A method and system for personalized push of vehicle fault resolution solutions

Abstract

The application discloses a personalized pushing method and system of a vehicle fault solution, and the method comprises the following steps: acquiring a target scene matched with a vehicle fault code and vehicle scene data in a preset fault scene library according to the acquired vehicle fault code and vehicle scene data; and sending a fault solution previously configured in the target scene to a vehicle terminal, so that the vehicle terminal pushes the fault solution to a user. The application can match a fault scene according to a vehicle fault code and vehicle scene data, and can provide a user with a personalized vehicle fault solution for the matched fault scene by previously configuring different fault solutions in different fault scenes.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, in particular to a personalized pushing method and system of vehicle fault solutions. BACKGROUND

[0002] With the increase of driving time and mileage of vehicles, various types of faults will inevitably occur in vehicles. In the prior art, when a vehicle fault occurs, the user often needs to check the paper manual or electronic manual of the vehicle to obtain the solution to the current fault. However, the solution obtained by the prior art is relatively single, and it is difficult to provide personalized vehicle fault solutions for different fault scenarios. SUMMARY

[0003] The present application provides a personalized pushing method and system of vehicle fault solutions to solve the technical problem that the prior art is difficult to provide personalized vehicle fault solutions for different fault scenarios. The vehicle fault code and vehicle scene data are matched according to the vehicle fault code and vehicle scene data, different fault solutions are pre-configured in different fault scenarios, and personalized vehicle fault solutions are provided for the user according to the matched fault scenario.

[0004] To solve the above technical problem, the first aspect of the embodiment of the present application provides a personalized pushing method of vehicle fault solutions, comprising the following steps:

[0005] According to the obtained vehicle fault code and vehicle scene data, a target scene matching the vehicle fault code and the vehicle scene data is obtained in a preset fault scene library;

[0006] The fault solution pre-configured in the target scene is sent to the vehicle terminal, so that the vehicle terminal pushes the fault solution to the user.

[0007] As a preferred solution, the target scene matching the vehicle fault code and the vehicle scene data in the preset fault scene library specifically comprises the following steps:

[0008] Based on the fault type pre-configured in each scene in the fault scene library, a plurality of matching scenes matching the fault type and the vehicle fault code are obtained;

[0009] According to the vehicle scene data, scene decision is made on the plurality of matching scenes to obtain the target scene.

[0010] As a preferred solution, the target scene matching the vehicle fault code and the vehicle scene data in the preset fault scene library specifically comprises the following steps:

[0011] According to the vehicle scene data, a plurality of current scene features of the vehicle are obtained;

[0012] The current scene features are input into a preset scene decision model, scene decision is performed on the plurality of matching scenes by the scene decision model, and the target scene is obtained.

[0013] As a preferred solution, the method specifically constructs the scene decision model by the following steps:

[0014] According to the push condition pre-configured in each scene in the fault scene library, the root node and the leaf node corresponding to each fault type are constructed, and a decision tree model is constructed according to the root node and the leaf node;

[0015] The decision tree model is trained by using a preset training data set, and the scene decision model is obtained.

[0016] As a preferred solution, the fault solution includes a preferred solution and a secondary solution;

[0017] Then, the fault solution pre-configured in the target scene is sent to the car end, so that the car end pushes the fault solution to the user, and specifically includes:

[0018] The preferred solution and the secondary solution pre-configured in the target scene are sent to the car end, so that the car end pushes the preferred solution and the secondary solution to the user.

[0019] As a preferred solution, the method further includes the following steps:

[0020] In response to a solution selection instruction input by the user, a target solution currently selected by the user is recorded;

[0021] When the target solution is the secondary solution, the fault solution of the target scene is updated to take the secondary solution as the updated preferred solution of the target scene.

[0022] As a preferred solution, the method further includes the following steps:

[0023] In response to a fault request instruction input by the user, voice data of the user is received, and the voice data is recognized to obtain recognized text corresponding to the voice data;

[0024] The recognized text is subjected to keyword extraction, and a plurality of fault recognition texts are obtained by performing semantic expansion processing on the extracted keywords;

[0025] According to the fault identification text, a plurality of fault types matching the fault identification text are determined in the fault scene library, and push information containing the plurality of fault types is sent to the vehicle terminal, so that the vehicle terminal pushes the push information to the user;

[0026] In response to a fault type selection instruction input by the user, a target fault type in the push information is determined;

[0027] A plurality of scenes corresponding to the target fault type are obtained, and scene decision is performed on the plurality of scenes according to current vehicle scene data to obtain a decision scene;

[0028] A fault solution pre-configured in the decision scene is sent to the vehicle terminal, so that the vehicle terminal pushes the fault solution to the user.

[0029] As a preferred solution, the method specifically obtains the vehicle fault code by the following steps:

[0030] The vehicle is detected for faults by a vehicle body detection module pre-configured in the vehicle, and the vehicle fault code sent by the vehicle body detection module is received.

[0031] As a preferred solution, the vehicle scene data at least includes driver information, vehicle location data, in-vehicle light intensity, in-vehicle number of people, current vehicle speed, and current weather conditions.

[0032] The second aspect of the embodiment of the application provides a personalized push system of a vehicle fault solution, including a cloud end and a vehicle terminal end;

[0033] The cloud end is configured to:

[0034] According to the obtained vehicle fault code and vehicle scene data, a target scene matching the vehicle fault code and the vehicle scene data is obtained in a pre-set fault scene library;

[0035] A fault solution pre-configured in the target scene is sent to the vehicle terminal end;

[0036] The vehicle terminal end is configured to:

[0037] The fault solution is pushed to the user.

[0038] Compared with the prior art, the embodiment of the application has the beneficial effect that the matching of the fault scene can be performed according to the vehicle fault code and the vehicle scene data, and by pre-configuring different fault solutions in different fault scenes, the user can be provided with personalized vehicle fault solutions for the matched fault scenes. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 is a flow diagram of a personalized push method of a vehicle fault solution in an embodiment of the present application;

[0040] Figure 2 is a schematic diagram of a scenario decision process in an embodiment of the present application;

[0041] Figure 3 is a structural schematic diagram of a personalized push system of a vehicle fault solution in an embodiment of the present application. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0043] Referring to Figure 1 , the first aspect of the embodiments of the present application provides a personalized push method of a vehicle fault solution, comprising the following steps S1 to S2:

[0044] S1, according to the obtained vehicle fault code and vehicle scene data, obtaining a target scene matched to the vehicle fault code and the vehicle scene data in a preset fault scene library;

[0045] S2, sending a fault solution pre-configured to the target scene to a vehicle terminal, so that the vehicle terminal pushes the fault solution to a user.

[0046] Specifically, when the vehicle fails, the embodiment obtains the current vehicle fault code and vehicle scene data, and obtains a target scene matching the vehicle fault code and vehicle scene data from a plurality of preset scenes in a fault scene library. It should be noted that the vehicle fault code is pre-configured by a cloud administrator for different vehicle fault types before the vehicle model is launched, and the vehicle scene data is obtained by sensing the environment inside and outside the vehicle through the camera, navigation module, built-in weather forecasting software, light sensor, etc. configured in the vehicle, including but not limited to driver identity, driver gender, number of people in the vehicle, vehicle location, weather outside the vehicle, and light intensity inside the vehicle. Since the unified fault solution is not necessarily suitable for all fault scenes, for example, when the tire pressure is too low due to the tire being punctured during driving, the spare tire needs to be replaced, generally speaking, men are stronger than women, so when there is only the driver in the vehicle, if the driver is male, the specific spare tire replacement solution is preferentially pushed to him, and if the driver is female, the telephone number of the nearby automobile repair shop is preferentially pushed to her. Therefore, in order to push different fault solutions for different fault scenes, the current fault scene needs to be confirmed by obtaining the vehicle scene data.

[0047] It should be noted that each scene in the fault scene library is pre-built by the cloud administrator. Specifically, the cloud administrator pre-configures vehicle fault codes and a plurality of fault solutions for each vehicle fault type. It can be understood that each fault solution corresponds to a fault scene, and each fault solution is provided with a push condition. Only when the push condition is met, the solution of the corresponding fault scene is triggered to be pushed. The cloud administrator sets the vehicle fault type, vehicle fault code, push condition and fault solution corresponding to each scene by adding, revising, deleting and other operations, thereby building a fault scene library containing a plurality of scenes.

[0048] Further, after obtaining the target scene, the fault solution pre-configured in the target scene is sent to the vehicle terminal, so that the vehicle terminal pushes the fault solution to the user. For example, the push mode of the fault solution can be played through the speaker in the vehicle, or it can be pushed in the form of text, picture or video on the vehicle central screen. The embodiment is not limited specifically herein.

[0049] The vehicle fault solution personalized push method provided by the embodiment can match the fault scene according to the vehicle fault code and vehicle scene data, and by pre-configuring different fault solutions in different fault scenes, the user can be provided with personalized vehicle fault solutions for the matched fault scene.

[0050] As a preferred solution, the step of obtaining the target scene matching the vehicle fault code and the vehicle scene data in the preset fault scene library comprises the following steps:

[0051] Based on the fault type pre-configured in each scene in the fault scene library, a plurality of matching scenes are obtained, wherein the fault type of each matching scene matches the vehicle fault code.

[0052] According to the vehicle scene data, scene decision is performed on the plurality of matching scenes to obtain the target scene.

[0053] In this embodiment, since each fault type is pre-configured with a corresponding vehicle fault code, and each fault type corresponds to a plurality of different fault scenes, a plurality of matching scenes can be obtained in the fault scene library, wherein the fault type of each matching scene matches the vehicle fault code.

[0054] Further, according to the vehicle scene data, scene decision is performed on the plurality of matching scenes to obtain the target scene.

[0055] As a preferred solution, the step of obtaining the target scene by performing scene decision on the plurality of matching scenes according to the vehicle scene data comprises the following steps:

[0056] According to the vehicle scene data, a plurality of current scene features of the vehicle are obtained.

[0057] The current scene features are input into a preset scene decision model, and scene decision is performed on the plurality of matching scenes by the scene decision model to obtain the target scene.

[0058] Specifically, a plurality of current scene features of the vehicle are obtained by the vehicle scene data, for example, the current vehicle speed is not 0, and the corresponding scene feature is that the vehicle is in a non-stationary state; the number of people in the vehicle is greater than 2, and the corresponding scene feature is that there are many people; the driver is a female driver, and the corresponding scene feature is that the driver is a female.

[0059] Further, the current scene features are input into a preset scene decision model, and scene decision is performed on the plurality of matching scenes by the scene decision model to obtain the target scene.

[0060] For example, referring to Figure 2As shown in the schematic diagram of the scenario decision process provided by the embodiment, first, it is determined by the vehicle speed whether the vehicle is stationary. If yes, the fault solution is preferentially pushed to the user in the form of a video. If no, it is determined whether the current fault belongs to a serious fault. If no, the fault solution is preferentially pushed to the user in the form of a text. If yes, it is determined by the vehicle position whether there is a 4S shop or a car repair shop nearby. If yes, the navigation information of the nearest 4S shop or car repair shop is preferentially provided to the user. If no, it is determined whether the vehicle is in a multi-person state. If yes, a specific repair scheme is preferentially pushed to the user. If no, it is determined whether the driver is male. If yes, a specific repair scheme is preferentially pushed to the user. If no, the phone number of the 4S shop or car repair shop is preferentially provided to the user.

[0061] It is worth noting that each fault type is classified in severity by the cloud administrator in advance, such as being classified into a serious fault and a non-serious fault. Exemplarily, for the fault type belonging to the serious fault, the phone number of the 4S shop is added in the fault solution to facilitate the user to call. For the fault type belonging to the non-serious fault, only the repair suggestion and the fault popularization are provided.

[0062] It is worth noting that, in order to improve the adaptability of the fault scenario, the push condition can be set according to the high-frequency feature and the easily-detected feature. For example, the gender is a high-frequency feature, and the fault severity, the vehicle speed, the vehicle position, and the number of people in the vehicle are easily-detected features.

[0063] As a preferred solution, the method specifically constructs the scenario decision model by the following steps:

[0064] According to the push condition pre-configured in each scenario in the fault scenario library, the root node and the leaf node corresponding to each fault type are constructed, and a decision tree model is constructed according to the root node and the leaf node;

[0065] The decision tree model is trained by using a preset training data set to obtain the scenario decision model.

[0066] It is worth noting that, in the embodiment, the root node and the leaf node corresponding to each fault type are constructed by the push condition pre-configured in each scenario in the fault scenario library. It can be understood that the root node represents the judgment of one of the push conditions, and the leaf node represents the output of the judgment result, i.e., a specific fault scenario. According to the root node and the leaf node corresponding to each fault type, a decision tree model is constructed.

[0067] As a preferred solution, the fault solution includes a preferred solution and a secondary solution.

[0068] The failure solution pre-configured for the target scene is sent to the vehicle terminal, so that the vehicle terminal pushes the failure solution to the user, and specifically includes:

[0069] The preferred solution and the second solution pre-configured for the target scene are sent to the vehicle terminal, so that the vehicle terminal pushes the preferred solution and the second solution to the user.

[0070] Specifically, in order to meet the personalized needs of the user for the failure solution push, the preferred solution and the second solution are pre-configured for each scene, and when the failure solution is pushed to the user, the preferred solution and the second solution are pushed together for the user to select.

[0071] As a preferred solution, the method further includes the following steps:

[0072] In response to the solution selection instruction input by the user, the target solution currently selected by the user is recorded;

[0073] When the target solution is the second solution, the failure solution of the target scene is updated to take the second solution as the updated preferred solution of the target scene.

[0074] Specifically, when the user performs solution selection interaction through the vehicle terminal, in response to the solution selection instruction input by the user, the target solution currently selected by the user is recorded; when the target solution is the second solution, it indicates that the user tends to handle the current vehicle failure through the second solution, so the failure solution of the current target scene is updated to take the second solution as the updated preferred solution of the current target scene, which is pushed as the preferred solution of the target scene in the next push, so as to optimize the personalized push of the failure solution. When the target solution is the preferred solution, it indicates that the user tends to handle the current vehicle failure through the preferred solution, so there is no need to update the failure solution of the current target scene.

[0075] As a preferred solution, the method further includes the following steps:

[0076] In response to the failure request instruction input by the user, the voice data of the user is received, and the voice data is identified to obtain the identified text corresponding to the voice data;

[0077] The identified text is subjected to keyword extraction, and the extracted keywords are subjected to semantic expansion processing to obtain a plurality of failure identification texts;

[0078] According to the fault identification text, a plurality of fault types matched with the fault identification text are determined in the fault scene library, and push information containing the plurality of fault types is sent to the vehicle terminal, so that the vehicle terminal pushes the push information to the user;

[0079] In response to a fault type selection instruction input by the user, a target fault type in the push information is determined;

[0080] A plurality of scenes corresponding to the target fault type are obtained, and scene decision is performed on the plurality of scenes according to current vehicle scene data to obtain a decision scene;

[0081] A fault solution pre-configured in the decision scene is sent to the vehicle terminal, so that the vehicle terminal pushes the fault solution to the user.

[0082] It should be noted that when the vehicle does not perceive that the vehicle has a fault through self-checking, the embodiment can actively request the fault by the user, so as to push the related fault solution to the user based on the fault request of the user.

[0083] In the embodiment, in response to a fault request instruction input by the user, voice data of the user is received, and the voice data is recognized to obtain recognition text corresponding to the voice data, such as "how to adjust the temperature of the air conditioner", "how to handle the expiration of the insurance", "how to deal with the low tire pressure in the vehicle", etc. Key words are extracted from the recognition text, and semantic expansion processing is performed on the extracted plurality of key words to obtain a plurality of fault identification texts. According to the plurality of fault identification texts, a plurality of fault types matched with the fault identification texts are determined in the fault scene library, and push information containing the plurality of fault types is sent to the vehicle terminal, so that the vehicle terminal pushes the push information to the user.

[0084] For example, if the voice text of the user is "what to do if the air conditioner is broken", the key words "air conditioner is broken" are extracted from the recognition text, and then semantic expansion processing is performed on the key words to obtain a plurality of fault identification texts, such as "air conditioner damage" and "air conditioner fault". According to these fault identification texts, a plurality of fault types matched with the fault identification texts are determined in the fault scene library, for example, in the fault scene library, there are 3 different fault types about the air conditioner. Then, push information containing the 3 fault types is sent to the vehicle terminal, so that the vehicle terminal pushes the push information to the user, for example, the central control screen displays: 3 air conditioner related results are found for you, which one do you want to know?

[0085] Further, in response to a user inputted fault type selection instruction, a target fault type in the push information is determined; a plurality of scenes corresponding to the target fault type are acquired, and scene decision is performed on the plurality of scenes according to current vehicle scene data to obtain a decision scene; a fault solution pre-configured in the decision scene is sent to the vehicle terminal, so that the vehicle terminal pushes the fault solution to the user.

[0086] As a preferred solution, the method specifically acquires the vehicle fault code through the following steps:

[0087] The vehicle is detected for fault by a vehicle body detection module pre-configured in the vehicle, and the vehicle fault code sent by the vehicle body detection module is received.

[0088] It is worth noting that the vehicle body detection module in the embodiment includes a plurality of vehicle body sensors for detecting the running state of the vehicle, and the vehicle is detected for fault by the plurality of vehicle body sensors, for example, whether the tire pressure is too low, whether the windshield wiper is abnormal, etc., and when any vehicle body sensor detects a vehicle fault, the vehicle body sensor can generate a corresponding vehicle fault code based on the detected vehicle fault, so that the embodiment can directly receive the vehicle fault code sent by the vehicle body detection module.

[0089] As a preferred solution, the vehicle scene data at least includes driver information, vehicle location data, in-vehicle light intensity, in-vehicle number of people, current vehicle speed, and current weather condition.

[0090] Referring to Figure 3 , the embodiment of the application provides a vehicle fault solution personalized push system, comprising a cloud end 301 and a vehicle terminal 302.

[0091] The cloud end 301 is configured to:

[0092] According to the acquired vehicle fault code and vehicle scene data, a target scene matching the vehicle fault code and the vehicle scene data is acquired in a preset fault scene library;

[0093] A fault solution pre-configured in the target scene is sent to the vehicle terminal 302;

[0094] The vehicle terminal 302 is configured to:

[0095] The fault solution is pushed to the user.

[0096] As a preferred solution, the cloud end 301 is configured to acquire a target scene matching the vehicle fault code and the vehicle scene data in a preset fault scene library, specifically comprising:

[0097] According to the fault type pre-configured in each scene in the fault scene library, a plurality of matching scenes matching the vehicle fault code are obtained;

[0098] According to the vehicle scene data, scene decision is performed on the plurality of matching scenes to obtain the target scene.

[0099] As a preferred solution, the cloud 301 is configured to perform scene decision on the plurality of matching scenes according to the vehicle scene data to obtain the target scene, and specifically includes:

[0100] According to the vehicle scene data, a plurality of current scene features of the vehicle are obtained;

[0101] The current scene features are input into a preset scene decision model, and the scene decision model is used to perform scene decision on the plurality of matching scenes to obtain the target scene.

[0102] As a preferred solution, the cloud 301 is further configured to:

[0103] According to the push condition pre-configured in each scene in the fault scene library, a root node and a leaf node corresponding to each fault type are constructed, and a decision tree model is constructed according to the root node and the leaf node;

[0104] The decision tree model is trained using a preset training data set to obtain the scene decision model.

[0105] As a preferred solution, the fault solution includes a preferred solution and a secondary solution;

[0106] Therefore, the cloud 301 is configured to send a fault solution pre-configured in the target scene to the car end 302, so that the car end 302 pushes the fault solution to the user, and specifically includes:

[0107] The preferred solution and the secondary solution pre-configured in the target scene are sent to the car end 302, so that the car end 302 pushes the preferred solution and the secondary solution to the user.

[0108] As a preferred solution, the car end 302 is further configured to:

[0109] In response to a solution selection instruction input by the user, a target solution currently selected by the user is recorded;

[0110] The cloud 301 is further configured to:

[0111] When the target solution is the sub-selected solution, the failure solution of the target scene is updated to take the sub-selected solution as an updated preferred solution of the target scene.

[0112] As a preferred solution, the car machine end 302 is further configured to:

[0113] In response to a failure request instruction input by a user, receive voice data of the user and identify the voice data to obtain identified text corresponding to the voice data.

[0114] Extract keywords from the identified text and perform semantic expansion processing on the extracted keywords to obtain a plurality of failure identification texts.

[0115] The cloud end 301 is further configured to:

[0116] According to the plurality of failure identification texts, determine a plurality of failure types in the failure scene library that match the failure identification texts, and send push information containing the plurality of failure types to the car machine end 302, so that the car machine end 302 pushes the push information to the user.

[0117] The car machine end 302 is further configured to:

[0118] In response to a failure type selection instruction input by a user, determine a target failure type in the push information.

[0119] The cloud end 301 is further configured to:

[0120] Obtain a plurality of scenes corresponding to the target failure type, and perform scene decision on the plurality of scenes according to current vehicle scene data to obtain a decision scene.

[0121] Send a failure solution pre-configured in the decision scene to the car machine end 302, so that the car machine end 302 pushes the failure solution to the user.

[0122] As a preferred solution, the car machine end 302 is further configured to:

[0123] Perform failure detection on the vehicle through a vehicle body detection module pre-configured in the vehicle, and receive the vehicle failure code sent by the vehicle body detection module.

[0124] As a preferred solution, the vehicle scene data at least includes driver information, vehicle location data, in-vehicle light intensity, in-vehicle number of people, current vehicle speed, and current weather conditions.

[0125] The vehicle fault solution personalized pushing system provided by the embodiment of the application can match fault scenes according to vehicle fault codes and vehicle scene data, and can provide users with personalized vehicle fault solutions for the matched fault scenes by previously configuring different fault solutions in different fault scenes.

[0126] The above is the preferred embodiment of the application. It should be pointed out that, for those skilled in the art, without departing from the principles of the application, a number of improvements and refinements can be made, which are also considered within the protection scope of the application.

Claims

1. A method of personalized push of vehicle fault resolution solutions, characterized in that, The method comprises the following steps: According to the obtained vehicle fault code and vehicle scene data, a target scene matching the vehicle fault code and the vehicle scene data is obtained in a preset fault scene library; The fault solution previously configured in the target scene is sent to the vehicle terminal, so that the vehicle terminal pushes the fault solution to the user; Wherein, the target scene matching the vehicle fault code and the vehicle scene data in the preset fault scene library is obtained, specifically including the following steps: Based on the fault type of each scene previously configured in the fault scene library, a plurality of matching scenes whose fault type matches the vehicle fault code are obtained; According to the vehicle scene data, scene decision is made on the plurality of matching scenes to obtain the target scene; According to the vehicle scene data, a plurality of current scene features of the vehicle are obtained; The current scene features are input into a preset scene decision model, and the scene decision model is used to make scene decision on the plurality of matching scenes to obtain the target scene; wherein, the scene decision model includes root nodes and leaf nodes corresponding to each fault type, the root node represents the judgment of one of the push conditions of the scene, and the leaf node represents the output of the fault scene judgment result. The method specifically constructs the scene decision model by the following steps:

2. The method of claim 1, wherein, According to the push condition of each scene previously configured in the fault scene library, the root nodes and leaf nodes corresponding to each fault type are constructed, and a decision tree model is constructed according to the root nodes and leaf nodes; The decision tree model is trained by using a preset training data set to obtain the scene decision model. The fault solution includes preferred solution and secondary solution; 3. The method of claim 1, wherein, Then, the preferred solution and the secondary solution previously configured in the target scene are sent to the vehicle terminal, so that the vehicle terminal pushes the preferred solution and the secondary solution to the user. The method further comprises the following steps: In response to the user input scheme selection instruction, the target scheme currently selected by the user is recorded; 4. The method of Claim 3, wherein, When the target scheme is the secondary solution, the fault solution of the target scene is updated to take the secondary solution as the updated preferred solution of the target scene. The method further comprises the following steps: In response to the user input fault request instruction, the voice data of the user is received, and the voice data is identified to obtain the identification text corresponding to the voice data; 5. The method of claim 1, wherein, The identification text is subjected to keyword extraction, and the plurality of extracted keywords are subjected to semantic expansion processing to obtain a plurality of fault identification texts; ​ ​ According to a plurality of fault identification texts, a plurality of fault types matching the fault identification texts are determined in the fault scene library, and push information containing the plurality of fault types is sent to the vehicle terminal, so that the vehicle terminal pushes the push information to the user; In response to a fault type selection instruction input by the user, a target fault type in the push information is determined; A plurality of scenes corresponding to the target fault type are obtained, and scene decision is performed on the plurality of scenes according to current vehicle scene data to obtain a decision scene; A fault solution pre-configured in the decision scene is sent to the vehicle terminal, so that the vehicle terminal pushes the fault solution to the user.

6. The method of claim 1, wherein, The method specifically obtains the vehicle fault code through the following steps: A vehicle body detection module pre-configured in the vehicle performs fault detection on the vehicle, and receives the vehicle fault code sent by the vehicle body detection module.

7. The method of claim 1, wherein, The vehicle scene data at least includes driver information, vehicle location data, in-vehicle light intensity, in-vehicle number of people, current vehicle speed, and current weather conditions.

8. A system for personalized push of vehicle fault resolution solutions, characterized in that, The cloud end and the vehicle terminal are included; The cloud end is configured to: According to the obtained vehicle fault code and vehicle scene data, a target scene matching the vehicle fault code and the vehicle scene data is obtained in a pre-set fault scene library; A fault solution pre-configured in the target scene is sent to the vehicle terminal; The vehicle terminal is configured to: Push the fault solution to the user; The cloud end is configured to obtain the target scene matching the vehicle fault code and the vehicle scene data in the pre-set fault scene library, specifically including: Based on the fault types pre-configured in each scene in the fault scene library, a plurality of matching scenes matching the fault types and the vehicle fault code are obtained; According to the vehicle scene data, scene decision is performed on the plurality of matching scenes to obtain the target scene; The cloud end is configured to perform scene decision on the plurality of matching scenes according to the vehicle scene data to obtain the target scene, specifically including: According to the vehicle scene data, a plurality of current scene features of the vehicle are obtained; The current scene features are input into a pre-set scene decision model, and the plurality of matching scenes are subjected to scene decision by the scene decision model to obtain the target scene; wherein the scene decision model includes a root node and a leaf node corresponding to each fault type, the root node represents the judgment of one of the push conditions of the scene, and the leaf node represents the output of the fault scene judgment result.

Images