A functional diagnosis method, device, equipment and storage medium
By acquiring fault diagnostic codes and functional clustering, the target application interface and functional category are determined, enabling efficient and reliable diagnosis and elimination of automotive functional faults, thus solving the problem of incomplete fault diagnosis in existing technologies.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA FAW CO LTD
- Filing Date
- 2022-11-07
- Publication Date
- 2026-06-26
AI Technical Summary
When diagnosing functional faults, automotive designers often find it difficult to achieve a comprehensive functional fault diagnosis using diagnostic codes, resulting in incomplete troubleshooting and low efficiency.
By obtaining fault diagnostic codes, identifying target records, matching target application interfaces, and utilizing functional clustering results to determine functional categories, a comprehensive functional diagnosis can be performed.
It improves the efficiency and reliability of functional fault diagnosis, reduces the possibility of fault recurrence, and enhances the thoroughness of fault elimination.
Smart Images
Figure CN116184976B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data analysis technology, and in particular to a functional diagnostic method, apparatus, device, and storage medium. Background Technology
[0002] In the field of automotive design and development, the creation of a car requires not only functional design before mass production, but also a post-production review of its functionality. Functional malfunctions that occur during user operation are a key concern for automotive designers.
[0003] Currently, automotive designers primarily use the Diagnostic Trouble Codes (DTCs) output by the electronic stability system to determine the cause of a malfunction, and then determine the corresponding Application Program Interface (API) based on the cause of the malfunction to eliminate the functional failure.
[0004] However, analyzing the cause of a fault based on the diagnostic codes places high demands on automotive designers. They need to combine information such as operation logs to analyze functional faults. At the same time, it is difficult to achieve a comprehensive functional fault diagnosis of the vehicle based on the diagnostic codes, and functional faults are difficult to completely eliminate. Summary of the Invention
[0005] This invention provides a functional diagnostic method, apparatus, device, and storage medium to solve the problems of difficulty in diagnosing and analyzing functional faults in automobiles and the difficulty in completely eliminating them. It can improve the efficiency of functional fault diagnosis, increase the reliability of eliminating functional faults, and avoid the recurrence of functional faults.
[0006] According to one aspect of the present invention, a functional diagnostic method is provided, the method comprising:
[0007] If a vehicle malfunction is detected, a fault diagnostic code is obtained, and the target record is determined in the operation log based on the fault diagnostic code.
[0008] Based on the target record, determine the target application interface and the target function that matches the target application interface;
[0009] Based on the pre-defined functional clustering results based on vehicle functions, determine the functional category of the target function;
[0010] Diagnose all functions associated with the aforementioned function category.
[0011] According to another aspect of the present invention, a functional diagnostic device is provided, the device comprising:
[0012] The target record determination module is used to obtain the fault diagnosis code if a vehicle fault is detected, and determine the target record in the operation log based on the fault diagnosis code.
[0013] The target function determination module is used to determine the target application interface based on the target record, and to determine the target function that matches the target application interface.
[0014] The function category determination module is used to determine the function category of the target function based on the function clustering results determined in advance based on vehicle functions;
[0015] The function diagnosis module is used to diagnose all functions associated with the function category.
[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0017] At least one processor; and
[0018] A memory communicatively connected to the at least one processor; wherein,
[0019] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the functional diagnostic method according to any embodiment of the present invention.
[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the functional diagnostic method described in any embodiment of the present invention.
[0021] The technical solution of this invention involves obtaining a fault diagnostic code when a vehicle fault is detected, identifying a target record in the operation log based on the fault diagnostic code, determining the target application interface based on the target record, and identifying the target function matching the target application interface. Then, based on the function clustering results pre-determined based on vehicle functions, the function category of the target function is determined. All functions associated with the function category are then diagnosed. This solution solves the problems of difficult diagnosis and analysis of automotive functional faults and the difficulty in completely eliminating them. It can improve the efficiency of functional fault diagnosis while increasing the reliability of functional fault elimination and preventing the recurrence of functional faults.
[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0024] Figure 1 This is a flowchart of a functional diagnostic method provided according to Embodiment 1 of the present invention;
[0025] Figure 2 This is a flowchart of a functional diagnostic method provided according to Embodiment 2 of the present invention;
[0026] Figure 3 This is a schematic diagram of the structure of a functional diagnostic device according to Embodiment 3 of the present invention;
[0027] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the functional diagnostic method of the present invention. Detailed Implementation
[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. The acquisition, storage, use, and processing of data in the technical solutions of this application all comply with the relevant provisions of national laws and regulations.
[0030] Example 1
[0031] Figure 1This is a flowchart illustrating a functional diagnostic method provided in Embodiment 1 of the present invention. This embodiment is applicable to functional fault diagnosis scenarios in automobiles. The method can be executed by a functional diagnostic device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:
[0032] S110. If a vehicle malfunction is detected, obtain the fault diagnostic code and determine the target record in the operation log based on the fault diagnostic code.
[0033] This solution can be executed by a functional fault analysis system, which can be used to detect, diagnose, and eliminate functional faults in the vehicle. If the functional fault analysis system detects a vehicle fault during the detection process, it can obtain the vehicle system's diagnostic fault code, such as a DTC (Diagnostic Trouble Code). It is understood that the diagnostic fault code can describe the fault type and may include identifying information such as the faulty system, manufacturer, fault type, and fault location. Based on the identifying information such as the faulty system identifier and fault location in the diagnostic fault code, the functional fault analysis system can locate the fault-related log record in the vehicle system's operation log. The operation log may include information such as usage time, interface used, usage frequency, and interface status. The target record can be the log record associated with the diagnostic fault code.
[0034] S120. Based on the target record, determine the target application interface and the target function that matches the target application interface.
[0035] The target application programming interface (API) can be an abnormal API. A functional fault analysis system can locate the abnormal API based on information such as usage time and interface status in the target record. Simply put, an Application Programming Interface (API) is a convention for connecting different components of a software system. It provides applications and developers with the ability to access a set of routines without needing to access the source code or understand the specific internal workings of the software system. Different APIs can implement different functions. Specifically, an API can correspond one-to-one with a function, and each function can implement a specific function; for example, a music sending function can send music data to an interactive terminal. Therefore, a functional fault analysis system can determine the target function corresponding to a target API.
[0036] S130. Based on the pre-determined functional clustering results based on vehicle functions, determine the functional category of the target function.
[0037] The functional fault analysis system can pre-cluster vehicle functions and determine the functional category of the target function based on the clustering results. Specifically, the system can use the function name as a metric vector for clustering analysis, or it can construct functional features based on information such as the unit to which the function belongs and its execution method, and then use these features as metric vectors for clustering analysis. Clustering analysis can employ algorithms such as K-means clustering, density-based spatial clustering, spectral clustering, and hierarchical clustering. The functional clustering results can include at least two classification categories.
[0038] If the target function is among all functions, the functional failure analysis system can determine its functional category by comparing it with each function within each category. If the target function is not among all functions, the system can process the target function, converting it into a metric vector with the same format as each function, calculating the similarity between the target function and each function's metric vector, and taking the category of the function with the highest similarity as the target function's functional category.
[0039] In this scheme, optionally, determining the functional category of the target function based on the pre-determined functional clustering results based on vehicle functions includes:
[0040] Determine the metric vector for each vehicle function, and determine a preset number of cluster centers in each metric vector;
[0041] Based on the distance information between each metric vector and each cluster center, at least one iterative operation is performed until the clustering termination condition is met, and the functional clustering result is output; the functional clustering result includes at least two partitioning categories;
[0042] Within each category, identify the functional category that matches the target function.
[0043] This solution employs K-means clustering to achieve functional clustering. Specifically, the functional fault analysis system can determine the vehicle's functions based on information such as vehicle model and brand, and determine the function's metric vector based on its functional characteristics. The functional fault analysis system can encode features such as the function's unit, execution method, input data, and output data to quantify the functional characteristics. For example, if a function includes four cases: having both input and output data, only input data, only output data, and neither input nor output data, the functional fault analysis system can encode these four input / output data features as 11, 10, 01, and 00, respectively. The functional fault analysis system can further encode based on the data type and byte size of the input and output data. This application does not impose any restrictions on the encoding dimension of the metric vector.
[0044] The functional failure analysis system can randomly select a preset number of metric vectors as cluster centers from among the various metric vectors. The preset number can be determined based on the application scenario, or it can be determined by setting different numbers of cluster centers based on the elbow rule. The functional failure analysis system can calculate the distance information between each metric vector and each cluster center, such as Euclidean distance. Based on the distance information, the functional failure analysis system can determine the functional category division result of the first iteration and determine whether the result of the first iteration meets the clustering termination condition.
[0045] If the initial iteration meets the clustering termination condition, the functional category partitioning result is output as the functional clustering result. If the initial iteration does not meet the clustering termination condition, the functional fault analysis system can update the cluster centers based on the initial functional category partitioning result and determine the distance information between each metric vector and the updated cluster centers for subsequent iterations until the iteration result meets the clustering termination condition. The functional category partitioning result of the last iteration is then used as the functional clustering result. The iteration result can include the functional category partitioning results obtained from each completed iteration, iterative evaluation metrics determined based on the functional category partitioning results, etc. Iterative evaluation metrics can include iteration loss, sum of squared errors, etc. The functional fault analysis system can also preset the number of iterations. When the preset number of iterations is reached, iteration can stop, and the functional clustering result is output.
[0046] After obtaining the functional clustering results, the functional failure analysis system can match the target function with a category within each partition. Specifically, if the target function exists among all functions, the system can use the partition to which the target function belongs as its functional category. If the target function is not among all functions, the system can process the target function, converting it into a metric vector with the same format as each function, calculating the similarity between the target function and the metric vectors of each function, and using the partition to which the function with the highest similarity belongs as the target function's functional category.
[0047] This solution uses functional clustering to determine the functional category of the target function, which facilitates the accurate classification of the target function and enables a comprehensive and thorough investigation of functional faults based on the functional category of the target function.
[0048] Based on the above scheme, the clustering termination condition includes at least one of the following conditions:
[0049] In two consecutive iterations, there are no unequal classification categories for the metric vectors, or there are no unequal classification categories for more than a first preset number of metric vectors;
[0050] In two consecutive iterations, there are no cluster centers that are not equal, or there are no cluster centers that are not equal in number greater than the second preset number;
[0051] The sum of squared errors is less than or equal to a preset error threshold; wherein the sum of squared errors is determined based on the distance between each metric vector and the cluster center matched in the current iteration.
[0052] It should be noted that the functional failure analysis system can use the distance between each metric vector and the cluster center matched in the current iteration as the error of each metric vector. The sum of squared errors can be obtained by squaring the errors of each metric vector and summing the results of the squaring operations of each metric vector.
[0053] In this embodiment, the clustering termination condition can be one or more of the above conditions, which helps to ensure the accuracy and robustness of the functional clustering results.
[0054] S140. Diagnose all functions associated with the function category.
[0055] Understandably, functions within the same functional category tend to be similar and strongly correlated. If one function within the same category malfunctions, other functions may also have potential malfunctions. Therefore, a functional failure analysis system needs to diagnose not only the target function but also all functions within the same functional category.
[0056] This technical solution involves obtaining a fault diagnostic code when a vehicle fault is detected, identifying the target record in the operation log based on the fault diagnostic code, determining the target application interface based on the target record, and identifying the target function that matches the target application interface. Then, based on the function clustering results pre-determined based on vehicle functions, the function category of the target function is determined. All functions associated with the function category are then diagnosed. This solution solves the problems of difficult diagnosis and analysis of automotive functional faults and the difficulty in completely eliminating them. It can improve the efficiency of functional fault diagnosis while increasing the reliability of functional fault elimination and preventing the recurrence of functional faults.
[0057] Example 2
[0058] Figure 2 This is a flowchart of a functional diagnostic method provided in Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiment. Figure 2 As shown, the method includes:
[0059] S210. If a vehicle malfunction is detected, obtain the fault diagnostic code and determine the target record in the operation log based on the fault diagnostic code.
[0060] S220. Based on the target record, determine the target application interface and the target function that matches the target application interface.
[0061] S230. Based on the pre-determined functional clustering results based on vehicle functions, determine the functional category of the target function.
[0062] After this step, you can continue with steps S240 and S250.
[0063] S240. Diagnose all functions associated with the function category.
[0064] S250. Identify at least one target review associated with the function category from the pre-acquired user review data.
[0065] While performing functional diagnostics, the functional fault analysis system can also obtain user feedback data after driving the vehicle through platforms such as test drive feedback and user services. It filters massive amounts of user comments based on criteria such as vehicle model, brand, comment publication time, and function category to obtain target comments associated with the function category. After this step, steps S260 and / or S290 can be executed.
[0066] S260. Determine the matching strength between each target comment and the functional category; wherein the matching strength is determined based on the text features of the target comment.
[0067] Functional failure analysis systems can recommend target feedback to automotive designers, enabling them to improve vehicle designs and prevent functional failures. Since automotive designers often struggle to extract useful information from a large volume of target feedback, functional failure analysis systems can further process this feedback to provide targeted feedback recommendations.
[0068] Specifically, the functional failure analysis system can quantify each target review and determine the matching strength between each target review and the functional category. The system can extract the text information of the target reviews, perform multi-level feature extraction on the text information to obtain the text features of the target reviews, and then define the matching strength between each target review and the functional category based on these text features.
[0069] In one feasible approach, the text features include keyword features, synonym features, and similarity features.
[0070] The keyword features can be characteristics such as the quantity and type of preset keywords contained in the text information. The synonym features can be characteristics such as the quantity and type of synonyms obtained by statistically analyzing the synonyms of the preset keywords contained in the text information after the keyword features are determined. For example, "skylight" and "roof window" can be considered a set of synonyms, and the functional fault analysis system can pre-construct a set of synonyms for the preset keyword set. The similarity features can be features determined based on the similarity between the text information and the target word after the synonym features are determined.
[0071] Based on the above scheme, determining the matching strength between each target comment and the functional category includes:
[0072] Based on the matching results between the target comments and each keyword in the preset keyword set, determine the keyword characteristics;
[0073] Synonymity features are determined based on the matching results between the target comments and each synonym group in the preset synonym set; wherein, the synonym set is determined based on each keyword in the keyword set;
[0074] Similarity features are determined based on the similarity between the target comment and the target words; wherein, the target words include each keyword in the keyword set and the synonyms in the synonym set that match each keyword;
[0075] Based on keyword features, synonym features, and similarity features, the matching strength between each target comment and the aforementioned functional category is determined.
[0076] The functional failure analysis system can match the text information of a target comment with each keyword in a keyword set, recording information such as the number of keywords present in the target comment and the category to which each keyword belongs. Based on the number of keywords and their categories, keyword features are determined. Keyword features can be evaluation values used to describe the degree of keyword matching; for example, the more keywords the target comment matches, the higher the evaluation value can be.
[0077] Similarly, a functional failure analysis system can match the text information of a target comment with each synonym group in a synonym set, recording the number of synonyms in the target comment and their respective categories. Based on the number of synonyms and their categories, synonymity features are determined. It should be noted that the synonym set includes at least two synonym groups, each containing a keyword and at least one synonym of that keyword. The functional failure analysis system can match the text information of the target comment with the synonyms in each synonym group. If a match is successful, the category of the synonym is determined based on the category of the keyword in the synonym group. Synonym features can be evaluation values used to describe the degree of synonym matching.
[0078] The functional failure analysis system can remove text that matches keywords or synonyms, leaving the remaining text. For the remaining text that matches neither keywords nor synonyms, the system can determine its similarity features based on the similarity between the remaining text and the target words in the target comment. Specifically, the system can use the cosine distance between the remaining text and the target words as a similarity feature. It should be noted that the target words include both keywords from the keyword set and synonyms from the synonym set.
[0079] The functional failure analysis system can add up the keyword features, synonym features, and similarity features of the target review, and use the sum of the features as the matching strength between the target review and the functional category.
[0080] This solution uses a target review analysis to determine the strength of the match, which helps to accurately filter user reviews and provides targeted reference information for automotive designers.
[0081] S270. Determine the target comment recommendation order based on the matching strength.
[0082] The functional failure analysis system can sort each target comment according to the matching strength of the target comments, and use the sorting result as the recommended order of the target comments.
[0083] S280. According to the recommended order of the target comments, send a preset number of target comments to the design terminal.
[0084] If the number of target comments exceeds a preset threshold, the functional fault analysis system can extract a preset number of target comments from the recommended order and send them to the design terminal for automotive designers' reference. If the number of target comments is less than or equal to the preset threshold, the functional fault analysis system can directly send the target comments to the design terminal according to the recommended order.
[0085] S290. Determine the target number of comments that match each function in the function category.
[0086] The functional failure analysis system can also statistically analyze the number of target comments from a functional perspective to recommend comments on the most relevant functions to automotive designers. Specifically, the type of target keywords can be determined according to vehicle functions. The functional failure analysis system can count the number of target comments for each function based on the type of target keywords involved in the target comments.
[0087] S2100. Determine the target comment recommendation order based on the target comment count.
[0088] The functional failure analysis system can sort functions by the number of target reviews. Based on this sorting, it then selects target reviews for each function in sequence to form a target review recommendation order. For example, given six functions A, B, C, D, E, and F, with 20, 16, 14, 10, 6, and 2 target reviews respectively, the system can select one target review from each of functions A, B, C, D, E, and F to form the target review recommendation order. This order can be represented as: A1, B1, C1, D1, E1, F1, A2, B2, C2, D2, E2, F2… where A1 represents the first target review for function A, A2 represents the second target review for function A, and so on. The system can also adjust the target review recommendation order based on the proportion of target reviews. For example, if the ratio of the target number of comments for functions A, B, C, D, E, and F is 10:8:7:5:3:1, the recommended order of the target comments can be adjusted to: A1-A10, B1-B8, C1-C7, D1-D5, E1-E3, F1, A11-A20... After this step, S280 can be executed.
[0089] It should be noted that the functional failure analysis system can also combine the statistical analysis of the number of target reviews from a functional perspective with the statistical analysis of the matching strength from the perspective of target reviews to determine the recommendation order of target reviews, so as to realize the multi-dimensional analysis of target reviews and provide more useful reference information for automotive designers.
[0090] This technical solution, based on the functional clustering results determined by vehicle functions, diagnoses all functions associated with the functional category to which the target function belongs, and can also provide targeted recommendations for target comments associated with the functional category. This solution not only increases the reliability of troubleshooting functional faults but also helps automotive designers promptly address vehicle shortcomings, providing vehicle designs that better meet user needs, thereby improving user satisfaction.
[0091] Example 3
[0092] Figure 3 This is a schematic diagram of the structure of a functional diagnostic device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes:
[0093] The target record determination module 310 is used to obtain a fault diagnosis code if a vehicle fault is detected, and determine the target record in the operation log based on the fault diagnosis code.
[0094] The target function determination module 320 is used to determine the target application interface based on the target record, and to determine the target function that matches the target application interface.
[0095] The function category determination module 330 is used to determine the function category of the target function based on the function clustering results determined in advance based on vehicle functions;
[0096] The function diagnosis module 340 is used to diagnose all functions associated with the function category.
[0097] In this solution, optionally, the function category determination module 330 is specifically used for:
[0098] Determine the metric vector for each vehicle function, and determine a preset number of cluster centers in each metric vector;
[0099] Based on the distance information between each metric vector and each cluster center, at least one iterative operation is performed until the clustering termination condition is met, and the functional clustering result is output; the functional clustering result includes at least two partitioning categories;
[0100] Within each category, identify the functional category that matches the target function.
[0101] Based on the above scheme, the clustering termination condition includes at least one of the following conditions:
[0102] In two consecutive iterations, there are no unequal classification categories for the metric vectors, or there are no unequal classification categories for more than a first preset number of metric vectors;
[0103] In two consecutive iterations, there are no cluster centers that are not equal, or there are no cluster centers that are not equal in number greater than the second preset number;
[0104] The sum of squared errors is less than or equal to a preset error threshold; wherein the sum of squared errors is determined based on the distance between each metric vector and the cluster center matched in the current iteration.
[0105] In one feasible embodiment, the device further includes a first user review recommendation module, used for:
[0106] Identify at least one target review associated with the function category from the pre-acquired user review data;
[0107] Determine the matching strength between each target comment and the functional category; wherein the matching strength is determined based on the textual features of the target comment;
[0108] The target comment recommendation order is determined based on the matching strength.
[0109] Based on the recommended order of the target comments, a preset number of target comments are sent to the design terminal.
[0110] Based on the above scheme, the text features include keyword features, synonym features, and similarity features.
[0111] In a preferred embodiment, the first user review recommendation module is specifically used for:
[0112] Based on the matching results between the target comments and each keyword in the preset keyword set, determine the keyword characteristics;
[0113] Synonymity features are determined based on the matching results between the target comments and each synonym group in the preset synonym set; wherein, the synonym set is determined based on each keyword in the keyword set;
[0114] Similarity features are determined based on the similarity between the target comment and the target words; wherein, the target words include each keyword in the keyword set and the synonyms in the synonym set that match each keyword;
[0115] Based on keyword features, synonym features, and similarity features, the matching strength between each target comment and the aforementioned functional category is determined.
[0116] In another feasible embodiment, the device further includes a second user review recommendation module, used for:
[0117] Identify at least one target review associated with the function category from the pre-acquired user review data;
[0118] Determine the target number of comments that match each function in the aforementioned function category;
[0119] The target comment recommendation order is determined based on the target comment count.
[0120] Based on the recommended order of the target comments, a preset number of target comments are sent to the design terminal.
[0121] The functional diagnostic device provided in the embodiments of the present invention can execute the functional diagnostic method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.
[0122] Example 4
[0123] Figure 4A schematic diagram of an electronic device 410 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0124] like Figure 4 As shown, the electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.
[0125] Multiple components in electronic device 410 are connected to I / O interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of displays, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0126] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as functional diagnostic methods.
[0127] In some embodiments, the functional diagnostic method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the functional diagnostic method described above may be performed. Alternatively, in other embodiments, processor 411 may be configured to perform the functional diagnostic method by any other suitable means (e.g., by means of firmware).
[0128] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0129] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0130] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0131] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0132] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0133] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.
[0134] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.
[0135] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A functional diagnostic method, characterized in that, The method includes: If a vehicle malfunction is detected, a fault diagnostic code is obtained, and the target record is determined in the operation log based on the fault diagnostic code. Based on the target record, determine the target application interface and the target function that matches the target application interface; Based on the pre-defined functional clustering results based on vehicle functions, determine the functional category of the target function; Diagnose all functions associated with the aforementioned function category.
2. The method according to claim 1, characterized in that, The step of determining the functional category of the target function based on the pre-determined functional clustering results based on vehicle functions includes: Determine the metric vector for each vehicle function, and determine a preset number of cluster centers in each metric vector; Based on the distance information between each metric vector and each cluster center, at least one iterative operation is performed until the clustering termination condition is met, and the functional clustering result is output; the functional clustering result includes at least two partitioning categories; Within each category, identify the functional category that matches the target function.
3. The method according to claim 2, characterized in that, The clustering termination condition includes at least one of the following conditions: In two consecutive iterations, there are no unequal classification categories for the metric vectors, or there are no unequal classification categories for more than a first preset number of metric vectors; In two consecutive iterations, there are no cluster centers that are not equal, or there are no cluster centers that are not equal in number greater than the second preset number; The sum of squared errors is less than or equal to a preset error threshold; wherein the sum of squared errors is determined based on the distance between each metric vector and the cluster center matched in the current iteration.
4. The method according to claim 1, characterized in that, After determining the functional category of the target function, the method further includes: Identify at least one target review associated with the function category from the pre-acquired user review data; Determine the matching strength between each target comment and the functional category; wherein the matching strength is determined based on the textual features of the target comment; The target comment recommendation order is determined based on the matching strength. Based on the recommended order of the target comments, a preset number of target comments are sent to the design terminal.
5. The method according to claim 4, characterized in that, The text features include keyword features, synonym features, and similarity features.
6. The method according to claim 5, characterized in that, Determining the matching strength between each target comment and the functional category includes: Based on the matching results between the target comments and each keyword in the preset keyword set, determine the keyword characteristics; Synonymity features are determined based on the matching results between the target comments and each synonym group in the preset synonym set; wherein, the synonym set is determined based on each keyword in the keyword set; Similarity features are determined based on the similarity between the target comment and the target words; wherein, the target words include each keyword in the keyword set and the synonyms in the synonym set that match each keyword; Based on keyword features, synonym features, and similarity features, the matching strength between each target comment and the aforementioned functional category is determined.
7. The method according to claim 1, characterized in that, After determining the functional category of the target function, the method further includes: Identify at least one target review associated with the function category from the pre-acquired user review data; Determine the target number of comments that match each function in the aforementioned function category; The target comment recommendation order is determined based on the target comment count. Based on the recommended order of the target comments, a preset number of target comments are sent to the design terminal.
8. A functional diagnostic device, characterized in that, The device includes: The target record determination module is used to obtain the fault diagnosis code if a vehicle fault is detected, and determine the target record in the operation log based on the fault diagnosis code. The target function determination module is used to determine the target application interface based on the target record, and to determine the target function that matches the target application interface. The function category determination module is used to determine the function category of the target function based on the function clustering results determined in advance based on vehicle functions; The function diagnosis module is used to diagnose all functions associated with the function category.
9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the functional diagnostic method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the functional diagnostic method according to any one of claims 1-7.