Intelligent maintenance scheme recommendation method and system based on intelligent voice, and related products

Abstract

The invention discloses an intelligent maintenance scheme recommendation method and system based on intelligent voice, and a related product. The method comprises the following steps: receiving first voice data of a target user for target vehicle maintenance; analyzing the first voice data to obtain target question content and a corresponding target question type; when the target question type is a question feedback type, displaying target guide content corresponding to the target question content, indicating the target user to reply the target guide content, and receiving target feedback information which is fed back by the target user and aims at the target guide content; determining a first maintenance strategy according to the target question content and the target feedback information, and pushing the first maintenance strategy to the target user; and when the target question type is the question query type, determining a second maintenance strategy according to the content of the target question, and pushing the second maintenance strategy to the target user. By adopting the method and the device, the accurate maintenance scheme can be obtained in time.

Description

Technical Field

[0001] The present application relates to the field of vehicle diagnosis technology, and in particular to an intelligent maintenance solution recommendation method, system and related products based on intelligent voice. Background Art

[0002] With the continuous development of automobile technology, the electronic system and mechanical structure of vehicles are becoming increasingly complex, and the difficulty of maintenance is gradually increasing. When maintenance personnel encounter various difficult problems during vehicle maintenance, they need to search for specific problems in various database websites, books and search engines to obtain accurate maintenance solutions.

[0003] Existing maintenance solutions are mainly based on fault codes. When the electronic control unit (ECU) of a vehicle detects an abnormality in the vehicle system, it will generate a fault code. Technicians read the fault code and look for the corresponding fault cause and maintenance suggestions in the maintenance manual or related database provided by the car manufacturer. However, this method requires maintenance personnel to spend a lot of time and energy to search for information in many scattered information sources. The whole process is cumbersome and complicated, and the efficiency is extremely low, which seriously affects the progress of maintenance.

[0004] Therefore, how to obtain accurate maintenance plans in a timely manner to improve maintenance efficiency and reduce vehicle downtime has become an urgent problem to be solved. Summary of the invention

[0005] The embodiments of the present application provide an intelligent maintenance plan recommendation method, system and related products based on intelligent voice, which receives the voice data of the target user for the maintenance of the target car and analyzes the problem type, obtains feedback information or determines keywords for the problem feedback type and the problem query type to further determine the corresponding maintenance strategy and push it, thereby achieving timely acquisition of accurate maintenance plans to improve maintenance efficiency and quality.

[0006] In a first aspect, an embodiment of the present application provides an intelligent maintenance solution recommendation method based on intelligent voice, which is applied to an on-board diagnostic device, and the method includes:

[0007] receiving first voice data of a target user for target car maintenance;

[0008] The first voice data is parsed to obtain target question content and a corresponding target question type; the target question type includes one of the following: a question feedback type and a question query type; the question feedback type is used to characterize that the target user feeds back fault information of the target car repair and obtains a fault repair strategy corresponding to the fault information, and the question query type is used to characterize that the target user queries for fault repair help information corresponding to the target car repair;

[0009] When the target question type is the question feedback type, displaying the target guidance content corresponding to the target question content, instructing the target user to reply to the target guidance content, and receiving target feedback information for the target guidance content fed back by the target user;

[0010] Determine a first maintenance strategy according to the target question content and the target feedback information, and push the first maintenance strategy to the target user;

[0011] When the target question type is the question query type, a second maintenance strategy is determined according to the target question content, and the second maintenance strategy is pushed to the target user.

[0012] In a second aspect, an embodiment of the present application provides an intelligent maintenance solution recommendation system based on intelligent voice, which is applied to an on-board diagnostic device. The intelligent maintenance solution recommendation system based on intelligent voice includes: a voice receiving module, a voice parsing module, a feedback information receiving module, a first strategy determination module, and a second strategy determination module, wherein:

[0013] The voice receiving module is used to receive first voice data of a target user for target car maintenance;

[0014] The speech analysis module is used to analyze the first speech data to obtain the target question content and the corresponding target question type; the target question type includes one of the following: a question feedback type and a question query type; the question feedback type is used to indicate that the target user feedbacks the fault information of the target car repair and obtains the fault repair strategy corresponding to the fault information, and the question query type is used to indicate that the target user queries the fault repair help information corresponding to the target car repair;

[0015] The feedback information receiving module is used to display the target guidance content corresponding to the target question content when the target question type is the question feedback type, instruct the target user to reply to the target guidance content, and receive the target feedback information fed back by the target user for the target guidance content;

[0016] The first strategy determination module is used to determine a first maintenance strategy according to the target problem content and the target feedback information, and push the first maintenance strategy to the target user;

[0017] The second strategy determination module is used to determine a second maintenance strategy according to the target question content when the target question type is the question query type, and push the second maintenance strategy to the target user.

[0018] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the embodiment of the present application.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiment of the present application.

[0020] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0021] It can be seen that the following beneficial effects are achieved by using the embodiments of the present application:

[0022] By implementing the embodiment of the present application, the first voice data of the target user for target car maintenance can be received; the first voice data is parsed to obtain the target question content and the corresponding target question type; when the target question type is the problem feedback type, the target guidance content corresponding to the target question content is displayed, and the target user is instructed to reply to the target guidance content, and the target feedback information for the target guidance content fed back by the target user is received; the first maintenance strategy is determined according to the target question content and the target feedback information, and the first maintenance strategy is pushed to the target user; when the target question type is the problem query type, the second maintenance strategy is determined according to the target question content, and the second maintenance strategy is pushed to the target user. It can be seen that the target user interacts with the on-board diagnostic device through voice to determine the corresponding maintenance strategy for different problem types, so as to obtain accurate maintenance solutions in a timely manner to improve maintenance efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background technology, the drawings required for use in the embodiments of the present application or the background technology will be described below.

[0024] Figure 1 It is a flowchart of an intelligent maintenance solution recommendation method based on intelligent voice provided in an embodiment of the present application;

[0025] Figure 2It is a structural diagram of an intelligent maintenance solution recommendation system based on intelligent voice provided in an embodiment of the present application;

[0026] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described 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, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0029] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] The following is an explanation of the relevant contents, concepts, meanings, technical issues, technical solutions, beneficial effects, etc. involved in the embodiments of the present application.

[0031] See also Figure 1 , Figure 1 : is a flow chart of an intelligent maintenance solution recommendation method based on intelligent voice provided in an embodiment of the present application. The method is applied to an on-board diagnostic device, and the method includes but is not limited to the following steps:

[0032] S101: Receive first voice data of a target user for target car maintenance.

[0033] In an embodiment of the present application, the application software carried by the on-board diagnostic device is provided with an intelligent AI robot, which is presented in a floating form on the application software to ensure that the target user can interact with it conveniently.

[0034] When the target user encounters difficulties during the maintenance process and urgently needs maintenance help, he can wake up the intelligent AI robot by saying a pre-set wake-up word or clicking a specific material wake-up shortcut key on the application software. At this time, the intelligent AI robot actively asks the user about the specific problem encountered based on the built-in text terminology library, and receives the target user's first voice data for the target car repair. Among them, the first voice data represents the target user's voice data that describes the vehicle's fault phenomenon or maintenance needs in detail. Through human-computer interaction between the intelligent AI robot and the target user, the convenience and naturalness of the interaction between the user and the on-board diagnostic equipment can be improved, thereby quickly conveying maintenance needs and improving maintenance efficiency.

[0035] In one possible embodiment, the target user encounters a problem during the diagnosis process. After waking up the intelligent AI robot with a pre-set wake-up word, the target user describes "I crashed during the diagnosis process, please help me see how to deal with it", and the intelligent AI robot uses this problem description as the first voice data. Of course, the target user can also describe "I don't know how to fix this problem, can you help open the corresponding maintenance database?" The intelligent AI robot also uses this problem description as the first voice data. The intelligent AI robot can also conduct multiple rounds of dialogue with the target user to identify the voice data described by the target user when repairing the target car as the first voice data.

[0036] S102: Analyze the first voice data to obtain target question content and corresponding target question type.

[0037] In the embodiment of the present application, the target question type includes one of the following: a question feedback type and a question query type. The question feedback type is used to characterize that the target user feedbacks the fault information of the target car repair and obtains the fault repair strategy corresponding to the fault information, and the question query type is used to characterize that the target user queries the fault repair help information corresponding to the target car repair.

[0038] In a specific embodiment, the recognized first voice data can be parsed to extract key information in the first voice data, and obtain the target problem content and the corresponding target problem type for the target car to be repaired. For example, in the voice signal processing stage of the first voice data, an adaptive filtering technology can be used to remove the background noise generated by the complex environment in the car, such as the roar of the engine, etc., to enhance the clarity and recognizability of the voice signal. At the same time, a voice feature extraction algorithm is used to extract key features such as the frequency, amplitude, and duration of the voice, and natural language processing is performed based on these key features to identify the target problem content and the corresponding target problem type in the first voice data.

[0039] Furthermore, the language model trained based on the text data in the field of automobile maintenance can be used to perform text conversion and semantic analysis on the first voice data after feature extraction. The language model divides the text into words through lexical analysis, marks the part of speech, and identifies key elements such as automobile component names, fault description vocabulary, and operation verbs. Then, the grammatical structure of the sentence is constructed using syntactic analysis to determine the logical relationship between the elements. For example, if the sentence structure is "certain component + occurrence + fault description", the question can be determined as a question feedback type, where "certain component" and "fault description" constitute the target question content. If the sentence structure is "search / obtain + maintenance information related vocabulary + about + automobile system or component", the question can be determined as a question query type, and the corresponding "maintenance information related vocabulary" and "automobile system or component" become the target question content.

[0040] By interacting with target users through intelligent AI robots, user needs can be classified quickly and accurately, and the focus can be placed on user needs for specific processing, thus avoiding wasting resources on unnecessary analysis and greatly improving maintenance efficiency.

[0041] Optionally, the step of parsing the first voice data to obtain the target question content and the corresponding target question type specifically includes the following steps:

[0042] S1021, recognizing the first voice data to obtain the target question content;

[0043] S1022, analyzing the target question content based on a preset natural language processing model to obtain a target classification result; the preset natural language processing model is trained based on a preset text term library; the preset text term library includes question texts corresponding to the question feedback type and the question query type;

[0044] S1023: When the target classification result meets a preset classification condition, determining that the target question type is the question feedback type;

[0045] S1024. Otherwise, when the target classification result does not meet the preset classification condition, determine that the target question type is the question query type.

[0046] Among them, the preset natural language processing model is a model used to parse the text converted from voice data and determine the target question type. It can be a model architecture based on a recurrent neural network or its variants such as a long short-term memory network, which can process semantic relationships in text sequences.

[0047] Among them, the preset text term library refers to the question text library constructed for training the preset natural language processing model, which includes question texts corresponding to question feedback types and question query types, so that when the model analyzes the target question content, it can quickly and effectively match and compare with the terms in the library, thereby accurately judging the target question type.

[0048] Among them, the preset classification condition refers to the pre-set judgment rule used to determine whether the target problem classification belongs to the problem feedback type. It is determined by factors such as vocabulary combination, semantic tendency and sentence structure in the target problem content. For example, if the target problem content contains a combination of the name of the specific automobile parts and the description of the fault phenomenon such as "fault", "abnormality" and "damage", and also has semantic expressions such as "how to solve" and "how to deal with" to seek solutions, then the preset classification condition of the problem feedback type is met. If the target problem content contains query verbs such as "find", "provide" and "obtain" and words related to maintenance help materials such as "maintenance information", "technical documents" and "case analysis", and no obvious fault feedback semantics appear, it is determined that it does not meet the preset classification condition, and the target problem type corresponding to the target problem content is the problem query type. By diverting the target problem content, it is ensured that the intelligent AI robot can accurately identify user needs and take corresponding subsequent processing steps, thereby improving the efficiency and accuracy of the entire maintenance solution recommendation process.

[0049] In a specific embodiment, the first voice data can be identified to obtain the target question content, and the target question content can be analyzed based on a preset natural language processing model to obtain a target classification result. When the target classification result meets the preset classification condition, the target question type is determined to be a problem feedback type. Otherwise, when the target classification result does not meet the preset classification condition, the target question type is determined to be a problem query type. By accurately distinguishing the different demand types of the target users, targeted maintenance strategies can be provided.

[0050] S103. When the target question type is the question feedback type, display the target guidance content corresponding to the target question content, instruct the target user to reply to the target guidance content, and receive target feedback information for the target guidance content fed back by the target user.

[0051] In the embodiment of the present application, the on-board diagnostic device may further include a display screen and a user feedback interface, wherein the display screen is used to display text information or image information, and the user feedback interface is used to receive user feedback information. The application software of the on-board diagnostic device may also have a guidance content database constructed based on historical automobile maintenance cases and professional knowledge, which can be used to determine the target guidance content corresponding to the target problem content.

[0052] In a specific embodiment, after determining that the target question type is a question feedback type by parsing the first voice data, the target guidance content corresponding to the target question content can be displayed, and the target guidance content can instruct the target user to reply. For example, the target guidance content can be displayed through voice prompts or the display screen of the on-board diagnostic device, wherein the target guidance content can be used to instruct the target user to upload a log of the target car fault phenomenon, upload scene pictures, describe the specific fault situation, etc. After receiving these instructions, the target user can feedback information on the target guidance content through voice or on the user feedback interface provided by the on-board diagnostic device, and this information becomes the target feedback information.

[0053] For example, if the target problem is that the power of the car engine suddenly drops, the target guidance content can be "Please upload the log information corresponding to the car power system, and describe in detail the driving state under which the power drop occurs, such as high-speed driving or climbing a slope. Please tell how often this situation occurs, whether it occurs once in a while or frequently." The target user can upload logs and pictures related to the fault and describe them in detail on the user feedback interface provided by the on-board diagnostic device according to the target guidance content.

[0054] By obtaining more detailed and targeted target feedback information from target users, targeted processing can be performed based on the target feedback information to determine the final maintenance strategy, thereby effectively improving the efficiency of the entire maintenance problem solving process.

[0055] Optionally, the target feedback information includes: target log information, target picture information and target question description information. The step of receiving the target feedback information for the target guidance content fed back by the target user specifically includes the following steps:

[0056] A user feedback interface is displayed according to the target guidance content, and the user feedback interface includes: a log upload control, a picture upload control and a problem description control; in response to a first upload operation on the log upload control, the target log information is obtained; in response to a second upload operation on the picture upload control, the target picture information is obtained; in response to a first interactive operation on the problem description control, the target problem description information is obtained; the first interactive operation is used to represent the text input or voice input of the target user.

[0057] In a specific embodiment, a user feedback interface may be displayed according to the target guidance content, wherein the user feedback interface includes controls such as a log upload control, a picture upload control, and a problem description control, for receiving user feedback information.

[0058] Among them, the log upload control is used to obtain the target log information. During daily operation, the on-board diagnostic equipment will continuously record the operating data of various vehicle systems, such as the change curves of parameters such as engine speed, temperature, oil pressure over time, and various event logs generated by the vehicle electronic control unit. When the target user clicks the log upload control (i.e., performs the first upload operation), the log upload control can filter out log information that may be related to the current problem from the local storage system of the target car, organize and extract it, and upload it as the target log information to the vehicle diagnostic equipment for subsequent analysis.

[0059] The image upload control is used to obtain target image information related to the target vehicle fault. During the vehicle maintenance process, the image upload control can be used to upload images of the vehicle's appearance, damaged parts, actual status of internal components, etc., for analysis of vehicle fault diagnosis. The target user can use the camera of the on-board diagnostic device or the pictures taken to click the image upload control (i.e., perform the second upload operation) to select pictures related to the fault, such as photos of abnormal wear of a component in the engine compartment or damaged pictures of the vehicle chassis. These selected pictures become target image information, which can be processed by image recognition and feature extraction to assist in fault diagnosis.

[0060] The problem description control is used to receive target problem description information. The target user can enter text in the control area to describe in detail the specific fault situation when the fault occurs and other more detailed information, such as "When the vehicle accelerates, the engine feels obvious frustration." At the same time, the problem description control also supports voice input. After the user clicks the voice button on the control, he can directly speak the problem description, and the voice is converted into text through voice recognition technology, which is also collected and processed as the target problem description information.

[0061] Through the user feedback interface, target log information, target image information and target problem description information are collected comprehensively and multi-dimensionally, which can be used to analyze the cause of the fault and formulate accurate maintenance strategies, thereby improving the accuracy and reliability of diagnosis and effectively improving the efficiency and quality of automobile maintenance.

[0062] S104: Determine a first maintenance strategy according to the target problem content and the target feedback information, and push the first maintenance strategy to the target user.

[0063] In a specific embodiment, the target problem content and target feedback information can be integrated and deeply analyzed, and then the first maintenance strategy for repairing the target vehicle can be determined based on the target problem content and target feedback information based on the automobile historical maintenance case database, automobile engineering knowledge system, or an intelligent algorithm trained by machine learning.

[0064] After obtaining the first maintenance strategy, the maintenance steps, required tools and precautions can be displayed in the form of pictures and texts through the display screen of the on-board diagnostic device. At the same time, the voice broadcast function on the on-board diagnostic device can be used to explain the key operating points in detail. In this way, it can be ensured that the target user can fully and accurately receive the first maintenance strategy and perform maintenance operations according to the first maintenance strategy, effectively improving the efficiency and quality of automobile maintenance and reducing the difficulty and uncertainty of maintenance.

[0065] Optionally, the step of determining the first maintenance strategy according to the target problem content and the target feedback information specifically includes the following steps:

[0066] Determine a target fault type according to the target problem content and the target feedback information; search for the first maintenance strategy corresponding to the target fault type based on a preset maintenance strategy mapping table; the preset maintenance strategy mapping table represents a mapping relationship between fault types and maintenance strategies.

[0067] The preset maintenance strategy mapping table includes a mapping relationship between fault types and maintenance strategies, which records in detail the corresponding relationship between various fault types and corresponding maintenance strategies.

[0068] In a specific embodiment, the target fault type can be determined based on the target problem content and the target feedback information, and specifically, a comprehensive analysis can be performed on the key descriptions in the target problem content, such as the name of the automobile component, the manifestation of the fault phenomenon, etc., as well as the abnormal vehicle operating parameters contained in the target log information in the target feedback information, the component damage or abnormal characteristics presented in the target image information, and the detailed description supplemented by the target user in the target problem description information. Then, the first maintenance strategy corresponding to the target fault type can be searched based on the preset maintenance strategy mapping table.

[0069] For example, when the target car has a fault problem related to vehicle software (vehicle software and application software), the relevant logs can be pushed to the corresponding professional engineering team, and the submission status can be fed back to the target user. When it is determined that the target car needs a software upgrade, the upgrade process can be initiated with the target user's consent. When it is determined that the target user has an operational error during the maintenance process, the on-board diagnostic equipment can provide a manual guidance option. After the target user selects, a video connection can be established through the application software to guide the target user to perform maintenance operations online.

[0070] Optionally, the step of determining the target fault type according to the target problem content and the target feedback information specifically includes the following steps:

[0071] S1031, analyzing the target log information according to a preset relationship extraction model to obtain a target problem feature; the target problem feature includes at least one problem feature, each problem feature represents a fault type;

[0072] S1032, identifying image features of the target image information to obtain target image features; the target image features include at least one image characteristic, and each image feature represents a fault type;

[0073] S1033, matching the fault type corresponding to each problem feature in the target problem feature with the fault type corresponding to each image feature in the target image feature, to obtain at least one fault type that is successfully matched;

[0074] S1034, determining keywords in the target question content to obtain a first keyword;

[0075] S1035, determining a keyword in the target problem description information to obtain a second keyword;

[0076] S1036. Filter the at least one fault type according to the first keyword and the second keyword to obtain the target fault type.

[0077] Among them, the preset relationship extraction model refers to an intelligent analysis model built based on a deep learning architecture, which can be used to identify and extract various logical relationships and key feature information closely related to automobile failures from complex target log information.

[0078] In a specific embodiment, the target log information can be analyzed according to a preset relationship extraction model to obtain target problem features, wherein the target problem features include at least one problem feature, and each problem feature represents a fault type. For example, in the target log information, if the engine-related log shows that the fuel injection amount continues to fluctuate abnormally within a certain period of time, the ignition timing deviates, and the engine speed is unstable, then the preset relationship extraction model will extract target problem features such as "abnormal fuel injection", "ignition timing failure", and "unstable speed" therefrom, and each problem feature can correspond to a fault type.

[0079] Next, the image features of the target image information can be identified to obtain the target image features, wherein the target image features include at least one image characteristic, and each image feature represents a fault type. For example, for a picture of a component of an automobile brake system, image features such as uneven wear marks on the surface of the brake disc, brake pad thickness below a normal threshold, and shadows of suspected leakage in the brake fluid pipeline can be identified. These are defined as target image features, and each image feature can correspond to a fault type.

[0080] Furthermore, the fault type corresponding to each problem feature in the target problem feature is matched with the fault type corresponding to each image feature in the target image feature to obtain at least one fault type that is successfully matched. The keywords in the target problem content are determined to obtain the first keyword, and the keywords in the target problem description information are determined to obtain the second keyword, wherein the first keyword and the second keyword both represent the text of the core features of the fault and related background information, and these keywords can represent the specific location and manifestation of the fault. At least one fault type is screened according to the first keyword and the second keyword, and specifically, the correlation between the first keyword and the second keyword and each fault type in the at least one fault type can be calculated. According to the correlation, the fault type with a stronger correlation can be determined to obtain the target fault type.

[0081] Among them, when calculating the correlation between the first keyword and the second keyword and a certain fault type, the natural language processing technology can be used to convert the first keyword and the second keyword into semantic vectors. For the fault type, its related semantic description can also be extracted based on the pre-built automobile fault knowledge graph and converted into a semantic vector. Then, the correlation between the keyword semantic vector and the fault type semantic vector is calculated through the cosine similarity algorithm. The correlation can reflect the closeness between the keyword and the fault type at the semantic level.

[0082] S105: When the target question type is the question query type, determine a second maintenance strategy according to the target question content, and push the second maintenance strategy to the target user.

[0083] In a specific embodiment, after determining that the target question type is a problem feedback type by parsing the first voice data, the second maintenance strategy can be determined according to the content of the target question, and the second maintenance strategy can be pushed to the target user. For example, if the content of the target question involves a query of maintenance information of the automobile brake system, the key information will be extracted first, such as keywords such as "brake system" and "maintenance information", and then the pre-built automobile maintenance database will be accessed. The database covers a wealth of maintenance manuals, technical documents, fault case analysis and other materials for various automobile systems, and is classified, stored and indexed according to multiple dimensions such as vehicle models, systems, and fault types. Then, partial information that meets user needs is retrieved according to keywords and a second maintenance strategy is generated based on the partial information. Among them, the content extracted, analyzed and integrated from different materials is combined to generate a complete, organized and operational second maintenance strategy.

[0084] Optionally, corresponding information can be retrieved from various automobile maintenance information storage websites according to the content of the target question. These websites include practical experience shared by automobile industry experts and maintenance technicians, cutting-edge maintenance technical documents, and detailed troubleshooting and handling cases of various models. The second maintenance strategy can be generated based on the information on these websites.

[0085] After obtaining the second maintenance strategy, the second maintenance strategy can be displayed in the form of pictures and texts through the display screen of the on-board diagnostic device, and explained to the target user using the voice broadcast function of the on-board diagnostic device, ensuring that the target user can fully understand and master the information, thereby effectively assisting the user in performing automobile maintenance work and improving the accuracy and efficiency of maintenance.

[0086] Optionally, the step of determining the second maintenance strategy according to the target problem content specifically includes the following steps:

[0087] S1051, determining keywords in the target question content to obtain n keywords, where n is an integer greater than 1;

[0088] S1052, when m keywords among the n keywords are preset keywords, obtaining the model VIN code and fault code of the target car; the preset keywords are used to represent the file type that the target user needs to query; m is a positive integer less than or equal to n;

[0089] S1053, acquiring a maintenance database corresponding to the m keywords to obtain a target maintenance database;

[0090] S1054, searching the target maintenance data library according to the vehicle model VIN code, the fault code, and other keywords among the n keywords except the m keywords to obtain target maintenance data;

[0091] S1055: Determine the second maintenance strategy according to the target maintenance data.

[0092] Among them, the preset keywords are used to characterize the file types that the target users need to query. The keyword classification set can be set in advance to classify and divide keywords with different purposes so as to accurately identify the file types that the target users expect to obtain, and then conduct targeted data search and strategy generation.

[0093] In a specific embodiment, key descriptive keywords in the target question content are determined to obtain n keywords, where n is an integer greater than 1. When m keywords among the n keywords are preset keywords, the model VIN code and fault code of the target car are obtained, where m is a positive integer less than or equal to n. A maintenance database corresponding to the m keywords can be obtained through a local storage database, an online service platform, a cloud storage database, and other platforms to obtain a target maintenance database. The target maintenance database is searched according to the model VIN code, the fault code, and other keywords among the n keywords except the m keywords to obtain the target maintenance data, and the second maintenance strategy can be determined according to the target maintenance data.

[0094] For example, when the target question content is "I want to query the maintenance manual and troubleshooting steps for the case of car engine shaking and insufficient power", the target question content is first subjected to keyword extraction operation, and n keywords such as "engine", "shaking", "lack of power", "maintenance manual", and "troubleshooting steps" can be extracted. Then, the keywords that are preset keywords are selected from the n keywords to obtain m keywords such as "maintenance manual" and "troubleshooting steps". The target maintenance database corresponding to the m keywords, the model VIN code and fault code of the target car are obtained. The target maintenance database can be searched according to the model VIN code, fault code and other keywords of the n keywords except the m keywords to obtain the target maintenance data, among which the other keywords of the n keywords except the m keywords are "engine", "shaking", "lack of power" and other keywords that reflect the specific situation of the fault. By extracting the target maintenance data, key information such as maintenance methods, operation sequence, required tools and precautions are obtained, and these key information are sorted and integrated to generate a second maintenance strategy suitable for the current target problem.

[0095] Optionally, the target vehicle maintains a communication connection with the on-board diagnostic device, and the following steps may also be included:

[0096] When the target vehicle is in a maintenance state, the working data of the target vehicle during the maintenance process is obtained to obtain first working data; the first working data is matched with first preset working data to obtain a first matching value; the first preset working data is the working data of the target vehicle in a normal state corresponding to the first maintenance strategy; when the first matching value satisfies a first preset condition, it is determined that the target vehicle has been repaired.

[0097] The first preset working data refers to the working data of the target vehicle under normal conditions corresponding to the first maintenance strategy. For example, when the fuel injection system of the vehicle is working normally, the fuel injection pressure is maintained within a specific reasonable range under different working conditions of the vehicle. Similarly, the engine speed also has a corresponding standard stable value range, etc. These standard data constitute the first preset working data.

[0098] In a specific embodiment, after the first maintenance strategy is pushed to the target user, the target user performs maintenance on the target car, and the on-board diagnostic device can collect in real time the working data reflecting the actual operating status of each component of the target car during the maintenance operation to obtain the first working data. For example, when the engine is being maintained, key parameter information such as the real-time oil temperature value, the change of the fuel injection pressure, and the real-time engine speed during the operation of the engine can be obtained as the first working data.

[0099] The first working data is matched with the first preset working data, and various parameters in the first working data are calculated and compared with the corresponding standard parameters in the first preset working data to determine the degree of difference between the parameters and the standard parameters, and further obtain a first matching value. When the first matching value satisfies a first preset condition, it is determined that the target vehicle has been repaired, wherein the first preset condition is an indicator for determining whether the repair is up to standard. For example, when the first matching value reaches a set threshold, it means that the working state of the target vehicle after repair matches the working data in a normal state, and it can be determined that the target vehicle has been repaired, which further indicates that the first maintenance strategy can effectively solve the fault problem existing in the target vehicle, so that the relevant systems of the vehicle are restored to a state that meets the normal operating standards, thereby achieving the expected maintenance goal.

[0100] Optionally, the target vehicle maintains a communication connection with the on-board diagnostic device, and the following steps may also be included:

[0101] When the target vehicle is in a maintenance state, the working data of the target vehicle during the maintenance process is obtained to obtain second working data; the second working data is matched with second preset working data to obtain a second matching value; the second preset working data is the working data of the target vehicle in a normal state corresponding to the second maintenance strategy; when the second matching value satisfies a second preset condition, it is determined that the target vehicle has been repaired.

[0102] In a specific embodiment, after the second maintenance strategy is pushed to the target user, the target user performs maintenance on the target car. During the maintenance process, the on-board diagnostic device collects the operating data of the relevant systems of the target car in real time as the second working data. For example, when the automobile brake system is maintained, the brake fluid pressure change, brake disc temperature and other data are collected as the second working data. Then, the second working data is matched with the second preset working data to obtain a second matching value, where the second preset working data refers to the working data of the components of the target car under normal conditions determined by the second maintenance strategy. If the second matching value satisfies the second preset condition, it is determined whether the second matching value reaches the set judgment threshold. If it reaches, it is determined that the target car has been repaired and the maintenance workflow is completed.

[0103] In summary, by implementing the embodiment of the present application, the first voice data of the target user for target car maintenance can be received; the first voice data is parsed to obtain the target question content and the corresponding target question type; when the target question type is the problem feedback type, the target guidance content corresponding to the target question content is displayed, and the target user is instructed to reply to the target guidance content, and the target feedback information for the target guidance content fed back by the target user is received; the first maintenance strategy is determined according to the target question content and the target feedback information, and the first maintenance strategy is pushed to the target user; when the target question type is the problem query type, the second maintenance strategy is determined according to the target question content, and the second maintenance strategy is pushed to the target user. It can be seen that the target user interacts with the on-board diagnostic device through voice to determine the corresponding maintenance strategy for different problem types, so as to obtain accurate maintenance solutions in a timely manner to improve maintenance efficiency and quality.

[0104] See also Figure 2 , Figure 2 200 is a structural diagram of an intelligent maintenance solution recommendation system based on intelligent voice provided in an embodiment of the present application. The intelligent maintenance solution recommendation system based on intelligent voice 200 is applied to an on-board diagnostic device. The system includes: a voice receiving module 201, a voice parsing module 202, a feedback information receiving module 203, a first strategy determination module 204, and a second strategy determination module 205, wherein:

[0105] The voice receiving module 201 is used to receive first voice data of a target user for target car maintenance;

[0106] The speech analysis module 202 is used to analyze the first speech data to obtain the target question content and the corresponding target question type; the target question type includes one of the following: a question feedback type and a question query type; the question feedback type is used to indicate that the target user feedbacks the fault information of the target car repair and obtains the fault repair strategy corresponding to the fault information, and the question query type is used to indicate that the target user queries the fault repair help information corresponding to the target car repair;

[0107] The feedback information receiving module 203 is used to display the target guidance content corresponding to the target question content when the target question type is the question feedback type, and instruct the target user to reply to the target guidance content, and receive the target feedback information fed back by the target user for the target guidance content;

[0108] The first strategy determination module 204 is used to determine a first maintenance strategy according to the target problem content and the target feedback information, and push the first maintenance strategy to the target user;

[0109] The second strategy determination module 205 is used to determine a second maintenance strategy according to the target question content when the target question type is the question query type, and push the second maintenance strategy to the target user.

[0110] Optionally, in the aspect of parsing the first voice data to obtain target question content and corresponding target question type, the voice parsing module 202 is further specifically used for:

[0111] Recognize the first voice data to obtain the target question content;

[0112] The target question content is analyzed based on a preset natural language processing model to obtain a target classification result; the preset natural language processing model is trained based on a preset text term library; the preset text term library includes question texts corresponding to the question feedback type and the question query type;

[0113] When the target classification result meets the preset classification condition, determining the target question type as the question feedback type;

[0114] Otherwise, when the target classification result does not meet the preset classification condition, the target question type is determined to be the question query type.

[0115] Optionally, the target feedback information includes: target log information, target picture information and target question description information; in terms of receiving the target feedback information for the target guidance content fed back by the target user, the feedback information receiving module 203 is further specifically used to:

[0116] Displaying a user feedback interface according to the target guidance content, the user feedback interface including: a log upload control, a picture upload control and a problem description control;

[0117] In response to a first upload operation on the log upload control, obtaining the target log information;

[0118] In response to a second upload operation on the picture upload control, obtaining the target picture information;

[0119] In response to a first interactive operation on the question description control, the target question description information is obtained; the first interactive operation is used to represent the text input or voice input of the target user.

[0120] Optionally, in determining the first maintenance strategy according to the target problem content and the target feedback information, the feedback information receiving module 203 is further specifically used for:

[0121] Determine a target fault type according to the target problem content and the target feedback information;

[0122] The first maintenance strategy corresponding to the target fault type is searched based on a preset maintenance strategy mapping table; the preset maintenance strategy mapping table represents a mapping relationship between fault types and maintenance strategies.

[0123] Optionally, in determining the target fault type according to the target problem content and the target feedback information, the feedback information receiving module 203 is further specifically configured to:

[0124] Analyze the target log information according to a preset relationship extraction model to obtain a target problem feature; the target problem feature includes at least one problem feature, each problem feature represents a fault type;

[0125] Identify the image features of the target image information to obtain target image features; the target image features include at least one image characteristic, and each image feature represents a fault type;

[0126] Matching the fault type corresponding to each problem feature in the target problem feature with the fault type corresponding to each image feature in the target image feature to obtain at least one fault type that is successfully matched;

[0127] Determine the keywords in the target question content to obtain a first keyword;

[0128] Determine the keyword in the target problem description information to obtain a second keyword;

[0129] The at least one fault type is screened according to the first keyword and the second keyword to obtain the target fault type.

[0130] Optionally, in determining the second maintenance strategy according to the target problem content, the second strategy determination module 205 is further specifically configured to:

[0131] Determine the keywords in the target question content to obtain n keywords, where n is an integer greater than 1;

[0132] When m keywords among the n keywords are preset keywords, the model VIN code and fault code of the target car are obtained; the preset keywords are used to represent the file type that the target user needs to query; m is a positive integer less than or equal to n;

[0133] Acquire a maintenance database corresponding to the m keywords to obtain a target maintenance database;

[0134] According to the vehicle model VIN code, the fault code and other keywords among the n keywords except the m keywords, the target maintenance data is searched in the target maintenance data library to obtain the target maintenance data;

[0135] The second maintenance strategy is determined according to the target maintenance data.

[0136] Optionally, the target vehicle maintains a communication connection with the on-board diagnostic device; and the system is further specifically used for:

[0137] When the target vehicle is in a maintenance state, obtaining working data of the target vehicle during the maintenance process to obtain first working data;

[0138] Matching the first working data with first preset working data to obtain a first matching value; the first preset working data is working data of the target vehicle in a normal state corresponding to the first maintenance strategy;

[0139] When the first matching value satisfies a first preset condition, it is determined that the target vehicle has been repaired.

[0140] Optionally, the target vehicle maintains a communication connection with the on-board diagnostic device; and the system is further specifically used for:

[0141] When the target vehicle is in a maintenance state, obtaining working data of the target vehicle during the maintenance process to obtain second working data;

[0142] Matching the second working data with second preset working data to obtain a second matching value; the second preset working data is working data of the target vehicle in a normal state corresponding to the second maintenance strategy;

[0143] When the second matching value satisfies a second preset condition, it is determined that the target vehicle has been repaired.

[0144] The intelligent voice-based intelligent maintenance solution recommendation system 200 described in this application can receive the first voice data of the target user for the maintenance of the target car; parse the first voice data to obtain the target question content and the corresponding target question type; when the target question type is the problem feedback type, display the target guidance content corresponding to the target question content, and instruct the target user to reply to the target guidance content, and receive the target feedback information for the target guidance content fed back by the target user; determine the first maintenance strategy according to the target question content and the target feedback information, and push the first maintenance strategy to the target user; when the target question type is the problem query type, determine the second maintenance strategy according to the target question content, and push the second maintenance strategy to the target user. It can be seen that the target user interacts with the on-board diagnostic device by voice to determine the corresponding maintenance strategy for different problem types, so as to obtain accurate maintenance solutions in a timely manner to improve maintenance efficiency and quality.

[0145] See also Figure 3 , Figure 3 : is a structural diagram of an electronic device provided in an embodiment of the present application, the electronic device may include a processor, a memory, a communication interface and one or more programs, the processor, the memory and the communication interface may be connected to each other through a bus; the one or more programs are stored in the memory and are configured to be executed by the processor; in an embodiment of the present application, the program is applied to an on-board diagnostic device, and the program includes instructions for executing the following steps:

[0146] receiving first voice data of a target user for target car maintenance;

[0147] The first voice data is parsed to obtain target question content and a corresponding target question type; the target question type includes one of the following: a question feedback type and a question query type; the question feedback type is used to characterize that the target user feeds back fault information of the target car repair and obtains a fault repair strategy corresponding to the fault information, and the question query type is used to characterize that the target user queries for fault repair help information corresponding to the target car repair;

[0148] When the target question type is the question feedback type, displaying the target guidance content corresponding to the target question content, instructing the target user to reply to the target guidance content, and receiving target feedback information for the target guidance content fed back by the target user;

[0149] Determine a first maintenance strategy according to the target question content and the target feedback information, and push the first maintenance strategy to the target user;

[0150] When the target question type is the question query type, a second maintenance strategy is determined according to the target question content, and the second maintenance strategy is pushed to the target user.

[0151] The electronic device described in this application can receive the first voice data of the target user for the target car maintenance; parse the first voice data to obtain the target question content and the corresponding target question type; when the target question type is the problem feedback type, display the target guidance content corresponding to the target question content, and instruct the target user to reply to the target guidance content, and receive the target feedback information for the target guidance content fed back by the target user; determine the first maintenance strategy according to the target question content and the target feedback information, and push the first maintenance strategy to the target user; when the target question type is the problem query type, determine the second maintenance strategy according to the target question content, and push the second maintenance strategy to the target user. It can be seen that the target user interacts with the on-board diagnostic device by voice to determine the corresponding maintenance strategy for different problem types, so as to obtain accurate maintenance solutions in a timely manner to improve maintenance efficiency and quality.

[0152] An embodiment of the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes an electronic device.

[0153] The embodiment of the present application also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes an electronic device.

[0154] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

[0155] The steps of the method or algorithm described in the embodiments of the present application can be implemented in hardware or by executing software instructions by a processor. The software instructions can be composed of corresponding software modules, and the software modules can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (electrically EPROM, EEPROM), registers, hard disks, mobile hard disks, read-only compact disks (CD-ROMs) or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in a terminal device or a management device. Of course, the processor and the storage medium can also be present in a terminal device or a management device as discrete components.

[0156] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0157] The modules / units included in the devices and products described in the above embodiments may be software modules / units or hardware modules / units, or may be partially software modules / units and partially hardware modules / units. For example, for the devices and products applied to or integrated in the chip, the modules / units included therein may all be implemented in the form of hardware such as circuits, or at least some of the modules / units may be implemented in the form of software programs, which run on the processor integrated inside the chip, and the remaining (if any) modules / units may be implemented in the form of hardware such as circuits; for the devices and products applied to or integrated in the chip module, the modules / units included therein may all be implemented in the form of hardware such as circuits, and different modules / units may be located in the same component (such as a chip, circuit module, etc.) or in different components of the chip module, or at least some of the modules / units may be implemented in the form of software programs. The software programs run on the processor integrated inside the chip, and the remaining (if any) modules / units may be implemented in the form of hardware such as circuits. It is implemented in the form of a software program, which runs on a processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in hardware such as circuits; for various devices and products applied to or integrated in the terminal equipment, the various modules / units contained therein can be implemented in hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or in different components in the terminal equipment, or, at least some modules / units can be implemented in the form of a software program, which runs on a processor integrated inside the terminal equipment, and the remaining (if any) modules / units can be implemented in hardware such as circuits.

[0158] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the embodiments of the present application. It should be understood that the above description is only the specific implementation method of the embodiments of the present application and is not intended to limit the protection scope of the embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application should be included in the protection scope of the embodiments of the present application.

Claims

1. An intelligent maintenance plan recommendation method based on intelligent voice, characterized in that: Applied to an on-board diagnostic device, the method comprises: receiving first voice data of a target user for target car maintenance; The first voice data is parsed to obtain target question content and a corresponding target question type; the target question type includes one of the following: a question feedback type and a question query type; the question feedback type is used to characterize that the target user feeds back fault information of the target car repair and obtains a fault repair strategy corresponding to the fault information, and the question query type is used to characterize that the target user queries for fault repair help information corresponding to the target car repair; When the target question type is the question feedback type, displaying the target guidance content corresponding to the target question content, instructing the target user to reply to the target guidance content, and receiving target feedback information for the target guidance content fed back by the target user; Determine a first maintenance strategy according to the target question content and the target feedback information, and push the first maintenance strategy to the target user; When the target question type is the question query type, a second maintenance strategy is determined according to the target question content, and the second maintenance strategy is pushed to the target user.

2. The method according to claim 1, characterized in that The parsing of the first voice data to obtain target question content and corresponding target question type includes: Recognize the first voice data to obtain the target question content; The target question content is analyzed based on a preset natural language processing model to obtain a target classification result; the preset natural language processing model is trained based on a preset text term library; the preset text term library includes question texts corresponding to the question feedback type and the question query type; When the target classification result meets the preset classification condition, determining the target question type as the question feedback type; Otherwise, when the target classification result does not meet the preset classification condition, the target question type is determined to be the question query type.

3. The method according to claim 1 or 2, characterized in that The target feedback information includes: target log information, target picture information and target question description information; the target feedback information received from the target user for the target guidance content includes: Displaying a user feedback interface according to the target guidance content, the user feedback interface including: a log upload control, a picture upload control and a problem description control; In response to a first upload operation on the log upload control, obtaining the target log information; In response to a second upload operation on the picture upload control, obtaining the target picture information; In response to a first interactive operation on the question description control, the target question description information is obtained; the first interactive operation is used to represent the text input or voice input of the target user.

4. The method according to claim 3, characterized in that The determining of the first maintenance strategy according to the target problem content and the target feedback information includes: Determine a target fault type according to the target problem content and the target feedback information; The first maintenance strategy corresponding to the target fault type is searched based on a preset maintenance strategy mapping table; the preset maintenance strategy mapping table represents a mapping relationship between fault types and maintenance strategies.

5. The method according to claim 4, characterized in that The determining the target fault type according to the target problem content and the target feedback information includes: Analyze the target log information according to a preset relationship extraction model to obtain a target problem feature; the target problem feature includes at least one problem feature, each problem feature represents a fault type; Identify the image features of the target image information to obtain target image features; the target image features include at least one image characteristic, and each image feature represents a fault type; Matching the fault type corresponding to each problem feature in the target problem feature with the fault type corresponding to each image feature in the target image feature to obtain at least one fault type that is successfully matched; Determine the keywords in the target question content to obtain a first keyword; Determine the keyword in the target problem description information to obtain a second keyword; The at least one fault type is screened according to the first keyword and the second keyword to obtain the target fault type.

6. The method according to claim 1 or 2, characterized in that: Determining the second maintenance strategy according to the target problem content includes: Determine the keywords in the target question content to obtain n keywords, where n is an integer greater than 1; When m keywords among the n keywords are preset keywords, the model VIN code and fault code of the target car are obtained; the preset keywords are used to represent the file type that the target user needs to query; m is a positive integer less than or equal to n; Acquire a maintenance database corresponding to the m keywords to obtain a target maintenance database; According to the vehicle model VIN code, the fault code and other keywords among the n keywords except the m keywords, the target maintenance data is searched in the target maintenance data library to obtain the target maintenance data; The second maintenance strategy is determined according to the target maintenance data.

7. The method according to claim 1 or 2, characterized in that: The target vehicle maintains a communication connection with the on-board diagnostic device; after pushing the first maintenance strategy to the target user, the method further includes: When the target vehicle is in a maintenance state, obtaining working data of the target vehicle during the maintenance process to obtain first working data; Matching the first working data with first preset working data to obtain a first matching value; the first preset working data is working data of the target vehicle in a normal state corresponding to the first maintenance strategy; When the first matching value satisfies a first preset condition, it is determined that the target vehicle has been repaired.

8. The method according to claim 1 or 2, characterized in that: The target vehicle maintains a communication connection with the on-board diagnostic device; after pushing the second maintenance strategy to the target user, the method further includes: When the target vehicle is in a maintenance state, obtaining working data of the target vehicle during the maintenance process to obtain second working data; Matching the second working data with second preset working data to obtain a second matching value; the second preset working data is working data of the target vehicle in a normal state corresponding to the second maintenance strategy; When the second matching value satisfies a second preset condition, it is determined that the target vehicle has been repaired.

9. An intelligent maintenance solution recommendation system based on intelligent voice, characterized in that: Applied to on-board diagnostic equipment, the intelligent maintenance solution recommendation system based on intelligent voice includes: a voice receiving module, a voice parsing module, a feedback information receiving module, a first strategy determination module, and a second strategy determination module, wherein: The voice receiving module is used to receive first voice data of a target user for target car maintenance; The speech analysis module is used to analyze the first speech data to obtain the target question content and the corresponding target question type; the target question type includes one of the following: a question feedback type and a question query type; the question feedback type is used to indicate that the target user feedbacks the fault information of the target car repair and obtains the fault repair strategy corresponding to the fault information, and the question query type is used to indicate that the target user queries the fault repair help information corresponding to the target car repair; The feedback information receiving module is used to display the target guidance content corresponding to the target question content when the target question type is the question feedback type, instruct the target user to reply to the target guidance content, and receive the target feedback information fed back by the target user for the target guidance content; The first strategy determination module is used to determine a first maintenance strategy according to the target problem content and the target feedback information, and push the first maintenance strategy to the target user; The second strategy determination module is used to determine a second maintenance strategy according to the target question content when the target question type is the question query type, and push the second maintenance strategy to the target user.

10. An electronic device, characterized in that: include: A processor, a memory, a communication interface, and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, the programs comprising instructions for executing the steps in the method according to any one of claims 1 to 8.

Images