Diagnosis report analysis method and system, terminal equipment and storage medium

Abstract

The invention belongs to the technical field of vehicle diagnosis, and discloses a diagnosis report analysis method and system, terminal equipment and a storage medium, and the method comprises the steps: carrying out the vectorization of fault information, received by automobile diagnosis equipment, of a target vehicle, and obtaining target vector data; preprocessing the collected original data of the vehicle to obtain original vector data; calculating the similarity between the target vector data and the original vector data, and obtaining matched data in a preset similarity range; and performing diagnostic analysis on the target vector data and the matching data by using the first pre-constructed model to obtain a diagnostic analysis result of the target vehicle. After the original data is preprocessed to obtain the original vector data, the similarity between the target vector data and the original vector data is calculated, then the selected matching data is input into the first pre-purchase modeling for diagnosis analysis, the diagnosis decomposition result is obtained, and the interpretation efficiency and accuracy of interpreting the automobile diagnosis report are improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle diagnosis, and in particular to an analysis method, system, terminal device and storage medium for a diagnostic report. Background Art

[0002] Currently in the field of automobile maintenance, automobile diagnostic reports are the key basis for determining vehicle failures and maintenance plans. Among them, fault codes are an important basis for determining vehicle failures.

[0003] However, the existing method of analyzing automobile diagnostic reports mainly relies on the experience and expertise of technicians. The manual interpretation process is cumbersome and time-consuming, and it is easy to make mistakes. For example, when faced with some new or rare fault codes, it may take a lot of time to study and analyze them. At the same time, with the increasing complexity of automobile technology, the information in the diagnostic report has become more complicated, which puts higher requirements on the accuracy and efficiency of interpretation.

[0004] Therefore the prior art still needs to be improved and enhanced. Summary of the invention

[0005] The present application provides a diagnostic report analysis method, system, terminal device and storage medium, aiming to solve the problems of low recognition efficiency and poor accuracy when interpreting automobile diagnostic reports in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a method for analyzing a diagnostic report, which is applied to an automobile diagnostic device, comprising:

[0007] Vectorizing the fault information of the target vehicle received by the vehicle diagnostic device to obtain target vector data;

[0008] Preprocessing the collected raw data of the vehicle to obtain raw vector data;

[0009] Calculating the similarity between the target vector data and the original vector data, and obtaining matching data within a preset similarity range;

[0010] The target vector data and the matching data are diagnosed and analyzed using the first pre-built model to obtain a diagnostic analysis result of the target vehicle.

[0011] In some embodiments, the method for analyzing the diagnostic report further comprises:

[0012] The diagnostic analysis result is verified, and the parameters of the first pre-built model are adjusted according to the obtained verification result.

[0013] In some embodiments, calculating the similarity between the target vector data and the original vector data to obtain matching data within a preset similarity range includes:

[0014] The target vector data and the original vector data are matched for similarity by a vector similarity algorithm, and data with similarity within a preset range is screened out to obtain the matching data.

[0015] In some embodiments, the using of the first pre-built model, before comprising:

[0016] Pre-setting the parameters of the first pre-built model to obtain a prompt word;

[0017] The prompt words are used to perform diagnostic analysis on the target vector data and the matching data.

[0018] In some embodiments, the use of the first pre-built model to perform diagnostic analysis on the target vector data and the matching data to obtain a diagnostic analysis result of the target vehicle includes:

[0019] Merging the target vector data and the matching data to obtain a merged text language;

[0020] The prompt words set in the first pre-built model are used to decode and identify the fault code, fault description and target component in the combined text language to obtain the fault component of the target vehicle and its fault information, fault cause and maintenance suggestion.

[0021] In some embodiments, the preprocessing of the collected raw data of the vehicle includes:

[0022] Acquiring vehicle maintenance record or fault record information input by a user or pre-stored to obtain the original data;

[0023] Cleaning, standardizing and word segmenting the vehicle maintenance records; or,

[0024] After the fault record information is cleaned, the cleaned fault record information is vectorized using the second pre-built model.

[0025] In some embodiments, vectorizing the fault information of the target vehicle received by the vehicle diagnostic device includes:

[0026] Acquiring data information of an electronic control unit of a target vehicle detected by the automobile diagnostic device;

[0027] vectorizing the data information of the electronic control unit by using a second pre-built model to obtain the target vector data;

[0028] The data information includes: data parameters and original fault code information, and the data parameters include: the speed, temperature, voltage and current of the engine of the target vehicle.

[0029] In a second aspect, an embodiment of the present application provides a diagnostic report analysis system, which is applied to an automobile diagnostic device, including:

[0030] A vectorization module, used for vectorizing the fault information of the target vehicle received by the vehicle diagnostic device to obtain target vector data;

[0031] A preprocessing module is used to preprocess the collected raw data of the vehicle to obtain raw vector data;

[0032] A calculation module, used to calculate the similarity between the target vector data and the original vector data, and obtain matching data within a preset similarity range;

[0033] The parsing module is used to perform diagnostic analysis on the target vector data and the matching data using the first pre-built model to obtain a diagnostic analysis result of the target vehicle.

[0034] In a third aspect, an embodiment of the present application provides a terminal device, comprising: a memory, a processor, a display, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the diagnostic report analysis method as described above.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the diagnostic report analysis method as described above.

[0036] Compared with the prior art, the present application provides a diagnostic report analysis method, system, terminal device and storage medium. The method vectorizes the fault information to obtain target vector data, calculates the similarity between the target vector data and the original vector data, and filters out the matching data within a preset similarity range, and then inputs the data into the first pre-purchase modeling for diagnostic analysis to obtain diagnostic analysis results such as possible causes of the fault, involved components and maintenance suggestions, so as to quickly and efficiently analyze the automobile diagnostic report, interpret the fault code, and give reasonable maintenance suggestions, thereby greatly improving the maintenance quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A schematic diagram of a flow chart of the analysis method of the diagnostic report provided in this application;

[0039] Figure 2 A schematic diagram of a process for obtaining target vector data in the analysis method of the diagnostic report provided in this application;

[0040] Figure 3 A schematic diagram of a process for preprocessing in an analysis method using a diagnostic report provided by the present application;

[0041] Figure 4 A schematic diagram of a process for obtaining diagnostic analysis results in the analysis method of the diagnostic report provided in this application;

[0042] Figure 5 A schematic diagram of the structure of the analysis system for the diagnostic report provided in this application. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0044] The components of the embodiments of the present application generally described and shown in the drawings herein may be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0045] Hereinafter, the terms "including", "having" and their cognates used in various embodiments of the present application are intended only to indicate specific features, numbers, steps, operations, elements, components or a combination of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or a combination of the foregoing items or increasing the possibility of one or more features, numbers, steps, operations, elements, components or a combination of the foregoing items. In addition, the terms "first", "second", "third" and the like are only used to distinguish descriptions and cannot be understood as indicating or implying relative importance.

[0046] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present application.

[0047] The present application provides a method, system, terminal device and storage medium for analyzing a diagnostic report. The method for analyzing a diagnostic report vectorizes the fault information to obtain target vector data, calculates the similarity between the target vector data and the original vector data, and screens out matching data within a preset similarity range, and then inputs the matching data into the first pre-purchase modeling for diagnostic analysis, and obtains diagnostic analysis results such as possible causes of the fault, involved components and maintenance suggestions, so that the automobile diagnostic report can be analyzed quickly and efficiently, the fault code can be explained, and reasonable maintenance suggestions can be given, thereby greatly improving the maintenance quality.

[0048] The design scheme of the analysis method of the diagnostic report is described below through some specific embodiments.

[0049] See also Figure 1 The embodiment of the present application provides a method for analyzing a diagnostic report, which is applied to an automobile diagnostic device and can be summarized as an analysis of an automobile diagnostic report and an analysis or interpretation of an automobile fault code, including steps S100-S400:

[0050] S100, vectorizing the fault information of the target vehicle received by the automobile diagnostic equipment to obtain target vector data.

[0051] Exemplarily, in the first embodiment of the present application (analysis of a vehicle diagnostic report), the vehicle diagnostic report (ie, fault information) is obtained, and the fault information is vectorized using vectorized data to obtain vectorized target vector data.

[0052] The diagnostic report includes: data information of the electronic control unit of the target vehicle (the target vehicle is the vehicle currently being tested), such as data parameters such as engine speed, temperature, voltage and current, as well as fault code information.

[0053] In the second embodiment (analysis or interpretation of automobile fault codes), at this time, by using the company's on-sale intelligent diagnostic equipment and OBD (abbreviation of On-Board Diagnostics, Chinese for "vehicle automatic diagnostic system") transmitter, when the target vehicle is connected, the device scans the target vehicle data and obtains the fault code information (i.e. fault information) returned by the system. Then, the fault code information is vectorized to obtain the target vector data. At the same time, the target vector data is also stored in the vector database to update the database.

[0054] Demonstratively, a large amount of fault information of the target vehicle is vectorized to obtain target vector data to serve as a comparison standard for similarity, thereby improving the accuracy of report analysis.

[0055] For example, in one implementation, see Figure 2 , vectorize the fault information of the target vehicle received by the automobile diagnostic equipment, including:

[0056] S101, acquiring data information of an electronic control unit of a target vehicle detected by an automobile diagnostic device.

[0057] S102: vectorize the data information of the electronic control unit using the second pre-built model to obtain target vector data.

[0058] The data information includes: data parameters and original fault code information, and the data parameters include: the speed, temperature, voltage and current of the engine of the target vehicle. The second pre-built model is a vectorized model.

[0059] Exemplarily, in the first embodiment, the interface of the automobile diagnostic device or system is used to obtain data information of the electronic control unit of the target vehicle detected by the automobile diagnostic device, such as data parameters such as engine speed, temperature, voltage and current, as well as fault code information.

[0060] Then, the vectorization model vectorizes the data information of the electronic control unit to obtain the target vector data.

[0061] S200: pre-processing the collected original data of the vehicle to obtain original vector data.

[0062] Among them, the original data includes: vehicle maintenance records, including basic vehicle information, fault information (including engine failure, display reading problems, brake system or wiper failure or insensitivity, automatic exhaust system failure and windows that cannot be closed, etc.), data flow information when the fault occurs and maintenance cases (including causes, maintenance process and follow-up visits, etc.).

[0063] Exemplarily, in the first embodiment, the original data (including basic vehicle information, fault information, data flow information when the fault occurs, and repair cases) such as vehicle maintenance records of a large number of vehicles (it should be noted that the vehicles here refer to a large number of vehicles of different or the same type) are first obtained. The original data is cleaned, standardized, and segmented to obtain preprocessed data, which is then saved in the vector knowledge base (i.e., database) to update the vector knowledge base.

[0064] In the second embodiment, after obtaining a large amount of raw data such as fault code data, the raw data is preprocessed by cleaning and vectorization to obtain preprocessed data, which is then saved in a vector database (ie, a database) to update the vector database.

[0065] It can be understood that in this application, the original data is preprocessed to ensure the quality and standardization of the data, so as to optimize the data and improve the accuracy of the recognition results.

[0066] For example, in one implementation, see Figure 3 , pre-process the collected raw data of the vehicle, including:

[0067] S201. Obtain vehicle maintenance record or fault record information input by a user or pre-stored to obtain original data.

[0068] S202: Clean, standardize and segment vehicle maintenance records.

[0069] S203, or, after cleaning the fault record information, use the second pre-built model to perform vectorization processing on the cleaned fault record information.

[0070] Among them, the second pre-built model is a vectorized model, which is used in the present application to perform vectorized processing on fault information or raw data, which helps to standardize the format and improve data processing data.

[0071] Exemplarily, in the first embodiment, first, a large amount of original data such as vehicle maintenance records uploaded by enterprise users or employees, or accumulated in the maintenance record management system of the vehicle manufacturer is obtained (including basic vehicle information, fault information, data flow information when the fault occurs, and maintenance cases).

[0072] Then, the vehicle maintenance records are cleaned, standardized, and segmented:

[0073] The original data is sorted, including format cleaning, removal of redundant symbols, standardized file formats and standardized typesetting formats, etc. The output can be used as reserve data for model preparatory training, fine-tuning models and additional maintenance data. Word segmentation means that the vector knowledge base and training data will need to use vectorized data. During processing, the target document needs to be cut into blocks to form a large number of text blocks, and then the text blocks are vectorized and escaped to form multi-dimensional floating-point data, thereby completing the accumulation of the vector knowledge base.

[0074] In the second embodiment, first, after obtaining the original data such as the fault record information of the vehicle input by the user or pre-stored, the fault record information is cleaned and vectorized:

[0075] The process of cleaning and processing fault record information to make it more accurate, consistent, and complete. This process includes identifying and correcting or deleting erroneous, duplicate, incomplete, or irrelevant data.

[0076] Identifying erroneous data means finding and identifying errors in data, such as input errors, inconsistent formats, etc. Handling missing data means supplementing or deleting missing data records to ensure data consistency and completeness. Deduplication means identifying and deleting duplicate data records to avoid repeated calculations and analysis. Standardizing data formats means unifying the format of data, such as date format, units, etc., to make the data more consistent. Correcting erroneous data means modifying or correcting erroneous data values ​​to ensure data accuracy.

[0077] Then, since the vectorization model cannot directly process unstructured data such as text, pictures, audio and video, vectorization processing is required, it is necessary to use the vectorization model (the second pre-built model) to vectorize the cleaned fault record information to obtain the target vector data, which is a floating point array of many dimensions, such as [0.3333, 0.1224, 0.3222...], and each dimension is represented by a data to represent its measurement.

[0078] S300: Calculate the similarity between the target vector data and the original vector data, and obtain matching data within a preset similarity range.

[0079] Exemplarily, after the original vector data is obtained, the target vector data is compared with the original vector data for similarity to obtain matching data, and matching data within a preset similarity range (eg, the top n similarity rankings) is obtained.

[0080] Furthermore, in another embodiment of the present application, the original vector data may be standard data set by an individual, and the standard data is obtained by using the standard of fault identification based on driving habits or analyzing and understanding the automobile fault code, and then the standard data is compared with the target vector data for similarity. Furthermore, the target vector data may also be compared with the standard data and the original vector data for similarity, and the data with higher similarity is retained as the comparison data of the original vector data.

[0081] It can be understood that in the present application, the accuracy of the diagnosis result is improved by calculating the similarity between the target vector data and the original vector data, and filtering out data within a preset similarity range as input data for model diagnosis analysis.

[0082] For example, in one implementation method, step S300, calculating the similarity between the target vector data and the original vector data, and obtaining matching data within a preset similarity range, includes:

[0083] The target vector data is matched with the original vector data by similarity through the vector similarity algorithm, and the data with similarity within a preset range is filtered out to obtain matching data.

[0084] Exemplarily, the detailed process of obtaining matching data is as follows:

[0085] Since the correct data in the database is huge, there are too many similar keyword contents. Therefore, vector retrieval technology (such as minimum cosine distance calculation method) can be used to retrieve the keywords that are the same as the target vector data.

[0086] Then, the target vector data and the original vector data are matched and calculated using the vector similarity algorithm. That is, after extracting the keywords in the target vector data, similar keywords are searched in the database, and the similarity between them is calculated using the vector similarity algorithm.

[0087] Among them, the vector similarity algorithm includes the cosine similarity algorithm. For example, if two-dimensional data point A and point B (keywords) each have x and y axis values, then the distance between AB can be obtained by cosine similarity. Similarly, if the distance between two points A and B in thousands of dimensional data is the smallest compared to other points, then the features of these two points are the most similar.

[0088] Furthermore, the contents of the first n (ie, a preset range, n can be freely set) keywords with the closest distance are selected and returned to obtain matching data.

[0089] S400: Utilize the first pre-built model to perform diagnostic analysis on the target vector data and the matching data to obtain a diagnostic analysis result of the target vehicle.

[0090] Among them, the first pre-built models are closed-source and open-source large language models, such as ChatGPT (a large language model, mainly used to generate natural language text), OpenAI and Llama (a series of large language models), etc.

[0091] Exemplarily, after obtaining the matching model, the target vector data and the matching data are input into the closed-source and open-source large language model (the first pre-built module), and the closed-source and open-source large language model performs diagnostic analysis on the target vector data and the matching data to obtain the diagnostic analysis results of the target vehicle, including possible causes of the fault, involved components and maintenance suggestions, etc.

[0092] It can be understood that the preprocessed text in this application enters the big model for intelligent analysis, and the big model extracts key information and generates maintenance suggestions based on the algorithm and knowledge base, thereby improving the analysis efficiency, providing direct information and suggestions on the cause of the fault, and improving the maintenance efficiency.

[0093] For example, in one implementation, see Figure 4 Step S400: using the first pre-built model, performing diagnostic analysis on the target vector data and the matching data to obtain a diagnostic analysis result of the target vehicle, including:

[0094] S410: Merge the target vector data and the matching data to obtain a merged text language.

[0095] S420: using the prompt words set in the first pre-built model, the fault code, the fault description and the target component in the merged text language are decoded and identified to obtain the fault component of the target vehicle and its fault information, the fault cause and the maintenance suggestion.

[0096] Among them, prompt words are used to diagnose and analyze target vector data and matching data. They are input through language instructions and generally include setting model roles, setting skills, setting restrictions, etc.

[0097] Exemplarily, the process of obtaining the diagnostic analysis results is as follows:

[0098] First, the target vector data and the matching data are merged to obtain a merged text language. If it is in the second embodiment, the original fault code information in the data information and the returned n contents (ie, matching data) are merged into the context language (merged text language), that is, normal language text.

[0099] Then, the context language is input into the closed source and open source big language models. After that, the closed source and open source big language models interpret the context language according to certain requirement rules, such as format, extraction of specific content and output tone and other prompts, and obtain diagnostic analysis results such as specified model output, fault code definition, phenomenon, circuit test results, component test results, maintenance guides and reference pictures.

[0100] For example, when fault codes such as P0101, P0107 and P0110 appear, it means that the car has a bad air flow meter circuit, the intake pressure sensor input voltage is too low, and the intake temperature sensor circuit is intermittent.

[0101] Here are some examples of fault codes and their corresponding explanations:

[0102] P0101: The air flow meter circuit is bad; P0102: The air flow meter circuit input voltage is too low; P0103: The air flow meter circuit input voltage is too high; P0104: The air flow meter circuit is intermittent fault; P0105: The intake pressure sensor circuit is bad; P0106: The intake pressure sensor circuit is bad; P0107: The intake pressure sensor input voltage is too low; P0108: The intake pressure sensor input voltage is too high; P0109: The intake temperature sensor circuit is bad or the intake pressure sensor circuit is intermittent; P0110: The intake temperature sensor circuit is intermittent, etc.

[0103] For example, in one implementation method, using a first pre-built model, the process includes:

[0104] The parameters of the first pre-built model are set in advance to obtain prompt words; the prompt words are used to perform diagnostic analysis on the target vector data and the matching data.

[0105] Exemplarily, the prompt word can be obtained by presetting the parameters of the first prebuilt model, that is, by setting the model role, setting the skills, setting the restrictions and the like.

[0106] For example, in one implementation method, after the diagnostic analysis results of the target vehicle are obtained, they are output in a clear format, such as text description or chart, etc., to facilitate user understanding and use.

[0107] For example, in one implementation method, the analysis method of the diagnostic report further includes:

[0108] S500: Verify the diagnostic analysis result, and adjust the parameters of the first pre-built model according to the obtained verification result.

[0109] Exemplarily, after obtaining the diagnostic analysis results, the technical personnel may verify and adjust the results, that is, continuously optimize and adjust the parameters of the first pre-built model according to the accuracy of the obtained diagnostic analysis results, thereby continuously optimizing the analytical model.

[0110] See also Figure 5 The embodiment of the present application provides a diagnostic report analysis system, which is applied to automobile diagnostic equipment, including:

[0111] The vectorization module 10 is used to vectorize the fault information of the target vehicle received by the vehicle diagnostic device to obtain target vector data.

[0112] The preprocessing module 20 is used to preprocess the collected original data of the vehicle to obtain original vector data.

[0113] The calculation module 30 is used to calculate the similarity between the target vector data and the original vector data, and obtain matching data within a preset similarity range.

[0114] The analysis module 40 is used to perform diagnostic analysis on the target vector data and the matching data using the first pre-built model to obtain a diagnostic analysis result of the target vehicle.

[0115] Exemplarily, the analysis system of the diagnostic report is applicable to the analysis method of the diagnostic report. Then, the implementation process of the analysis system of the diagnostic report is as follows:

[0116] The first embodiment: during the analysis of the automobile diagnostic report, the automobile diagnostic report (i.e., fault information) such as the data information of the electronic control unit is first obtained using the interface of the automobile diagnostic device or system, and then the automobile diagnostic report is vectorized to obtain the target vector data.

[0117] Then, a large number of vehicle maintenance records, such as basic vehicle information, fault information, data flow information when the fault occurs, and maintenance cases, uploaded by enterprise users or employees, or pre-stored by the vehicle factory, are obtained, and pre-processing operations such as cleaning, standardization, and word segmentation are performed on the vehicle maintenance records. The pre-processed vehicle maintenance records are then saved in a vector knowledge base (i.e., a database) to update the vector knowledge base.

[0118] Furthermore, the target vector data is compared with the data in the updated vector knowledge base in terms of similarity to obtain matching data, and the matching data with the top n similarity rankings (within a preset similarity range) are extracted.

[0119] Finally, the target vector data and matching data are input into the closed-source and open-source large language models together, and the closed-source and open-source large language models perform diagnostic analysis to obtain diagnostic analysis results such as possible causes of the fault, involved components, and maintenance recommendations.

[0120] Second embodiment: In the process of analyzing or interpreting the automobile fault code, similarly, the fault code information of the target vehicle is first acquired through the interface of the automobile diagnostic device or system, and then the fault code information is vectorized to obtain target vector data.

[0121] Then, the fault code data such as the fault record information of the target vehicle input by the user or pre-stored by the vehicle manufacturer is obtained, and after the fault record information is cleaned, the cleaned fault record information is vectorized using a vectorization model (a second pre-built model) to complete the preprocessing operation, and then the preprocessed fault record information is saved in a vector database (i.e., a database) to update the vector database.

[0122] Furthermore, similarly, the target vector data is compared with the target vector data for similarity to obtain matching data, and the matching data with the top n similarities are extracted. After that, the target vector data and the matching data are input into the closed-source and open-source big language models, which perform diagnostic analysis to obtain diagnostic analysis results such as possible causes of the fault, involved components, and maintenance recommendations.

[0123] It can be understood that the diagnostic report analysis system is an interactive intelligent analysis diagnostic report system based on AI and large model technology. It performs diagnostic analysis on the target vector data and matching data through the first pre-built model, so as to quickly and accurately analyze the diagnostic report of the target vehicle and interpret the fault code, which not only reduces the manual interpretation time, but also enables maintenance personnel to quickly understand the cause of the fault and the direction of maintenance, thereby effectively saving a lot of time and improving maintenance efficiency.

[0124] In addition, accurate analysis results and fault code explanations help technicians develop more reasonable maintenance plans, thereby reducing misjudgments and maintenance errors and improving maintenance quality.

[0125] Furthermore, applying big model parsing technology to the analysis of automobile diagnostic reports and the interpretation of fault codes helps to accumulate and pass on automobile maintenance technical knowledge and reduces the difficulty of interpreting fault codes, so that novice technicians can also better understand and process diagnostic reports.

[0126] The present application also provides a terminal device, which can be exemplarily an automobile diagnostic device, and the terminal device includes a processor and a memory, wherein the memory stores a computer program, and the processor runs the computer program to enable the terminal device to execute the above-mentioned diagnostic report analysis method or the functions of each module in the above-mentioned diagnostic report analysis system.

[0127] Among them, the car diagnostic equipment collects all types of car data to enter the original data. When the car is fault-checked, the car diagnostic equipment will automatically identify the vehicle information and find the historical data of this car (not necessarily the same car). Among them, the historical data refers to the maintenance records saved at the last inspection or the original data of the same car (not necessarily the same car, as long as the model and brand are the same).

[0128] Then, the automobile diagnostic equipment can call the historical data in the database for comparative analysis. If no historical data is found during this diagnostic process, but the original data exists in the database, the original vector data can be used to compare and analyze the target vector data. If the database only has historical data but no original data, then the historical data and target vector data are used for comparative analysis. If there is neither historical data nor original data, then a new database is created to store the vehicle model data and fault data so that it can be used for comparison the next time the vehicle model needs fault diagnosis.

[0129] Among them, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU) and a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or at least one of other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application.

[0130] The memory may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. The memory is used to store a computer program, and the processor may execute the computer program accordingly after receiving an execution instruction.

[0131] The present application also provides a computer-readable storage medium for storing the computer program used in the above-mentioned terminal device. For example, the computer-readable storage medium may include but is not limited to: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0132] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or the flow diagram, and the combination of boxes in the structure diagram and / or the flow diagram, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0133] In addition, the functional modules or units in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0134] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application.

[0135] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for analyzing a diagnostic report, applied to an automobile diagnostic device, characterized in that: include: Vectorizing the fault information of the target vehicle received by the vehicle diagnostic device to obtain target vector data; Preprocessing the collected raw data of the vehicle to obtain raw vector data; Calculating the similarity between the target vector data and the original vector data, and obtaining matching data within a preset similarity range; The target vector data and the matching data are diagnosed and analyzed using the first pre-built model to obtain a diagnostic analysis result of the target vehicle.

2. The method for analyzing a diagnostic report according to claim 1, characterized in that: Also includes: The diagnostic analysis result is verified, and the parameters of the first pre-built model are adjusted according to the obtained verification result.

3. The method for analyzing a diagnostic report according to claim 1, characterized in that: The calculating the similarity between the target vector data and the original vector data to obtain matching data within a preset similarity range includes: The target vector data and the original vector data are matched for similarity by a vector similarity algorithm, and data with similarity within a preset range is screened out to obtain the matching data.

4. The method for analyzing a diagnostic report according to claim 1, characterized in that: The utilizing of the first pre-built model previously comprises: Pre-setting the parameters of the first pre-built model to obtain a prompt word; The prompt words are used to perform diagnostic analysis on the target vector data and the matching data.

5. The method for analyzing a diagnostic report according to claim 4, characterized in that: The using of the first pre-built model to perform diagnostic analysis on the target vector data and the matching data to obtain a diagnostic analysis result of the target vehicle includes: Merging the target vector data and the matching data to obtain a merged text language; The prompt words set in the first pre-built model are used to identify the fault code, fault description and target component in the combined text language to obtain the fault component of the target vehicle and its fault information, fault cause and maintenance suggestion.

6. The method for analyzing a diagnostic report according to claim 1, characterized in that: The preprocessing of the collected raw data of the vehicle includes: Acquiring vehicle maintenance record or fault record information input by a user or pre-stored to obtain the original data; Cleaning, standardizing and word segmenting the vehicle maintenance records; or, After the fault record information is cleaned, the cleaned fault record information is vectorized using the second pre-built model.

7. The method for analyzing a diagnostic report according to claim 1, characterized in that: The vectorizing of the fault information of the target vehicle received by the vehicle diagnostic device includes: Acquiring data information of an electronic control unit of a target vehicle detected by the automobile diagnostic device; vectorizing the data information of the electronic control unit by using the second pre-built model to obtain the target vector data; The data information includes: data parameters and original fault code information, and the data parameters include: the speed, temperature, voltage and current of the engine of the target vehicle.

8. A diagnostic report analysis system, applied to automobile diagnostic equipment, characterized in that: include: A vectorization module, used for vectorizing the fault information of the target vehicle received by the vehicle diagnostic device to obtain target vector data; A preprocessing module is used to preprocess the collected raw data of the vehicle to obtain raw vector data; A calculation module, used to calculate the similarity between the target vector data and the original vector data, and obtain matching data within a preset similarity range; The parsing module is used to perform diagnostic analysis on the target vector data and the matching data using the first pre-built model to obtain a diagnostic analysis result of the target vehicle.

9. A terminal device, characterized in that: include: A memory, a processor, a display, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the method for analyzing a diagnostic report according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the steps of the method for analyzing a diagnostic report according to any one of claims 1 to 7 are implemented.

Images