the reference value of recent problem records in fault location, improving the sensitivity and rationality of fault probability assessment to the time dimension, and further enhancing the accuracy and timeliness of faulty component identification.

[0137] In one example, the weight of the target data is determined based on the bill of lading time of the problem description information corresponding to the target data, including:

[0138] When the bill of lading time of the problem description information corresponding to the target data is in the second time interval, if the ranking of the bill of lading time of the problem description information corresponding to the target data in the second time interval is greater than the set ranking threshold, the weight of the corresponding target data is reset to zero, wherein the second time interval is a time interval greater than the set time distance from the target time, and the target time is the latest bill of lading time in the problem description information containing the interception test unit item description in the target problem quality list. When the ranking exceeds the set value, the target data is in the area.

[0139] By comparing the billing time of the problem description information corresponding to the target data with the target time, it is determined whether it is in the second time interval, that is, the time interval that is greater than the set time length from the target time. If it is in this interval, and its time ranking in the second time interval exceeds the set ranking threshold, the weight of the target data is reset to zero. This solution uses a time sorting mechanism to screen out historical problem description information that is earlier, may have expired, or has low reference value, to avoid interference with the fault probability assessment, thereby effectively improving the accuracy of weight allocation and further improving the timeliness, reliability and stability of the results in the fault location process. In one example, when there is only one problem description information for the same problem quality order, and it contains an interception test unit item description, the weight of the corresponding target data is set to a first preset value; when there is only one problem description information for the same problem quality order, and it does not contain an interception test unit item description, the weight of the corresponding target identifier is set to a second preset value; wherein the first preset value is greater than the second preset value.

[0140] Among them, "intercepted test unit item description" refers to the problem description information that explicitly mentions the abnormality, failure or interruption of a specific test unit item during the test process, which is usually more targeted and indicative. Since some devices may only be associated with one problem description information in the entire test process, in order to improve the judgment and value assessment of this single data in fault modeling, this example distinguishes its importance based on whether the description information contains a clear description of the test behavior. When the problem description contains interception or abnormal information of the test unit item, it indicates that it has a strong positioning reference significance for the target identification, so it is given a higher weight (first preset value); on the contrary, if the description content is relatively vague or only generally states the fault phenomenon, it is given a relatively low weight (second preset value). Through this differentiated weighting mechanism, the ability to identify high-quality descriptive information in the data mining stage can be effectively improved, and the credibility and accuracy of the fault probability calculation results can be enhanced. The first preset value and the second preset value can be set according to needs, for example, the first preset value is set to 1 and the second preset value is set to 0.5.

[0141] In one example, when there are more than one problem description information for the same problem quality sheet, and only one of them contains the interception test unit item description, the weight is set to the first preset value, and the remaining weights are 0.

[0142] During actual maintenance, a particular device or test unit item may be associated with multiple problem descriptions. These descriptions may originate from multiple rounds of maintenance records, completed by multiple personnel, and may vary in quality. To avoid duplicate weighting or erroneous interference, this example introduces an exclusive weighting strategy to enhance the utilization of information with clear test behavior descriptions.

[0143] When only one problem description message contains content related to the interception test unit item, it indicates that this information is the description most relevant to the actual test behavior, so its corresponding target data is given a complete first preset value weight; the remaining information that does not contain such a description is considered redundant or has no reference value, and the corresponding weight is set to 0 to avoid noise data from interfering with the overall analysis results.

[0144] This strategy improves the accuracy and discrimination ability of weight allocation, effectively strengthens the role of information screening in sample construction, and thus improves the accuracy and stability of subsequent component failure probability calculations.

[0145] In one example, if there are more than one problem description information for the same problem quality ticket, and at least two of them contain intercepted test unit item descriptions, then:

[0146] In the corresponding problem description information containing the interception test unit item description after the first target time, the weight of the target data corresponding to the corresponding problem description information is set to an average value of the first preset value;

[0147] In the problem description information containing the interception test unit item description before the first target time, the target data weight corresponding to the latest corresponding problem description information is set to a first preset value;

[0148] The first target time is a preset duration before the last time point in all the problem description information.

[0149] When multiple problem descriptions contain intercept test unit descriptions, simply selecting one or assigning an equal weight can easily lead to insufficient information utilization or weight imbalance. This example introduces a time window mechanism for segmented weighting: all problem descriptions are divided into two stages in chronological order: before and after the "first target time".

[0150] For the description of "after the first target time", because it is relatively new and may reflect recent test behaviors or newly discovered problems, the first preset value is evenly distributed to these multiple records, so that these data can obtain relatively stable representativeness in the model.

[0151] For the descriptions “before the first target time”, only the latest information is retained and given full weight, aiming to ensure that the most valuable single description in history is retained, while suppressing the adverse effects of earlier, potentially duplicated or redundant information on the results.

[0152] This strategy fully combines time factors and content quality, realizes the differentiated use of multiple valid test descriptions, improves the rationality of weight distribution and the timeliness of data modeling, and helps to improve the accuracy of fault probability assessment and model robustness.

[0153] In an example, if there are more than one problem description information for the same problem quality ticket and no intercept test unit item description is included, then:

[0154] In the problem description information after the second target time, the weight of the target data corresponding to the corresponding problem description information is set to the average value of the second preset value;

[0155] In the problem description information before the second target time, the target data weight corresponding to the latest corresponding problem description information is set to a second preset value;

[0156] The second target time is a preset duration before the last time point in all the problem description information.

[0157] Even in the absence of structured test behavior information, effective screening and reasonable weighting can still be achieved based on the time distribution law of information, thereby improving the robustness and adaptability of the fault probability model in weak feature data scenarios.

[0158] In one embodiment, determining the failure probability of each faulty component type based on the first cumulative value of the target data corresponding to each faulty component type and the second cumulative value of all target data includes:

[0159] The ratio of the first cumulative value of the target data corresponding to each faulty component type to the second cumulative value of all target data is calculated to obtain the failure probability of each faulty component type.

[0160] The ratio of the first cumulative value to the second cumulative value of the target data corresponding to each faulty component type is used as the failure probability of each faulty component type.

[0161] In the above technical solution, the failure probability of each faulty component type is obtained by calculating the ratio of the first cumulative value of the target data corresponding to each faulty component type to the second cumulative value of all target data. This makes the calculation method of the failure probability clear and quantifiable, and can accurately reflect the relative occurrence frequency of various types of faulty components in historical problem description information, thereby improving the scientificity and accuracy of the fault probability assessment, providing a reliable basis for the subsequent determination of the faulty component type, and further improving the accuracy and credibility of the fault location results.

[0162] In one embodiment, determining the type of the faulty component of the device to be detected based on the failure probability of each faulty component type includes:

[0163] According to the failure probability of each fault component type, a fault component type having a failure probability greater than a preset probability threshold is determined as the fault component type of the device to be detected.

[0164] By using faulty component types with a probability greater than a preset probability threshold, some high-probability faulty component types can be eliminated, improving the accuracy of fault location. It should be understood that in actual applications, all probabilistic faulty component types can be located as faulty components, and the names and probabilities of all faulty component types can be displayed.

[0165] The preset probability threshold can be set according to needs, for example, 30%, 20%, or 50%.

[0166] In one embodiment, determining the type of the faulty component of the device to be detected based on the failure probability of each faulty component type includes:

[0167] According to the failure probability of each fault component type, the fault component type with a preset sorting threshold before the failure probability sorting is determined as the fault component type of the device to be detected.

[0168] The preset sorting threshold can be set according to needs, for example, 2 or 3.

[0169] By screening out faulty component types with a fault probability greater than a preset probability threshold, or screening out faulty component types with a fault probability ranking before a preset ranking threshold, based on the fault probability of each faulty component type, as the faulty component types of the equipment to be detected, a flexible decision-making strategy based on probability threshold control or ranking priority can be implemented, which can not only ensure the accuracy of the fault judgment result, but also adjust the output range according to actual needs, thereby improving the controllability and adaptability of the fault location result, and further enhancing the practicality and intelligence level of the fault diagnosis system. In a specific example, see Figure 5 Taking the number of problem descriptions in a quality problem sheet as an example, the weights are determined according to the following steps.

[0170] S501, determine whether the number of problem description information is greater than 1, if not, execute step S502, if yes, execute S503;

[0171] S502, determining whether the number of problem description information items including interception test unit item descriptions is equal to 1, if so, assigning a weight value of 1, otherwise, assigning a weight value of 0.5.

[0172] S503: Determine whether the number of problem descriptions containing interception test unit item descriptions is 0. If not, proceed to step S504. If so, assign an average weight of 0.5 to each item whose "bill of lading time" differs from the last item by less than 2 hours. For each item whose "bill of lading time" differs from the last item by more than 2 hours, assign a weight of 0.5 to the last item. The weights of all other items are set to 0.

[0173] S504, determine whether the number of problem description information items including the intercepted test unit item description is equal to 1, if not, execute S505, if yes, assign a weight of 1 to the problem description information of the intercepted test unit item description.

[0174] S505: If the number of problem descriptions containing interception test unit item descriptions is greater than one, the items whose difference with the last "bill of lading time" is within 2 hours are assigned an average weight of 1. For items whose difference with the last "bill of lading time" is greater than 2 hours, the last item is assigned a weight of 1. The weights of all other items are set to 0.

[0175] The decision tree model calculates weights and generates the component failure probability for the corresponding aircraft model and faulty TU. Because there are multiple maintenance scenarios, from a business perspective, previous maintenance attempts are misjudgments, so a time constraint is introduced. Based on a 2-hour difference in "bill of lading time," identical data within 2 hours will no longer be collected.

[0176] In one example, when the number of problem description information corresponding to the target model is less than a preset number, a prompt message is generated or a fault location entry process is triggered.

[0177] The above 0.5, 1 and 2h are all set values ​​and can be set according to actual needs.

[0178] For example, see Figure 6 , the method further comprises:

[0179] S601, determine whether the maintenance record is greater than X, if so, execute step S605, if not, execute step S602;

[0180] S602, determine whether there is expert experience, if yes, execute step S603, if not, execute step S604;

[0181] S603, expert experience results, does not reflect probability data;

[0182] S604, reminder for maintenance;

[0183] S605, model calculation results, reflecting probability data.

[0184] In this example, the maintenance record contains the problem description. X is a preset value set according to requirements, such as 10. For models with fewer than 10 pieces of fault maintenance data corresponding to the input device SN and fault TU (same model, same TU, same fault type), fault location is performed based on expert experience.

[0185] The format for entering expert experience is as follows:

[0186] 1.TU name: The name of the fault TU for each test item, which can be obtained in the whole machine test system.

[0187] 2. TU test content: Explanation of the specific test content of the faulty TU and the test commands to be manually executed.

[0188] 3. Component Correlation 1-n: The correlation between each faulty TU and the hardware component. Correlation is arranged in order from highest to lowest, for example, component correlation 1 is the component with the highest correlation.

[0189] The user enters the machine SN (the system can obtain the model) and the fault TU.

[0190] In a specific example, the corresponding model data is queried based on the whole machine SN, and the historical data of the quality problem ticket of the same model is obtained based on the model. The fault TU identifier filled in the quality problem ticket history data is matched according to the regular expression. The text similarity test is performed on the fault TU extracted from the quality problem ticket history data and the fault TU configured in the whole machine test system. The corresponding fault TU data with a text similarity greater than 90 is extracted as the fault data base table of the model, TU, and fault component category. Figure 7 , Figure 7 is the fault location probability obtained according to the fault location method in the embodiment of the present application.

[0191] See also Figure 8 , an embodiment of the present application provides a fault location device, comprising:

[0192] The first acquisition module 801 acquires a target identifier and a target model, where the target identifier is a test unit item identifier of the device to be tested, and the target model is a model of the device to be tested;

[0193] A second acquisition module 802 acquires target data from a target data set based on the target identifier and the target model. The target data set includes at least one target data, each target data including a target identifier, a target model, and a faulty component type. The target identifier, target model, and faulty component type of the same target data are obtained based on the same problem description information. Each problem description information includes a test unit item identifier, a model, and description information of the faulty component type.

[0194] A failure probability determination module 803 is configured to determine the failure probability of each faulty component type based on the first cumulative value of the target data corresponding to each faulty component type and the second cumulative value of all target data;

[0195] The fault component determination module 804 is configured to determine the fault component type of the device to be detected based on the fault probability of each fault component type.

[0196] In one example, the target identifier, target model, and faulty component type of the same target data are obtained based on the same problem description information, including: when there is description information in the problem description information that matches the text format of the test unit item identifier, the target identifier in the target data is extracted from the test unit item identifier library of the target model, and the similarity with the text of the description information is greater than a preset threshold; the target model and faulty component type in the target data are obtained based on the description information of the problem description information.

[0197] In one example, the fault location device further includes a cumulative value calculation module for obtaining a weight of each target data; determining a first cumulative value based on the sum of the weights of the target data corresponding to each faulty component;

[0198] The weighted sum of all target data is used as the second cumulative value.

[0199] In one example, the fault location device further includes a weight determination module, which is configured to:

[0200] If the target problem quality sheet contains multiple problem description information containing interception test unit item descriptions, the weight of the target data is determined according to the bill of lading time of the problem description information corresponding to the target data, wherein the target problem quality sheet is the problem quality sheet containing the problem description information corresponding to the target data;

[0201] Otherwise, the weight of the target data is determined according to the preset weight value.

[0202] In one example, the weight determination module is used to determine the weight of the target data based on the bill of lading time of the problem description information corresponding to the target data, specifically for:

[0203] When the bill of lading time of the problem description information corresponding to the target data is in the first time interval, a preset first weight total value is allocated according to the number of problem description information containing the interception test unit item description in the first time interval to obtain the weight of the target data, wherein the first time interval is a time interval less than the set time length from the target time, and the target time is the latest bill of lading time in the problem description information containing the interception test unit item description in the target problem quality order.

[0204] In one example, the weight determination module is used to determine the weight of the target data based on the bill of lading time of the problem description information corresponding to the target data, specifically for:

[0205] When the bill of lading time of the problem description information corresponding to the target data is in the second time interval, if the ranking of the bill of lading time of the problem description information corresponding to the target data in the second time interval is greater than the set ranking threshold, the weight of the corresponding target data is reset to zero, wherein the second time interval is a time interval greater than the set time distance from the target time, and the target time is the latest bill of lading time in the problem description information containing the interception test unit item description in the target problem quality list. When the ranking exceeds the set value, the target data is in the area.

[0206] In one example, the failure probability determination module is configured to determine the failure probability of each faulty component type based on the first cumulative value of the target data corresponding to each faulty component type and the second cumulative value of all target data, specifically to:

[0207] The ratio of the first cumulative value of the target data corresponding to each faulty component type to the second cumulative value of all target data is calculated to obtain the failure probability of each faulty component type.

[0208] In one example, the faulty component determination module is configured to determine the faulty component type of the device to be detected based on the failure probability of each faulty component type, specifically to:

[0209] According to the failure probability of each fault component type, a fault component type having a failure probability greater than a preset probability threshold is determined as the fault component type of the device to be detected.

[0210] In one example, the faulty component determination module is configured to determine the faulty component type of the device to be detected based on the failure probability of each faulty component type, specifically to:

[0211] According to the failure probability of each fault component type, the fault component type with a preset sorting threshold before the failure probability sorting is determined as the fault component type of the device to be detected.

[0212] In one example, it also includes an information generation or process triggering module, which is used to generate prompt information or trigger the fault location entry process when the number of problem description information corresponding to the target model is less than a preset number.

[0213] An embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any of the above-mentioned fault location methods.

[0214] An embodiment of the present application further provides a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to execute a method according to an embodiment of the present application.

[0215] refer to Figure 9The embodiment of the present application further provides a computer program product 900, comprising a computer program 901, wherein the computer program, when executed by a processor of a computer, is used to enable the computer to perform a method according to an embodiment of the present application.

[0216] refer to Figure 10 , a block diagram of a computing device 1000 that can serve as a server or client of the present application will now be described, which is an example of a hardware device that can be applied to various aspects of the present application. Electronic equipment is intended to represent various forms of digital electronic computer equipment, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic equipment can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present application described and / or required herein.

[0217] The computing device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a random access memory (RAM) 1003. Various programs and data required for device operation may also be stored in the RAM 1003. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0218] Several components within computing device 1000 are connected to I / O interface 1005, including an input unit 1006, an output unit 1007, a storage unit 1008, and a communication unit 1009. Input unit 1006 can be any type of device capable of inputting information into computing device 1000. Input unit 1006 can receive input numeric or character information and generate key input signals related to user settings and / or function control of the electronic device. Output unit 1007 can be any type of device capable of presenting information and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. Storage unit 1008 may include, but is not limited to, a magnetic disk or an optical disk. Communication unit 1009 allows computing device 1000 to exchange information / data with other devices via computer networks such as the Internet and / or various telecommunication networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver and / or chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0219] The computing unit 1001 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units for running device learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1001 performs the various methods and processes described above. For example, in some embodiments, the method of the embodiment of the present application may be implemented as a computer software program, which is tangibly included in a device-readable medium, such as a storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on the computing device 1000 via ROM 1002 and / or communication unit 1009. In some embodiments, the computing unit 1001 may be configured to perform the method of the embodiment of the present application in any other appropriate manner (e.g., by means of firmware).

[0220] The basic principles of the present application have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this application are merely illustrative and not restrictive, and it should not be assumed that these advantages, strengths, and effects are required of each embodiment of this application. In addition, the specific details disclosed above are merely illustrative and facilitating understanding, and are not restrictive. The above details do not limit this application to necessarily being implemented using the above specific details.

[0221] The block diagrams of the devices, devices, equipment, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0222] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0223] It should also be noted that in the system and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0224] Various changes, substitutions, and modifications of the technology herein may be made without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims herein is not limited to the specific aspects of the processes, apparatus, manufacture, compositions of things, means, methods, and actions described above. Currently existing or later developed processes, apparatus, manufacture, compositions of things, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects herein may be utilized. Accordingly, the appended claims include within their scope such processes, apparatus, manufacture, compositions of things, means, methods, or actions.

[0225] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0226] The above description has been provided for the purpose of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A fault location method, characterized in that: include: Obtain a target identifier and a target model, wherein the target identifier is a test unit item identifier of a device to be detected, and the target model is a model of the device to be detected; Acquire target data from a target data set according to the target identifier and the target model, the target data set including at least one target data, each target data including the target identifier, the target model, and the faulty component type, the target identifier, the target model, and the faulty component type of the same target data being obtained based on the same problem description information, each problem description information including description information of the test unit item identifier, the model, and the faulty component type; determining a failure probability of each of the faulty component types according to a first cumulative value of the target data corresponding to each of the faulty component types and a second cumulative value of all of the target data; The faulty component type of the device to be detected is determined according to the failure probability of each faulty component type.

2. The method according to claim 1, characterized in that The target identifier, target machine model, and fault component type of the same target data are obtained based on the same problem description information, including: The target identifier in the target data is an identifier extracted from the test unit item identifier library of the target model when there is description information matching the text format of the test unit item identifier in the problem description information, and the identifier has a text similarity with the description information greater than a preset threshold; The target machine model and the faulty component type in the target data are obtained according to the description information of the problem description information.

3. A fault location method according to claim 1, characterized in that: Before determining the failure probability of each faulty component type based on the first cumulative value of the target data corresponding to each faulty component type and the second cumulative value of all the target data, the method further includes: Obtaining a weight for each target data; determining the first cumulative value based on a weighted sum of the target data corresponding to each of the faulty components; The weighted sum of all the target data is used as the second cumulative value.

4. A fault location method according to claim 1, characterized in that: Before obtaining each of the preset weight values ​​and determining, the method further includes: If the target problem quality sheet includes multiple pieces of problem description information including interception test unit item descriptions, the weight of the target data is determined according to the bill of lading time of the problem description information corresponding to the target data, wherein the target problem quality sheet is the problem quality sheet including the problem description information corresponding to the target data; Otherwise, the weight of the target data is determined according to a preset weight value.

5. A fault location method according to claim 4, characterized in that: Determining the weight of the target data according to the bill of lading time of the problem description information corresponding to the target data includes: When the bill of lading time of the problem description information corresponding to the target data is in the first time interval, a preset first weight total value is allocated according to the number of problem description information containing the interception test unit item description in the first time interval to obtain the weight of the target data, wherein the first time interval is a time interval less than a set time length from the target time, and the target time is the latest bill of lading time in the problem description information containing the interception test unit item description in the target problem quality order.

6. A fault location method according to claim 4, characterized in that: Determining the weight of the target data according to the bill of lading time of the problem description information corresponding to the target data includes: When the bill of lading time of the problem description information corresponding to the target data is in the second time interval, if the ranking of the bill of lading time of the problem description information corresponding to the target data in the second time interval is greater than the set ranking threshold, the weight of the corresponding target data is reset to zero, wherein the second time interval is a time interval greater than the set time distance from the target time, and the target time is the latest bill of lading time in the problem description information containing the interception test unit item description in the target problem quality list.

7. A fault location method according to claim 1, characterized in that: Determining the failure probability of each faulty component type according to the first cumulative value of the target data corresponding to each faulty component type and the second cumulative value of all the target data includes: The ratio of the first cumulative value of the target data corresponding to each of the faulty component types to the second cumulative values ​​of all of the target data is calculated to obtain the failure probability of each of the faulty component types.

8. A fault location method according to claim 1, characterized in that: The determining the type of the faulty component of the device to be detected according to the failure probability of each type of the faulty component includes: According to the failure probability of each of the faulty component types, determining the faulty component type having the failure probability greater than a preset probability threshold as the faulty component type of the device to be detected; Alternatively, according to the failure probability of each of the faulty component types, the faulty component type with a preset sorting threshold before the failure probability sorting is determined as the faulty component type of the device to be detected.

9. The method according to claim 1, characterized in that When the number of the problem description information corresponding to the target model is less than a preset number, a prompt message is generated or a fault location entry process is triggered.

10. A computing device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the steps of any one of claims 1 to 9.

Images