Rapid positioning method and system for intelligent vehicle type diagnosis

Abstract

The invention provides a rapid positioning method and system for intelligent vehicle type diagnosis, and relates to the field of electric digital data processing. The method comprises the steps of determining a target vehicle type and a diagnosis function selected by a user for the first time through a client, then determining an interaction mode of shortcut keys and / or voice entries according to the information, and storing the interaction mode in a menu mapping database to establish a target mapping relationship. When information which is sent by a client and generated by clicking a shortcut key or inputting a voice entry by a user is received, the target mapping relation is retrieved from the database, a menu jump instruction is generated, and finally the instruction is sent to the client, so that the client displays a target vehicle type and a diagnosis function. By implementing the method, the user only needs to select the target vehicle model and the diagnosis function when the diagnosis function is used for the first time, and only needs to click the shortcut key or input the voice entry to quickly position the target vehicle model and the diagnosis function when the user wants to use the diagnosis function every time later, so that the operation efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of electronic digital data processing, and in particular to a rapid positioning method and system for intelligent vehicle model diagnosis. Background Art

[0002] As the number of cars on the road continues to increase, the demand for car diagnostic services continues to grow. Car owners and car repairers need to diagnose car faults quickly and accurately to ensure vehicle safety and performance.

[0003] Currently, vehicle diagnostic software on the market generally uses manual selection or VIN (Vehicle Identification Code) self-identification to enter the diagnostic interface. The VIN self-identification method requires the user to first start the vehicle diagnostic software application. There is usually a "VIN Identification" button or option on the software interface. The user clicks the button to start the VIN identification function. The user can manually enter the VIN or scan it. After the software receives the VIN code, it will parse the VIN code through the internal database or online query service to identify the vehicle's brand, model, year and other information. If the vehicle information is successfully identified, the software will automatically load the corresponding diagnostic parameters and interface.

[0004] However, for individual car owners, the existing methods require each diagnosis to select menus step by step or require multiple operations to enter diagnostic functions such as reading fault codes, clearing fault codes or data streams. The operation is cumbersome and time-consuming, affecting user experience and maintenance efficiency. Summary of the invention

[0005] The present application provides a rapid positioning method and system for intelligent vehicle model diagnosis, which is used to implement a method and system for rapid positioning of a specified vehicle model and diagnostic function by simply clicking a shortcut key or inputting a voice entry in the case where the vehicle model diagnosis operation in the prior art is cumbersome and inefficient, thereby improving the operational efficiency and convenience of vehicle model diagnosis.

[0006] In a first aspect, the present application provides a rapid positioning method for intelligent vehicle model diagnosis, which is applied to a server in a vehicle model diagnosis system, and the method includes: determining, through a client, a target vehicle model and a diagnostic function selected for the first time by a user; determining a corresponding interaction method based on the target vehicle model and the diagnostic function, the interaction method including shortcut keys and / or voice entries; storing the interaction method in a menu mapping database, and establishing a corresponding target mapping relationship; receiving user input information sent by the client, the user input information including information generated by the user clicking the shortcut key or entering the voice entry on the client; retrieving the target mapping relationship from the menu mapping database based on the user input information and generating a corresponding menu jump instruction; sending the menu jump instruction to the client so that the client displays the target vehicle model and the diagnostic function.

[0007] By adopting the above technical solution, the user only needs to select the target vehicle model and diagnostic function when using the diagnostic function for the first time. Every time he wants to use the diagnostic function thereafter, he only needs to click the shortcut key or enter the voice entry to quickly locate the target vehicle model and diagnostic function, which greatly improves the operating efficiency and effectively avoids the tedious search process among many vehicle models and function options in the traditional way, saving time and energy.

[0008] In combination with some embodiments of the first aspect, in some embodiments, after the step of storing the interaction mode in the menu mapping database and establishing the corresponding target mapping relationship, it also includes: collecting and recording the historical operation behavior data of the target user during the historical target vehicle model diagnosis process; determining the historical menu access path and historical stay time data of the target user based on the historical operation behavior data; building a user behavior model based on the historical menu access path and the historical stay time data; when receiving the user input information sent by the client again, tracking the real-time operation behavior of the target user on the client; predicting the user's next operation intention through the user behavior model combined with the real-time operation behavior; and recommending the predicted operation path to the client based on the next operation intention, so that the client displays the operation path.

[0009] By adopting the above technical solution, it is possible to proactively provide users with personalized operation path recommendations to improve the fluency and efficiency of user operations. For example, if a user often checks specific system parameters first when diagnosing a certain vehicle model, the system can recommend this path in advance in subsequent operations based on this habit, reducing user decision-making time and improving user experience.

[0010] In combination with some embodiments of the first aspect, in some embodiments, after the step of storing the interaction mode in a menu mapping database and establishing a corresponding target mapping relationship, it also includes: receiving multiple interaction modes for the same target vehicle model and the same diagnostic function from multiple clients; counting the number of interaction modes uploaded by multiple clients, and sorting the multiple interaction modes according to the number of interaction modes; determining the commonly used interaction modes for the target vehicle model and the diagnostic function according to the sorting result; when a request to establish an interaction mode is received from a new client that matches the target vehicle model and the diagnostic function, sending a commonly used interaction mode recommendation instruction to the new client, so that the menu interface of the new client displays information recommending the commonly used interaction mode; when the ranking of the number of times the commonly used interaction mode is used is reduced, canceling the information recommending the commonly used interaction mode in the menu interface of the new client.

[0011] By adopting the above technical solution, when a new client requests, commonly used interaction methods are recommended, which can improve the operation efficiency and accuracy of new users. If the number of times a commonly used interaction method is used decreases, the recommendation is cancelled to ensure the effectiveness and timeliness of the recommendation.

[0012] In combination with some embodiments of the first aspect, in some embodiments, after the step of receiving user input information sent by the client, it also includes: obtaining the voice entry instructions of the user during the use of the diagnostic function through voice recognition technology; analyzing the voice features in the voice entry instructions; judging the user's emotional state based on the voice features in combination with a voice emotion judgment model, the voice emotion judgment model is trained using multiple voice feature data sets and corresponding expressed emotional states, and the emotional state includes at least a negative emotional state; if the emotional state is a negative emotion, recording that the user experience of the corresponding diagnostic function needs to be improved; collecting multiple negative emotional feedbacks from all users, sorting the diagnostic functions according to the multiple negative emotional feedbacks, and obtaining a diagnostic function sorting result; determining the diagnostic function that needs to be improved first based on the diagnostic function sorting result, and optimizing the diagnostic function.

[0013] By adopting the above technical solutions, it is helpful to promptly discover problems and dissatisfactions encountered by users during use, optimize functions in a targeted manner, and improve user experience.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of receiving user input information sent by the client, it also includes: receiving problem queries raised by the user during the diagnosis process; collecting and recording the problem queries and corresponding problem operation paths; when receiving information consistent with the problem query again, controlling the client to operate according to the problem operation path.

[0015] By adopting the above technical solution, when a user encounters the same problem as before and wants to make a query, the server controls the client to operate according to the operation path of the problem, which can quickly solve the problems that the user encounters repeatedly and improve the user's diagnostic efficiency.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of sending the menu jump instruction to the client so that the client displays the target vehicle model and the diagnostic function, it also includes: determining the diagnostic result, which is the result data reflecting the fault condition generated after fault diagnosis; determining the relevant fault code and repair plan according to the diagnostic result, and the fault code is a code used to indicate the fault type; when the diagnostic result is a common fault, automatically matching a repair reference case that matches the common fault, and the repair reference case is a successful case for solving the common fault in the past; and sending the repair reference case to the client for display.

[0017] By adopting the above technical solutions, users are provided with practical solution references to help them solve vehicle failure problems more quickly.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of retrieving the target mapping relationship from the menu mapping database according to the user input information, it also includes: determining whether the target mapping relationship corresponding to the user input information exists; if not, sending a non-existence prompt message to the client, and the non-existence prompt message is used to prompt the user that the target mapping relationship does not exist, and prompt the user to establish a new target mapping relationship.

[0019] By adopting the above technical solution, the user is effectively prevented from being confused and making wrong operations due to the non-existence of the mapping relationship during use. Timely prompt information enables the user to quickly understand the situation and take corresponding measures, thus improving the usability and reliability of the system.

[0020] In a second aspect, the present application provides a vehicle type diagnostic system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the vehicle type diagnostic system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, the present application provides a computer-readable storage medium comprising instructions, which, when executed on a vehicle type diagnostic system, causes the vehicle type diagnostic system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, the present application provides a computer program product, which, when executed on a vehicle type diagnostic system, enables the vehicle type diagnostic system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The invention adopts a technical method of determining shortcut keys and / or voice entries according to the target vehicle model and diagnostic function selected by the user for the first time, and storing and establishing a mapping relationship. Therefore, the problem of cumbersome and inefficient vehicle model diagnosis operation in the prior art is effectively solved, and the user can quickly locate the target vehicle model and diagnostic function by simply clicking a shortcut key or inputting a voice entry, thereby greatly improving the technical effect of operating efficiency and convenience.

[0024] 2. The technical means of collecting and recording the historical operation behavior data of the target user, building a user behavior model to predict the user's next operation intention and recommend an operation path are adopted. Therefore, the problem of lack of personalized guidance for user operations in the existing technology is effectively solved, thereby achieving the technical effect of providing users with personalized operation experience and improving operation fluency and efficiency.

[0025] 3. The method uses voice recognition technology to obtain user voice entry instructions, analyzes voice features and combines voice emotion judgment models to judge the user's emotional state, and then optimizes the diagnostic function. Therefore, it effectively solves the problem that it is difficult to detect user dissatisfaction with the diagnostic function in the existing technology, and thus achieves the technical effect of timely discovering problems and optimizing diagnostic functions to improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of a rapid positioning method for intelligent vehicle type diagnosis in an embodiment of the present application; Figure 2 is another flow chart of the rapid positioning method of intelligent vehicle model diagnosis in the embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a physical device of a vehicle type diagnostic system in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more listed items.

[0028] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0029] For ease of understanding, the method provided in this embodiment is described in detail below.

[0030] The vehicle model diagnosis system can be set up at the management department. The vehicle model diagnosis system includes a built-in server, which is connected to multiple vehicle model diagnosis software clients. A client with a touch screen and voice recognition function can be set at a preset position inside each car, such as between the main driver and the co-driver. The user can perform vehicle model diagnosis queries on the client. In addition, the client can also be a remote display terminal with a data connection to the vehicle, such as a smart phone. The user operates on the vehicle model diagnosis client, and the client provides a user interaction interface. The user can also set voice entries through voice input. The client uploads the user's shortcut keys, voice entries, and the corresponding target vehicle model and diagnostic function to the server for the diagnosis process.

[0031] Combine the following Figure 1 , describes the process of the method provided by this implementation. Figure 1 , which is a flow chart of a rapid positioning method for intelligent vehicle model diagnosis in an embodiment of the present application.

[0032] S101, determining, through a client, a target vehicle model and a diagnostic function selected for the first time by a user; When the user starts the vehicle model diagnostic function through the preset channel (such as software APP) in the client, if the client detects that the number of times the user has used the vehicle model diagnostic function in history is 0, it is determined that the user is using the vehicle model diagnostic function for the first time, and the vehicle model selection interface will be displayed. This interface design needs to take into account the user's usage habits and convenience. For example, a drop-down menu, search box or graphical vehicle model display method can be used. Assuming that the client uses a drop-down menu, the menu lists common car brands. After the user clicks on a brand, a specific model list under the brand will pop up. The user then selects a model to determine it as the target model. After receiving the target model, the server will search for the diagnostic function list corresponding to the target model in the existing diagnostic function directory database, and the server will return the diagnostic function list to the client. The client displays the diagnostic function list, the user selects the diagnostic function to be used, and the client sends the diagnostic function selected by the user to the server. After receiving the target model and diagnostic function, the server determines that the user is using it for the first time, and records the user's unique ID, as well as the target model and diagnostic function selected by the user.

[0033] S102, determining a corresponding interaction method according to the target vehicle model and the diagnostic function, the interaction method including shortcut keys and / or voice entries; After determining the user's target vehicle model and diagnostic function, the server needs to generate an interactive method for the target to facilitate subsequent operations by the user. The server provides the client with a shortcut key setting interface and a voice entry setting interface. In the setting interface, the user can customize shortcut keys and voice entries, such as the fault code reading function of the Mercedes-Benz A series B system, and set the corresponding shortcut keys (such as "Mercedes-Benz AB-Read Code") or voice entries (such as "Mercedes-Benz A series B system Read Fault Code").

[0034] In some embodiments, if the user is in a noisy environment, the way the user outputs speech will be disturbed to a certain extent. In this case, in addition to traditional audio signals, the server can also use other sensor information from the client, such as changes in the user's mouth shape captured by the camera, gestures when the user operates the device, etc. By fusing these multimodal information with the voice signal, the user's intention can be understood more accurately. For example, when the server detects that the voice signal spoken by the user is greatly disturbed in a noisy environment, it can be combined with the changes in the user's mouth shape captured by the camera to assist in determining what the user said.

[0035] At the same time, gesture information can be used to further determine the user's operating intention. Specifically, the camera can be installed on the front or side of the device to cover the user's operating area at a suitable angle. For example, for a tablet-style diagnostic client, the front camera can be used to capture the user's facial and upper body gestures; if the device has a rotatable or multi-angle adjustable bracket, additional cameras can be added in advance at the appropriate position to obtain more comprehensive gesture information from different angles. The accelerometer and gyroscope are built into the device corresponding to the client to detect the motion state and direction changes of the device itself. They can assist in determining the gestures of the user holding the device, such as the tilt and rotation of the device. For example, when the user says "check the engine fault code" and makes a gesture pointing to the engine, the server can more accurately understand that the user wants to check the engine-related fault code, not the fault code of other systems. Accurate voice entries can be obtained in a variety of ways.

[0036] In some embodiments, a communication connection can be established between servers of multiple clients, and the server can receive customized interaction methods for the same vehicle model and diagnostic function from different users, that is, for a specific diagnostic function of a specified vehicle model, different clients submit their own defined interaction methods, such as voice entries or shortcut keys. The server needs to include logic to parse the input and determine whether it is a different interaction method for the same target vehicle model and function. After the server receives the above-mentioned different interaction methods for the same target, it is necessary to perform a statistical calculation to count the total number of times each interaction method is submitted for use by each client, and sort these interaction methods based on the statistical number of times, with the most times ranked first. After obtaining the ranking results of the number of uses of all candidate interaction methods for the diagnostic function of the target vehicle model, the server can determine the most frequently used one or several interaction methods, that is, the most recognized by users, and determine them as the "common interaction methods" corresponding to the target.

[0037] When a new user wants to use the vehicle model diagnostic function for the first time and sends a request to the server to establish an interaction method, the server will first check whether the target vehicle model and function corresponding to the request already have a certain common interaction method. If so, an instruction containing the recommended common interaction method is sent to the new client, so that the client menu interface displays prompt information such as "The system recommends using 'Mercedes-Benz AB-Read Code'". Guide new users to directly use the common interaction method to improve the operation efficiency of new users. The server needs to continuously and dynamically count the usage of each interaction method. If the frequency of use of a common interaction method originally recommended is significantly reduced and the ranking declines, the common method needs to be updated in time. When the ranking of the original common method drops below a certain threshold, the server cancels the instruction to recommend the method, and the client also synchronously offlines the corresponding recommendation information to avoid recommending outdated interaction methods to users. Recommending common interaction methods to new users allows new users to directly use more efficient methods without defining them themselves, which can improve diagnostic efficiency.

[0038] S103, storing the interaction mode in a menu mapping database, and establishing a corresponding target mapping relationship; After receiving the interaction method submitted by the client, the server will store the interaction method and the corresponding vehicle model and diagnostic function in the menu mapping database on the server side. The database will establish a mapping relationship between the interaction method and the vehicle model and function, that is, when the user enters the interaction method, the mapped target vehicle model and diagnostic function can be found. For example, when the interaction method submitted by the user is "Mercedes-Benz S-Class automatic parking diagnosis", the server will add a mapping relationship record to the database to store the mapping relationship between the interaction method and the "Mercedes-Benz S-Class" vehicle model and the "automatic parking diagnosis" function. The database adopts an extensible structure, which can continuously store the newly added interaction methods submitted by the client, and establish and update the mapping relationship in real time, providing storage support for the personalized interaction method requirements of different users.

[0039] S104, receiving user input information sent by the client, where the user input information includes information generated by the user clicking the shortcut key or inputting the voice entry on the client; After the user submits the interaction mode through the client, when the user clicks the corresponding set shortcut key on the client or inputs the set voice term through voice in the subsequent use process, the client will send the user input information to the server.

[0040] In some embodiments, the server can identify user input information to obtain verbal questions raised by the user when using the vehicle diagnostic function, such as "Why does it show that the battery life is insufficient?". At the same time, the server can also receive question query requests entered by the user through typing. These question queries reflect the actual confusion or problems encountered by the user in the process of operating the diagnostic function. For each question query received, the server needs to locate the corresponding operation path where the problem occurs. That is, identify which function operation step in the entire diagnostic process the question query appears after, for example, determine that the above-mentioned battery problem appears after the battery test. The server will continue to monitor the newly input user question query information. If it is determined that there is a high similarity with a certain historical question query that has been recorded (such as a keyword matching degree of more than 80%), it is determined that the corresponding question is repeated. At this time, the server generates a control instruction according to the operation path corresponding to the historical question record, and sends the control instruction to the client. The instruction will include enabling the diagnostic function of the corresponding path and displaying the operation of each step of the diagnostic process in sequence. After receiving the instruction, the client automatically turns on the diagnostic function and guides the user to operate according to the established process to solve the repeated problem query.

[0041] S105, retrieving the target mapping relationship from the menu mapping database according to the user input information and generating a corresponding menu jump instruction; The server will establish a reverse index for the menu mapping database. The reverse index uses all interactive keywords (including customized shortcut keys and voice terms) that the user may enter as index items, and records the target vehicle model and diagnostic function mapped to each index item, so that the unique target mapping relationship can be quickly located through the interactive keywords. When looking for a matching target mapping relationship, the edit distance between the keywords in the user input information and the keywords in all interactive methods stored in the database is calculated, and the keyword record of the interactive method with the smallest edit distance to the user input keyword is returned, and the target vehicle model and diagnostic function mapped to the record are obtained. If an exact matching target mapping relationship is found, the server will generate a menu jump instruction based on the matched vehicle model and function information. The instruction can contain the unique ID of the vehicle model and the unique ID of the function. The server will also maintain a command template library. Different types of command templates correspond to different clients. The server needs to select the corresponding command template according to the type of the current client, and insert the found vehicle model ID and function ID into the command template, and finally generate a standard menu jump instruction that can be recognized by the client system.

[0042] The server verifies the queried target mapping relationship again to avoid returning invalid results. It checks whether the vehicle model information and diagnostic function information in the relationship match the known vehicle model directory and function directory in the verification database. The verification database contains a full amount of vehicle model information and function information, which is the basis for judging whether a mapping relationship is correct. If the information in the mapping relationship cannot find a corresponding match in the verification database, it can be judged that the relationship is invalid, and the user may have mistakenly set a non-existent mapping. The server will actively generate a non-existent prompt message, which will inform the user that the relationship does not exist and cannot be jumped. At the same time, it will also give a suggestion for resetting so that the user can establish a new valid mapping relationship. Finally, the server directly sends the prompt message to the client corresponding to the requesting user without a jump instruction. The client will display the prompt message to remind the user that the current interaction method cannot find the target.

[0043] By actively sending a non-existent prompt, erroneous jumps can be avoided, and users can be guided in time to correct incorrect mapping relationships, thereby establishing new correct relationships and improving the reliability and usability of the system.

[0044] S106: Send the menu jump instruction to the client so that the client displays the target vehicle model and the diagnostic function.

[0045] The server calls the internal interface jump program to parse the menu jump instruction and extract the parameters in the instruction, including the vehicle model ID and function ID. The client will locally maintain a vehicle model and interface correspondence table, and the vehicle model ID can be used to locate the diagnostic interface corresponding to the vehicle model. The client will also maintain a function and menu correspondence table, and the function ID can be used to locate the menu option of the function in the corresponding interface. Therefore, the client can open the interface that matches the vehicle model ID according to the parameters of the menu jump instruction, and automatically jump to the menu item that matches the function ID, and finally quickly locate the specified diagnostic function of the target vehicle model. On the client interface, the user can see the jump result triggered by the menu jump instruction, and directly enter the expected diagnostic function for subsequent operations, without the need to manually search step by step, which simplifies the user's operation process.

[0046] In the above embodiment, the user can quickly locate the target after entering the keyword, and directly access the specified diagnostic function with one click, which greatly improves the efficiency of vehicle model diagnosis.

[0047] In some embodiments, after step S106, various diagnostic data of the vehicle are obtained after vehicle diagnosis, and the diagnostic data includes status parameter readings of various systems of the vehicle. These parameter readings can reflect whether the system or component is within the normal working range. The server has a parameter standard range database of the automobile system. By comparing the actual parameter readings obtained by the diagnosis with the standard range data, it can be determined whether the parameters are abnormal, so as to locate the fault situation and determine the diagnosis result. Different faults correspond to different abnormal parameter characteristics. The server also has a fault feature database, which matches the parameter abnormality with various fault modes. By matching the parameter abnormality with the fault mode, the most likely fault can be determined. In addition to parameter judgment, the diagnostic data also includes a dedicated fault code. Fault codes with different numbers correspond to different fault types. The server has a fault code interpretation database, which can directly find the corresponding fault type according to the fault code in the diagnostic data. Based on the parameter abnormality information and fault code judgment, the server can comprehensively analyze the root cause and determine the specific fault that occurred. For some common faults with a high frequency of occurrence, the server can collect and record the repair cases that have solved the fault in the past as a repair reference. When the diagnostic result is detected as this type of common fault, the relevant case library can be automatically searched to find and extract cases similar to the common fault. These real cases can provide more specific and intuitive reference ideas than general maintenance solutions. For example, a specific solution idea for an engine with excessive pressure. After obtaining the actual maintenance cases corresponding to common faults, the server can transmit these cases to the client in the form of text, pictures or videos, and display these reference cases in the form of cards or lists on the client's diagnostic result display interface, which is convenient for users to intuitively understand and refer to, and solve the fault faster.

[0048] In some embodiments, when a vehicle has a certain recurring fault, the user can collect relevant operational behavior data during multiple attempts to diagnose and solve the fault. The server can record the user's various operational behaviors in real time when the user performs vehicle model diagnosis to build a historical diagnostic behavior data set for the user. The specific behavioral data that can be recorded include: the order of interfaces or menu pages visited by the user, that is, the historical page access path; the length of time the user stays on each page or operation; the voice interaction terms selected by the user; the sequence of diagnostic functions commonly used by the user, and other information, extract the user's historical menu access path and the length of time on each menu. These detailed behaviors can accurately reflect the user's personalized preferences and diagnostic habits, and all behavioral data can be associated with the unique ID of the user's client for storage. Based on the above-mentioned multiple menu access paths and length of stay data, a user behavior model is constructed using a machine learning algorithm. The user behavior model can learn the patterns and relationships between these data to form a prediction of the user's diagnostic behavior habits. When the user uses the diagnostic system again, the server can track the user's current actual operation behavior in real time to obtain the current page access path and stay time information. The server inputs the user's real-time operation behavior into the pre-built user behavior model. The model can predict the user's most likely next operation intention based on the user's learned historical behavior pattern and the current operation. For example, the model analyzes that the user has stayed on the "Power System" page for a long time. Historically, such behavior usually indicates that the user will visit the "Engine Diagnosis" page or function next. Therefore, the model can predict that the user may want to view the engine status or information. After obtaining the user's possible next operation intention, the server can actively provide operation suggestions to the client, recommend functions or page access paths that match the intention, and guide the user's next operation.

[0049] It should be noted that in the entire system, the server's voice recognition of the client's corresponding user and the acquisition of the user's historical operation data are not performed at will. The server will only perform these operations with the user's explicit consent in advance, which can fully protect the user's privacy and right to choose independently.

[0050] In some scenarios, if the fault code or diagnostic result given by the diagnostic system is inaccurate or unclear, users may doubt and be dissatisfied with the diagnostic function. New users are unfamiliar with the vehicle diagnostic system and may encounter various operational difficulties and comprehension barriers during use, which may lead to impatience, and these emotions often imply that the system fails to meet user expectations in some aspects. In this case, the user's dissatisfaction can be accurately captured by analyzing voice emotions, such as the cumbersome operation of the diagnostic function causing user impatience, or the unclear diagnostic results confusing the user, etc., so as to make targeted improvements and improve user satisfaction with the system.

[0051] After combining the above scenarios, the following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the rapid positioning method for intelligent vehicle model diagnosis in an embodiment of the present application.

[0052] S201, obtaining a user's voice entry instruction during the use of a diagnosis function through voice recognition technology; The server will monitor the client's audio input in real time. When the user speaks while using the vehicle diagnostic function, the client's microphone will collect the voice signal and use voice recognition technology to identify the voice entry instructions.

[0053] In order to more accurately determine whether the server is collecting the client's user, biometric recognition technology can also be used to detect in real time whether the voice command is issued by the target user to avoid collecting other people's voice output. The specific method is: collect the voiceprint characteristics of the target user in advance, and when a voice command is detected, use voiceprint recognition to confirm the identity of the speaker. If the recognition matches the voiceprint characteristics of the target user, subsequent voice-to-text processing will be performed. This solution can effectively filter out voice input other than the target user and ensure the accuracy of voice sentiment analysis.

[0054] S202, analyzing the voice features in the voice entry instruction; Parameters of the sound data of the voice entry instruction are extracted to obtain the acoustic characteristic parameters of the voice signal, such as the data variation range of the pitch, the intonation, the strength of the volume, and other characteristics.

[0055] S203, judging the emotional state of the user according to the speech feature in combination with a speech emotion judgment model, wherein the speech emotion judgment model is trained using a plurality of speech feature data sets and corresponding expressed emotional states, wherein the emotional state at least includes a negative emotional state; The server combines various acoustic feature parameters extracted from the speech signal and inputs a pre-trained speech emotion judgment model. The speech emotion judgment model can judge the emotional state expressed by the speech. During the training process of the speech emotion judgment model, a large-scale speech data set with emotional labels is used for supervised learning. These data sets contain speech samples of different groups expressing various emotional states, such as calm, happy, sad, angry, etc. It is also possible to collect the speech generated by actual users when using the diagnosis function, invite professional scorers to label the emotions of the speech, obtain the data set of the user's real speech emotion, train the deep neural network model with rich labeled speech data sets, and establish the mapping between speech features and emotional labels. The model can analyze the intonation, pitch, volume and other features of the input speech to judge the emotional state it expresses. For example, a speech with obvious ups and downs may express anxiety, and a loud volume may express anger. The speech emotion judgment model can at least judge negative emotional states, such as anxiety, confusion, boredom, etc., to support the subsequent improvement of the diagnosis function for negative experiences.

[0056] In order to expand the types of emotions to be judged, facial expressions can also be added as additional judgment basis. Specifically, the client can capture the user's facial expression image in real time through the camera, and the server extracts expression features, such as the degree of mouth opening, eyebrow position, etc., and inputs the pre-trained facial expression recognition model to obtain expression classification results, such as "angry" and "confused" expression labels. The model is trained with a large number of face image data sets containing different facial expressions. The facial expression results can be integrated with the speech emotion results, that is, the outputs of the speech emotion judgment model and the facial expression judgment model are combined to perform emotion scoring and obtain the most likely emotional state corresponding to the current speech sentence.

[0057] S204, if the emotional state is a negative emotion, then the user experience of the corresponding diagnostic function needs to be improved; If the judgment result is a negative emotional state, it can be determined that the diagnostic function that the user is using when the emotion is generated may have a problem, causing the user to have an emotional reaction of dissatisfaction. The failed diagnostic function may be too complicated to operate, or the results given are inaccurate, causing user confusion, etc. In order to collect overall user experience data to guide subsequent optimization, the server needs to record the diagnostic function that the user is using when the current emotion is judged, that is, record the feedback of the diagnostic function corresponding to the negative emotion, indicating that the user experience of this function is not good, and it is necessary to improve this function in a targeted manner to improve user satisfaction.

[0058] For example, if the judgment result is "anxious", the server can check the diagnostic process log and analyze the diagnostic operation steps that the user is performing when the anxious emotion judgment appears. It may be that the user is performing a complex subsystem status detection. This link requires the user to follow the prompts step by step, and there are many page jumps. The user may feel anxious because the process is too long. Consider simplifying the diagnostic process, strengthening the guidance of each step, and reducing the user's anxiety. If the judgment result is "confused", the user's current diagnostic content can be checked. If an unclear or difficult to understand diagnostic result has just been given, it is possible that the user is confused about the result due to improper expression of the result. This requires optimizing the presentation of the result and using clearer and more straightforward statements for explanation.

[0059] S205, collecting multiple negative emotion feedbacks from all users, sorting the diagnostic functions according to the multiple negative emotion feedbacks, and obtaining a diagnostic function sorting result; The server can continuously track the negative emotional feedback generated by all users connected to the client when using the diagnostic function, and collect the number of negative emotions corresponding to each diagnostic function. If a diagnostic function causes more negative emotions, it means that the problem with the function is more serious and the user satisfaction is lower.

[0060] The server uses diagnostic functions as the statistical dimension, and summarizes and sorts the number of negative emotional feedbacks corresponding to all functions. The sorting results can intuitively reflect the level of user satisfaction with different diagnostic functions and the quality of user experience. The diagnostic functions with the most negative emotional feedback in the sorting results are the functions that need to be given priority for improvement and optimization. For example, the number of negative feedbacks on the function of reading engine fault codes appears very often, and its ranking result is high, indicating that there are many problems with this function that cause user dissatisfaction, such as complex interface operation, long loading waiting time, and difficult to understand result format. This can be used as a priority direction for server improvement.

[0061] S206: Determine the diagnostic function that needs to be improved first according to the diagnostic function ranking result, and optimize the diagnostic function.

[0062] According to the results of sorting the number of negative emotional feedback, the server can clearly identify the diagnostic functions or functional modules that need to be optimized and improved first. For these functions with negative feedback, the server development team can perform code optimization, algorithm improvement, interface adjustment, etc. For example, for the "read engine fault code" function with the most feedback, a clearer and more concise code query interface can be set up, and the diagnostic results can be described in a language that non-professionals can understand. The background diagnostic algorithm can also be improved to provide more accurate speculation on the cause of the fault.

[0063] In addition, if it is found that most of the negative feedback appears on a certain page or operation step in the diagnostic process, the design of the page or step can be specifically examined to find the specific cause of user confusion or discomfort, and the interface or guidance information can be redesigned to reduce the user's negative emotions. At the same time, the changes in user satisfaction corresponding to each function after optimization can be continuously tracked. If the number of negative feedbacks for a certain function decreases significantly, it means that the optimization is successful, and it can be promoted and applied to the optimization of other functions, forming a virtuous circle and continuously improving the overall user experience of the system.

[0064] Since the technical solution is adopted for obtaining user voice commands and analyzing voice features, combining the voice emotion judgment model to judge the user's emotional state, and then finding the diagnostic functions that cause negative emotions and optimizing them, it effectively solves the problems in the existing technology that it is difficult to accurately obtain user usage experience feedback and difficult to actively discover and improve problematic diagnostic functions. It achieves the technical effect of being able to accurately judge the user's emotional state, find the diagnostic functions that cause negative emotions, and make targeted optimization and improvements, thereby improving user satisfaction and providing more humane and intelligent vehicle diagnosis services.

[0065] The vehicle type diagnosis system in the embodiment of the present invention is described below from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of a vehicle type diagnostic system in an embodiment of the present application.

[0066] It should be noted that Figure 3 The structure of the vehicle type diagnosis system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0067] like Figure 3 As shown, the vehicle diagnostic system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0068] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0069] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0070] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0071] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0072] Specifically, the vehicle type diagnosis system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the rapid positioning method for intelligent vehicle type diagnosis provided in the above embodiment is implemented.

[0073] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the vehicle type diagnosis system described in the above embodiment; or may exist independently without being assembled into the vehicle type diagnosis system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the vehicle type diagnosis system, the vehicle type diagnosis system implements the rapid positioning method of intelligent vehicle type diagnosis provided in the above embodiment.

[0074] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0075] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0076] 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.

Claims

1. A rapid positioning method for intelligent vehicle type diagnosis, applied to vehicle type diagnosis system, characterized in that: The method comprises: Determine the target vehicle model and diagnostic function selected by the user for the first time through the client; Determining a corresponding interaction mode according to the target vehicle model and the diagnostic function, the interaction mode including shortcut keys and / or voice entries; Storing the interaction mode in a menu mapping database and establishing a corresponding target mapping relationship; Receiving user input information sent by the client, the user input information including information generated by the user clicking the shortcut key or inputting the voice entry at the client; Retrieving the target mapping relationship from the menu mapping database according to the user input information and generating a corresponding menu jump instruction; The menu jump instruction is sent to the client so that the client displays the target vehicle model and the diagnostic function.

2. The method according to claim 1, characterized in that After the step of storing the interaction mode in the menu mapping database and establishing the corresponding target mapping relationship, the method further includes: Collect and record the historical operation behavior data of the target user during the diagnosis process of the historical target vehicle model; Determine the target user's historical menu access path and historical stay duration data based on the historical operation behavior data; Constructing a user behavior model based on the historical menu access path and the historical stay duration data; When receiving the user input information sent by the client again, tracking the real-time operation behavior of the target user on the client; Predicting the user's next operation intention by combining the user behavior model with the real-time operation behavior; The predicted operation path is recommended to the client according to the next operation intention, so that the client displays the operation path.

3. The method according to claim 1, characterized in that After the step of storing the interaction mode in the menu mapping database and establishing the corresponding target mapping relationship, the method further includes: Receive multiple interactive modes of the same target vehicle model and the same diagnostic function from multiple clients; Counting the number of interaction methods uploaded by multiple clients, and sorting the multiple interaction methods according to the number of interaction methods; Determining a common interaction mode between the target vehicle type and the diagnostic function according to the sorting result; When receiving a request for establishing an interaction mode from a new client matching the target vehicle model and the diagnostic function, sending a common interaction mode recommendation instruction to the new client, so that a menu interface of the new client displays information recommending the common interaction mode; When the ranking of the number of times the commonly used interaction methods are used decreases, the information recommending the commonly used interaction methods in the menu interface of the new client is cancelled.

4. The method according to claim 1, characterized in that After the step of receiving the user input information sent by the client, the method further includes: Acquire the user's voice entry instructions when using the diagnostic function through voice recognition technology; Analyzing the voice features in the voice entry instruction; Determine the user's emotional state based on the speech feature in combination with a speech emotion judgment model, wherein the speech emotion judgment model is trained using a plurality of speech feature data sets and corresponding expressed emotional states, wherein the emotional state includes at least a negative emotional state; If the emotional state is a negative emotion, the user experience of recording the corresponding diagnostic function needs to be improved; Collect multiple negative emotion feedbacks from all users, sort the diagnostic functions according to the multiple negative emotion feedbacks, and obtain the diagnostic function sorting results; The diagnostic functions that need to be improved first are determined according to the diagnostic function ranking results, and the diagnostic functions are optimized.

5. The method according to claim 1, characterized in that After the step of receiving the user input information sent by the client, the method further includes: Receive questions and inquiries from users during the diagnosis process; Collect and record the problem query and corresponding problem operation path; When receiving again a query that matches the question query, the client is controlled to operate according to the question operation path.

6. The method according to claim 1, characterized in that After the step of sending the menu jump instruction to the client so that the client displays the target vehicle model and the diagnostic function, the method further includes: Determine a diagnosis result, wherein the diagnosis result is result data reflecting the fault condition generated after the fault diagnosis is performed; Determine relevant fault codes and maintenance plans according to the diagnosis results, wherein the fault codes are codes used to indicate the type of fault; When the diagnosis result is a common fault, a maintenance reference case that matches the common fault is automatically matched, and the maintenance reference case is a successful case that solved the common fault in the past; The maintenance reference case is sent to the client for display.

7. The method according to claim 1, characterized in that After the step of retrieving the target mapping relationship from the menu mapping database according to the user input information, the method further includes: Determine whether the target mapping relationship corresponding to the user input information exists; If it does not exist, a non-existence prompt message is sent to the client, where the non-existence prompt message is used to prompt the user that the target mapping relationship does not exist and to prompt the user to establish a new target mapping relationship.

8. A vehicle type diagnosis system, characterized in that: The vehicle type diagnostic system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the vehicle type diagnostic system to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a vehicle type diagnostic system, the vehicle type diagnostic system is caused to execute the method as claimed in any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a vehicle type diagnosis system, the vehicle type diagnosis system is enabled to execute the method according to any one of claims 1 to 7.

Images